Compare commits

...

34 Commits

Author SHA1 Message Date
blob42
2b776bec55 searx: add install instructions details, update doc and notebooks 2023-03-03 20:33:14 +01:00
Jon Luo
882f7964fb
fix sql misinterpretation of % in query (#1408)
% is being misinterpreted by sqlalchemy as parameter passing, so any
`LIKE 'asdf%'` will result in a value error with mysql, mariadb, and
maybe some others. This is one way to fix it - the alternative is to
simply double up %, like `LIKE 'asdf%%'` but this seemed cleaner in
terms of output.
Fixes #1383
2023-03-02 16:03:16 -08:00
JonLuca De Caro
443992c4d5
[Docs] Add missing word from prompt docs (#1406)
The prompt in the first example of the quickstart guide was missing `for
`
2023-03-02 16:02:54 -08:00
Eugene Yurtsev
a83a371069
Minor documentation update in initialize_agent (#1397)
Updating documentation in initialize_agent.

One thing that could benefit from further clarification is the
responsibility
breakdown by between an AgentExecutor vs. an Agent. The documentation
for an
AgentExecutor does not clarify that. From the class attributes, it
appears that
executor has access to the tools, while the agent is only aware of the
tool
names. Anyway, additional clarification would be beneficial on the
AgentExecutor class.
2023-03-02 11:46:35 -08:00
Nuno Campos
499e76b199
Allow the regular openai class to be used for ChatGPT models (#1393)
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-03-02 09:04:18 -08:00
Kacper Łukawski
8947797250
Return Cohere embeddings as lists of floats (#1394)
This PR fixes the types returned by Cohere embeddings. Currently, Cohere
client returns instances of `cohere.embeddings.Embeddings`. Since the
transport layer relies on JSON, some numbers might be represented as
ints, not floats, which happens quite often. While that doesn't seem to
be an issue, it breaks some pydantic models if they require strict
floats.
2023-03-02 09:02:10 -08:00
Jason Gill
1989e7d4c2
Update examples to prevent confusing missing _type warning (#1391)
The YAML and JSON examples of prompt serialization now give a strange
`No '_type' key found, defaulting to 'prompt'` message when you try to
run them yourself or copy the format of the files. The reason for this
harmless warning is that the _type key was not in the config files,
which means they are parsed as a standard prompt.

This could be confusing to new users (like it was confusing to me after
upgrading from 0.0.85 to 0.0.86+ for my few_shot prompts that needed a
_type added to the example_prompt config), so this update includes the
_type key just for clarity.

Obviously this is not critical as the warning is harmless, but it could
be confusing to track down or be interpreted as an error by a new user,
so this update should resolve that.
2023-03-02 07:39:57 -08:00
Harrison Chase
dda5259f68
bump version to 0.0.99 (#1390) 2023-03-02 07:25:59 -08:00
Kacper Łukawski
f032609f8d
Add recursive parameter to DirectoryLoader (#1389)
This PR allows loading a directory recursively.
2023-03-02 07:06:26 -08:00
Kacper Łukawski
9ac442624c
Add Qdrant named arguments (#1386)
This PR:
- Increases `qdrant-client` version to 1.0.4
- Introduces custom content and metadata keys (as requested in #1087)
- Moves all the `QdrantClient` parameters into the method parameters to
simplify code completion
2023-03-02 07:05:14 -08:00
Francisco Ingham
34abcd31b9
remove limit clause from prompt for compatibility with ms sql server (#1385)
For reference see:
8a35811556

Co-authored-by: Francisco Ingham <>
2023-03-02 07:02:42 -08:00
Ankush Gola
fe30be6fba
add async and streaming support to OpenAIChat (#1378)
title says it all
2023-03-01 21:55:43 -08:00
Lakshya Agarwal
cfed0497ac
Minor grammatical fixes (#1325)
Fixed typos and links in a few places across documents
2023-03-01 21:18:09 -08:00
Ryan Dao
59157b6891
Bug: Fix Python version validation in PythonAstREPLTool (#1373)
The current logic checks if the Python major version is < 8, which is
wrong. This checks if the major and minor version is < 3.9.
2023-03-01 21:15:27 -08:00
Harrison Chase
e178008b75
Harrison/track token usage (#1382)
Co-authored-by: Zak King <zaking17@gmail.com>
2023-03-01 21:15:13 -08:00
Harrison Chase
1cd8996074
Harrison/summarizer chain (#1356)
Co-authored-by: Tim Asp <707699+timothyasp@users.noreply.github.com>
2023-03-01 20:59:07 -08:00
yakigac
cfae03042d
Fix the openaichat example (#1377)
The example was wrong.
2023-03-01 18:24:32 -08:00
Harrison Chase
4b5e850361
chatgpt wrapper (#1367) 2023-03-01 11:47:01 -08:00
Harrison Chase
4d4b43cf5a
fix doc names (#1354) 2023-03-01 09:40:31 -08:00
Harrison Chase
c01f9100e4
bump version to 0097 (#1365) 2023-03-01 08:20:24 -08:00
Christie Jacob
edb3915ee7
typo in vectorstores (#1362) 2023-03-01 07:21:37 -08:00
Harrison Chase
fe7dbecfe6
pandas and csv agents (#1353) 2023-02-28 22:19:11 -08:00
Harrison Chase
02ec72df87
improve docs (#1351) 2023-02-28 21:37:18 -08:00
Jon Luo
92ab27e4b8
sql doc formatting (#1350)
My bad, missed a few tabs between the two PRs
2023-02-28 19:54:46 -08:00
Ankush Gola
82baecc892
Add a SQL agent for interacting with SQL Databases and JSON Agent for interacting with large JSON blobs (#1150)
This PR adds 

* `ZeroShotAgent.as_sql_agent`, which returns an agent for interacting
with a sql database. This builds off of `SQLDatabaseChain`. The main
advantages are 1) answering general questions about the db, 2) access to
a tool for double checking queries, and 3) recovering from errors
* `ZeroShotAgent.as_json_agent` which returns an agent for interacting
with json blobs.
* Several examples in notebooks

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-02-28 19:44:39 -08:00
Jon Luo
35f1e8f569
separate columns by tabs instead of single space in sql sample rows (#1348)
Use tabs to separate columns instead of a single space - confusing when
there are spaces in a cell
2023-02-28 18:59:53 -08:00
kurehajime
6c629b54e6
Fixed arguments passed to InvalidTool.run(). (#1340)
[InvalidTool.run()](72ef69d1ba/langchain/agents/tools.py (L43))
returns "{arg}is not a valid tool, try another one.".
However, no function name is actually given in the argument.
This causes LLM to be stuck in a loop, unable to find the right tool.

This may resolve these Issues.
https://github.com/hwchase17/langchain/issues/998
https://github.com/hwchase17/langchain/issues/702
2023-02-28 18:58:23 -08:00
James Brotchie
3574418a40
Fix link in summarization.md (#1344)
"Utilities for working with Documents" was linking to a non-useful page.
Re-linked to the utils page that includes info about working with docs.
2023-02-28 18:58:12 -08:00
Jon Luo
5bf8772f26
add option to use user-defined SQL table info (#1347)
Currently, table information is gathered through SQLAlchemy as complete
table DDL and a user-selected number of sample rows from each table.
This PR adds the option to use user-defined table information instead of
automatically collecting it. This will use the provided table
information and fall back to the automatic gathering for tables that the
user didn't provide information for.

Off the top of my head, there are a few cases where this can be quite
useful:
- The first n rows of a table are uninformative, or very similar to one
another. In this case, hand-crafting example rows for a table such that
they provide the good, diverse information can be very helpful. Another
approach we can think about later is getting a random sample of n rows
instead of the first n rows, but there are some performance
considerations that need to be taken there. Even so, hand-crafting the
sample rows is useful and can guarantee the model sees informative data.
- The user doesn't want every column to be available to the model. This
is not an elegant way to fulfill this specific need since the user would
have to provide the table definition instead of a simple list of columns
to include or ignore, but it does work for this purpose.
- For the developers, this makes it a lot easier to compare/benchmark
the performance of different prompting structures for providing table
information in the prompt.

These are cases I've run into myself (particularly cases 1 and 3) and
I've found these changes useful. Personally, I keep custom table info
for a few tables in a yaml file for versioning and easy loading.

Definitely open to other opinions/approaches though!
2023-02-28 18:58:04 -08:00
Harrison Chase
924bba5ce9
bump version (#1342) 2023-02-28 08:48:32 -08:00
Harrison Chase
786852e9e6
partial variables (#1308) 2023-02-28 08:40:35 -08:00
Tim Asp
72ef69d1ba
Add new iFixit document loader (#1333)
iFixit is a wikipedia-like site that has a huge amount of open content
on how to fix things, questions/answers for common troubleshooting and
"things" related content that is more technical in nature. All content
is licensed under CC-BY-SA-NC 3.0

Adding docs from iFixit as context for user questions like "I dropped my
phone in water, what do I do?" or "My macbook pro is making a whining
noise, what's wrong with it?" can yield significantly better responses
than context free response from LLMs.
2023-02-27 20:40:20 -08:00
Matt Robinson
1aa41b5741
feat: document loader for image files (#1330)
### Summary

Adds a document loader for image files such as `.jpg` and `.png` files.

### Testing

Run the following using the example document from the [`unstructured`
repo](https://github.com/Unstructured-IO/unstructured/tree/main/example-docs).

```python
from langchain.document_loaders.image import UnstructuredImageLoader

loader = UnstructuredImageLoader("layout-parser-paper-fast.jpg")
loader.load()
```
2023-02-27 14:43:32 -08:00
Eugene Yurtsev
c14cff60d0
Documentation: Minor typo fixes (#1327)
Fixing a few minor typos in the documentation (and likely introducing
other
ones in the process).
2023-02-27 14:40:43 -08:00
154 changed files with 12019 additions and 1167 deletions

1
.gitignore vendored
View File

@ -106,6 +106,7 @@ celerybeat.pid
# Environments
.env
.envrc
.venv
.venvs
env/

View File

@ -42,7 +42,7 @@ Please see [here](https://langchain.readthedocs.io/en/latest/?) for full documen
- Getting started (installation, setting up the environment, simple examples)
- How-To examples (demos, integrations, helper functions)
- Reference (full API docs)
Resources (high-level explanation of core concepts)
- Resources (high-level explanation of core concepts)
## 🚀 What can this help with?

View File

@ -5,21 +5,44 @@ It is broken into two parts: installation and setup, and then references to the
## Installation and Setup
- You can find a list of public SearxNG instances [here](https://searx.space/).
- It recommended to use a self-hosted instance to avoid abuse on the public instances. Also note that public instances often have a limit on the number of requests.
- To run a self-hosted instance see [this page](https://searxng.github.io/searxng/admin/installation.html) for more information.
- To use the tool you need to provide the searx host url by:
1. passing the named parameter `searx_host` when creating the instance.
2. exporting the environment variable `SEARXNG_HOST`.
While it is possible to utilize the wrapper in conjunction with [public searx
instances](https://searx.space/) these instances frequently do not permit API
access (see note on output format below) and have limitations on the frequency
of requests. It is recommended to opt for a self-hosted instance instead.
### Self Hosted Instance:
See [this page](https://searxng.github.io/searxng/admin/installation.html) for installation instructions.
When you install SearxNG, the only active output format by default is the HTML format.
You need to activate the `json` format to use the API. This can be done by adding the following line to the `settings.yml` file:
```yaml
search:
formats:
- html
- json
```
You can make sure that the API is working by issuing a curl request to the API endpoint:
`curl -kLX GET --data-urlencode q='langchain' -d format=json http://localhost:8888`
This should return a JSON object with the results.
## Wrappers
### Utility
To use the wrapper we need to pass the host of the SearxNG instance to the wrapper with:
1. the named parameter `searx_host` when creating the instance.
2. exporting the environment variable `SEARXNG_HOST`.
You can use the wrapper to get results from a SearxNG instance.
```python
from langchain.utilities import SearxSearchWrapper
s = SearxSearchWrapper(searx_host="http://localhost:8888")
s.run("what is a large language model?")
```
### Tool
@ -29,7 +52,7 @@ You can do this with:
```python
from langchain.agents import load_tools
tools = load_tools(["searx-search"], searx_host="https://searx.example.com")
tools = load_tools(["searx-search"], searx_host="http://localhost:8888")
```
For more information on this, see [this page](../modules/agents/tools.md)
For more information on tools, see [this page](../modules/agents/tools.md)

View File

@ -66,7 +66,7 @@ llm = OpenAI(temperature=0.9)
We can now call it on some input!
```python
text = "What would be a good company name a company that makes colorful socks?"
text = "What would be a good company name for a company that makes colorful socks?"
print(llm(text))
```

View File

@ -2,7 +2,7 @@ Agents
==========================
Some applications will require not just a predetermined chain of calls to LLMs/other tools,
but potentially an unknown chain that depends on the user input.
but potentially an unknown chain that depends on the user's input.
In these types of chains, there is a “agent” which has access to a suite of tools.
Depending on the user input, the agent can then decide which, if any, of these tools to call.
@ -12,7 +12,7 @@ The following sections of documentation are provided:
- `Key Concepts <./agents/key_concepts.html>`_: A conceptual guide going over the various concepts related to agents.
- `How-To Guides <./agents/how_to_guides.html>`_: A collection of how-to guides. These highlight how to integrate various types of tools, how to work with different types of agent, and how to customize agents.
- `How-To Guides <./agents/how_to_guides.html>`_: A collection of how-to guides. These highlight how to integrate various types of tools, how to work with different types of agents, and how to customize agents.
- `Reference <../reference/modules/agents.html>`_: API reference documentation for all Agent classes.
@ -27,4 +27,4 @@ The following sections of documentation are provided:
./agents/getting_started.ipynb
./agents/key_concepts.md
./agents/how_to_guides.rst
Reference<../reference/modules/agents.rst>
Reference<../reference/modules/agents.rst>

View File

@ -0,0 +1,202 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "7094e328",
"metadata": {},
"source": [
"# CSV Agent\n",
"\n",
"This notebook shows how to use agents to interact with a csv. It is mostly optimized for question answering.\n",
"\n",
"**NOTE: this agent calls the Pandas DataFrame agent under the hood, which in turn calls the Python agent, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.**\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "827982c7",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import create_csv_agent"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "caae0bec",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "16c4dc59",
"metadata": {},
"outputs": [],
"source": [
"agent = create_csv_agent(OpenAI(temperature=0), 'titanic.csv', verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "46b9489d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of rows\n",
"Action: python_repl_ast\n",
"Action Input: len(df)\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m891\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: There are 891 rows in the dataframe.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'There are 891 rows in the dataframe.'"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"how many rows are there?\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "a96309be",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of people with more than 3 siblings\n",
"Action: python_repl_ast\n",
"Action Input: df[df['SibSp'] > 3].shape[0]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m30\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 30 people have more than 3 siblings.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'30 people have more than 3 siblings.'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"how many people have more than 3 sibligngs\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "964a09f7",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to calculate the average age first\n",
"Action: python_repl_ast\n",
"Action Input: df['Age'].mean()\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m29.69911764705882\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
"Action: python_repl_ast\n",
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mname 'math' is not defined\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to import the math library\n",
"Action: python_repl_ast\n",
"Action Input: import math\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mNone\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
"Action: python_repl_ast\n",
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m5.449689683556195\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 5.449689683556195\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'5.449689683556195'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"whats the square root of the average age?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "551de2be",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@ -0,0 +1,190 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab",
"metadata": {},
"source": [
"# JSON Agent\n",
"\n",
"This notebook showcases an agent designed to interact with large JSON/dict objects. This is useful when you want to answer questions about a JSON blob that's too large to fit in the context window of an LLM. The agent is able to iteratively explore the blob to find what it needs to answer the user's question.\n",
"\n",
"In the below example, we are using the OpenAPI spec for the OpenAI API, which you can find [here](https://github.com/openai/openai-openapi/blob/master/openapi.yaml).\n",
"\n",
"We will use the JSON agent to answer some questions about the API spec."
]
},
{
"cell_type": "markdown",
"id": "893f90fd-f8f6-470a-a76d-1f200ba02e2f",
"metadata": {},
"source": [
"## Initialization"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "ff988466-c389-4ec6-b6ac-14364a537fd5",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"import yaml\n",
"\n",
"from langchain.agents import (\n",
" create_json_agent,\n",
" AgentExecutor\n",
")\n",
"from langchain.agents.agent_toolkits import JsonToolkit\n",
"from langchain.chains import LLMChain\n",
"from langchain.llms.openai import OpenAI\n",
"from langchain.requests import RequestsWrapper\n",
"from langchain.tools.json.tool import JsonSpec"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "9ecd1ba0-3937-4359-a41e-68605f0596a1",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"with open(\"openai_openapi.yml\") as f:\n",
" data = yaml.load(f, Loader=yaml.FullLoader)\n",
"json_spec = JsonSpec(dict_=data, max_value_length=4000)\n",
"json_toolkit = JsonToolkit(spec=json_spec)\n",
"\n",
"json_agent_executor = create_json_agent(\n",
" llm=OpenAI(temperature=0),\n",
" toolkit=json_toolkit,\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "05cfcb24-4389-4b8f-ad9e-466e3fca8db0",
"metadata": {},
"source": [
"## Example: getting the required POST parameters for a request"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "faf13702-50f0-4d1b-b91f-48c750ccfd98",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
"Action Input: data\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the /completions endpoint to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['post']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the post key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['operationId', 'tags', 'summary', 'requestBody', 'responses', 'x-oaiMeta']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the requestBody key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['required', 'content']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the required key to see what parameters are required\n",
"Action: json_spec_get_value\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"required\"]\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mTrue\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the content key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['application/json']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the application/json key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['schema']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['$ref']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to see what parameters are required\n",
"Action: json_spec_get_value\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m#/components/schemas/CreateCompletionRequest\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the CreateCompletionRequest schema to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['type', 'properties', 'required']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the required key to see what parameters are required\n",
"Action: json_spec_get_value\n",
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"][\"required\"]\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m['model']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The required parameters in the request body to the /completions endpoint are 'model'.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"The required parameters in the request body to the /completions endpoint are 'model'.\""
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"json_agent_executor.run(\"What are the required parameters in the request body to the /completions endpoint?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ba9c9d30",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,242 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "85fb2c03-ab88-4c8c-97e3-a7f2954555ab",
"metadata": {},
"source": [
"# OpenAPI Agent\n",
"\n",
"This notebook showcases an agent designed to interact with an OpenAPI spec and make a correct API request based on the information it has gathered from the spec.\n",
"\n",
"In the below example, we are using the OpenAPI spec for the OpenAI API, which you can find [here](https://github.com/openai/openai-openapi/blob/master/openapi.yaml)."
]
},
{
"cell_type": "markdown",
"id": "893f90fd-f8f6-470a-a76d-1f200ba02e2f",
"metadata": {},
"source": [
"## Initialization"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "ff988466-c389-4ec6-b6ac-14364a537fd5",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"import yaml\n",
"\n",
"from langchain.agents import create_openapi_agent\n",
"from langchain.agents.agent_toolkits import OpenAPIToolkit\n",
"from langchain.llms.openai import OpenAI\n",
"from langchain.requests import RequestsWrapper\n",
"from langchain.tools.json.tool import JsonSpec"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "9ecd1ba0-3937-4359-a41e-68605f0596a1",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"with open(\"openai_openapi.yml\") as f:\n",
" data = yaml.load(f, Loader=yaml.FullLoader)\n",
"json_spec=JsonSpec(dict_=data, max_value_length=4000)\n",
"headers = {\n",
" \"Authorization\": f\"Bearer {os.getenv('OPENAI_API_KEY')}\"\n",
"}\n",
"requests_wrapper=RequestsWrapper(headers=headers)\n",
"openapi_toolkit = OpenAPIToolkit.from_llm(OpenAI(temperature=0), json_spec, requests_wrapper, verbose=True)\n",
"openapi_agent_executor = create_openapi_agent(\n",
" llm=OpenAI(temperature=0),\n",
" toolkit=openapi_toolkit,\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "f111879d-ae84-41f9-ad82-d3e6b72c41ba",
"metadata": {},
"source": [
"## Example: agent capable of analyzing OpenAPI spec and making requests"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "548db7f7-337b-4ba8-905c-e7fd58c01799",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: json_explorer\n",
"Action Input: What is the base url for the API?\u001b[0m\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
"Action Input: data\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the servers key to see what the base url is\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"servers\"][0]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mValueError('Value at path `data[\"servers\"][0]` is not a dict, get the value directly.')\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should get the value of the servers key\n",
"Action: json_spec_get_value\n",
"Action Input: data[\"servers\"][0]\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m{'url': 'https://api.openai.com/v1'}\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the base url for the API\n",
"Final Answer: The base url for the API is https://api.openai.com/v1\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mThe base url for the API is https://api.openai.com/v1\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should find the path for the /completions endpoint.\n",
"Action: json_explorer\n",
"Action Input: What is the path for the /completions endpoint?\u001b[0m\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
"Action Input: data\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the path for the /completions endpoint\n",
"Final Answer: data[\"paths\"][2]\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mdata[\"paths\"][2]\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should find the required parameters for the POST request.\n",
"Action: json_explorer\n",
"Action Input: What are the required parameters for a POST request to the /completions endpoint?\u001b[0m\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: json_spec_list_keys\n",
"Action Input: data\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['openapi', 'info', 'servers', 'tags', 'paths', 'components', 'x-oaiMeta']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the paths key to see what endpoints exist\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['/engines', '/engines/{engine_id}', '/completions', '/edits', '/images/generations', '/images/edits', '/images/variations', '/embeddings', '/engines/{engine_id}/search', '/files', '/files/{file_id}', '/files/{file_id}/content', '/answers', '/classifications', '/fine-tunes', '/fine-tunes/{fine_tune_id}', '/fine-tunes/{fine_tune_id}/cancel', '/fine-tunes/{fine_tune_id}/events', '/models', '/models/{model}', '/moderations']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the /completions endpoint to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['post']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the post key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['operationId', 'tags', 'summary', 'requestBody', 'responses', 'x-oaiMeta']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the requestBody key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['required', 'content']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the content key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['application/json']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the application/json key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['schema']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['$ref']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mValueError('Value at path `data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]` is not a dict, get the value directly.')\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the $ref key to get the value directly\n",
"Action: json_spec_get_value\n",
"Action Input: data[\"paths\"][\"/completions\"][\"post\"][\"requestBody\"][\"content\"][\"application/json\"][\"schema\"][\"$ref\"]\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m#/components/schemas/CreateCompletionRequest\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the CreateCompletionRequest schema to see what parameters are required\n",
"Action: json_spec_list_keys\n",
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m['type', 'properties', 'required']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the required key to see what parameters are required\n",
"Action: json_spec_get_value\n",
"Action Input: data[\"components\"][\"schemas\"][\"CreateCompletionRequest\"][\"required\"]\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m['model']\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The required parameters for a POST request to the /completions endpoint are 'model'.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[33;1m\u001b[1;3mThe required parameters for a POST request to the /completions endpoint are 'model'.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the parameters needed to make the request.\n",
"Action: requests_post\n",
"Action Input: { \"url\": \"https://api.openai.com/v1/completions\", \"data\": { \"model\": \"davinci\", \"prompt\": \"tell me a joke\" } }\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m{\"id\":\"cmpl-6oeEcNETfq8TOuIUQvAct6NrBXihs\",\"object\":\"text_completion\",\"created\":1677529082,\"model\":\"davinci\",\"choices\":[{\"text\":\"\\n\\n\\n\\nLove is a battlefield\\n\\n\\n\\nIt's me...And some\",\"index\":0,\"logprobs\":null,\"finish_reason\":\"length\"}],\"usage\":{\"prompt_tokens\":4,\"completion_tokens\":16,\"total_tokens\":20}}\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: Love is a battlefield. It's me...And some.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Love is a battlefield. It's me...And some.\""
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"openapi_agent_executor.run(\"Make a post request to openai /completions. The prompt should be 'tell me a joke.'\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6ec9582b",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@ -0,0 +1,204 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "c81da886",
"metadata": {},
"source": [
"# Pandas Dataframe Agent\n",
"\n",
"This notebook shows how to use agents to interact with a pandas dataframe. It is mostly optimized for question answering.\n",
"\n",
"**NOTE: this agent calls the Python agent under the hood, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.**"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "0cdd9bf5",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import create_pandas_dataframe_agent"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "051ebe84",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"import pandas as pd\n",
"\n",
"df = pd.read_csv('titanic.csv')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "4185ff46",
"metadata": {},
"outputs": [],
"source": [
"agent = create_pandas_dataframe_agent(OpenAI(temperature=0), df, verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "a9207a2e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of rows\n",
"Action: python_repl_ast\n",
"Action Input: len(df)\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m891\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: There are 891 rows in the dataframe.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'There are 891 rows in the dataframe.'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"how many rows are there?\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "bd43617c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to count the number of people with more than 3 siblings\n",
"Action: python_repl_ast\n",
"Action Input: df[df['SibSp'] > 3].shape[0]\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m30\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 30 people have more than 3 siblings.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'30 people have more than 3 siblings.'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"how many people have more than 3 sibligngs\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "94e64b58",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mThought: I need to calculate the average age first\n",
"Action: python_repl_ast\n",
"Action Input: df['Age'].mean()\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m29.69911764705882\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
"Action: python_repl_ast\n",
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mname 'math' is not defined\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to import the math library\n",
"Action: python_repl_ast\n",
"Action Input: import math\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mNone\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I can now calculate the square root\n",
"Action: python_repl_ast\n",
"Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m5.449689683556195\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 5.449689683556195\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'5.449689683556195'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"whats the square root of the average age?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "eba13b4d",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@ -0,0 +1,228 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "82a4c2cc-20ea-4b20-a565-63e905dee8ff",
"metadata": {},
"source": [
"## Python Agent\n",
"\n",
"This notebook showcases an agent designed to write and execute python code to answer a question."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "f98e9c90-5c37-4fb9-af3e-d09693af8543",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.agents.agent_toolkits import create_python_agent\n",
"from langchain.tools.python.tool import PythonREPLTool\n",
"from langchain.python import PythonREPL\n",
"from langchain.llms.openai import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "cc422f53-c51c-4694-a834-72ecd1e68363",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"agent_executor = create_python_agent(\n",
" llm=OpenAI(temperature=0, max_tokens=1000),\n",
" tool=PythonREPLTool(),\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "c16161de",
"metadata": {},
"source": [
"## Fibonacci Example\n",
"This example was created by [John Wiseman](https://twitter.com/lemonodor/status/1628270074074398720?s=20)."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "25cd4f92-ea9b-4fe6-9838-a4f85f81eebe",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to calculate the 10th fibonacci number\n",
"Action: Python REPL\n",
"Action Input: def fibonacci(n):\n",
" if n == 0:\n",
" return 0\n",
" elif n == 1:\n",
" return 1\n",
" else:\n",
" return fibonacci(n-1) + fibonacci(n-2)\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to call the function with 10 as the argument\n",
"Action: Python REPL\n",
"Action Input: fibonacci(10)\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: 55\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'55'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What is the 10th fibonacci number?\")"
]
},
{
"cell_type": "markdown",
"id": "7caa30de",
"metadata": {},
"source": [
"## Training neural net\n",
"This example was created by [Samee Ur Rehman](https://twitter.com/sameeurehman/status/1630130518133207046?s=20)."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "4b9f60e7-eb6a-4f14-8604-498d863d4482",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to write a neural network in PyTorch and train it on the given data.\n",
"Action: Python REPL\n",
"Action Input: \n",
"import torch\n",
"\n",
"# Define the model\n",
"model = torch.nn.Sequential(\n",
" torch.nn.Linear(1, 1)\n",
")\n",
"\n",
"# Define the loss\n",
"loss_fn = torch.nn.MSELoss()\n",
"\n",
"# Define the optimizer\n",
"optimizer = torch.optim.SGD(model.parameters(), lr=0.01)\n",
"\n",
"# Define the data\n",
"x_data = torch.tensor([[1.0], [2.0], [3.0], [4.0]])\n",
"y_data = torch.tensor([[2.0], [4.0], [6.0], [8.0]])\n",
"\n",
"# Train the model\n",
"for epoch in range(1000):\n",
" # Forward pass\n",
" y_pred = model(x_data)\n",
"\n",
" # Compute and print loss\n",
" loss = loss_fn(y_pred, y_data)\n",
" if (epoch+1) % 100 == 0:\n",
" print(f'Epoch {epoch+1}: loss = {loss.item():.4f}')\n",
"\n",
" # Zero the gradients\n",
" optimizer.zero_grad()\n",
"\n",
" # Backward pass\n",
" loss.backward()\n",
"\n",
" # Update the weights\n",
" optimizer.step()\n",
"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mEpoch 100: loss = 0.0013\n",
"Epoch 200: loss = 0.0007\n",
"Epoch 300: loss = 0.0004\n",
"Epoch 400: loss = 0.0002\n",
"Epoch 500: loss = 0.0001\n",
"Epoch 600: loss = 0.0001\n",
"Epoch 700: loss = 0.0000\n",
"Epoch 800: loss = 0.0000\n",
"Epoch 900: loss = 0.0000\n",
"Epoch 1000: loss = 0.0000\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The prediction for x = 5 is 10.0.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The prediction for x = 5 is 10.0.'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"\"\"Understand, write a single neuron neural network in PyTorch.\n",
"Take synthetic data for y=2x. Train for 1000 epochs and print every 100 epochs.\n",
"Return prediction for x = 5\"\"\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "eb654671",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@ -0,0 +1,527 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "0e499e90-7a6d-4fab-8aab-31a4df417601",
"metadata": {},
"source": [
"# SQL Database Agent\n",
"\n",
"This notebook showcases an agent designed to interact with a sql databases. The agent builds off of [SQLDatabaseChain](https://langchain.readthedocs.io/en/latest/modules/chains/examples/sqlite.html) and is designed to answer more general questions about a database, as well as recover from errors.\n",
"\n",
"Note that, as this agent is in active development, all answers might not be correct. Additionally, it is not guaranteed that the agent won't perform DML statements on your database given certain questions. Be careful running it on sensitive data!\n",
"\n",
"This uses the example Chinook database. To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the .db file in a notebooks folder at the root of this repository."
]
},
{
"cell_type": "markdown",
"id": "ec927ac6-9b2a-4e8a-9a6e-3e429191875c",
"metadata": {
"tags": []
},
"source": [
"## Initialization"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "53422913-967b-4f2a-8022-00269c1be1b1",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.agents import create_sql_agent\n",
"from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
"from langchain.sql_database import SQLDatabase\n",
"from langchain.llms.openai import OpenAI\n",
"from langchain.agents import AgentExecutor"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "090f3699-79c6-4ce1-ab96-a94f0121fd64",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"db = SQLDatabase.from_uri(\"sqlite:///../../../../notebooks/Chinook.db\")\n",
"toolkit = SQLDatabaseToolkit(db=db)\n",
"\n",
"agent_executor = create_sql_agent(\n",
" llm=OpenAI(temperature=0),\n",
" toolkit=toolkit,\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "36ae48c7-cb08-4fef-977e-c7d4b96a464b",
"metadata": {},
"source": [
"## Example: describing a table"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "ff70e83d-5ad0-4fc7-bb96-27d82ac166d7",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
"Action Input: \"\"\u001b[0m\n",
"Observation: \u001b[38;5;200m\u001b[1;3mArtist, Invoice, Playlist, Genre, Album, PlaylistTrack, Track, InvoiceLine, MediaType, Employee, Customer\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the playlisttrack table\n",
"Action: schema_sql_db\n",
"Action Input: \"PlaylistTrack\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m\n",
"CREATE TABLE \"PlaylistTrack\" (\n",
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"PlaylistId\", \"TrackId\"), \n",
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
"\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
")\n",
"\n",
"SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
"PlaylistId TrackId\n",
"1 3402\n",
"1 3389\n",
"1 3390\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The PlaylistTrack table has two columns, PlaylistId and TrackId, and is linked to the Playlist and Track tables.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The PlaylistTrack table has two columns, PlaylistId and TrackId, and is linked to the Playlist and Track tables.'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"Describe the playlisttrack table\")"
]
},
{
"cell_type": "markdown",
"id": "9abcfe8e-1868-42a4-8345-ad2d9b44c681",
"metadata": {},
"source": [
"## Example: describing a table, recovering from an error\n",
"\n",
"In this example, the agent tries to search for a table that doesn't exist, but finds the next best result"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "bea76658-a65b-47e2-b294-6d52c5556246",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
"Action Input: \"\"\u001b[0m\n",
"Observation: \u001b[38;5;200m\u001b[1;3mGenre, PlaylistTrack, MediaType, Invoice, InvoiceLine, Track, Playlist, Customer, Album, Employee, Artist\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the PlaylistSong table\n",
"Action: schema_sql_db\n",
"Action Input: \"PlaylistSong\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mError: table_names {'PlaylistSong'} not found in database\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should check the spelling of the table\n",
"Action: list_tables_sql_db\n",
"Action Input: \"\"\u001b[0m\n",
"Observation: \u001b[38;5;200m\u001b[1;3mGenre, PlaylistTrack, MediaType, Invoice, InvoiceLine, Track, Playlist, Customer, Album, Employee, Artist\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m The table is called PlaylistTrack\n",
"Action: schema_sql_db\n",
"Action Input: \"PlaylistTrack\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m\n",
"CREATE TABLE \"PlaylistTrack\" (\n",
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"PlaylistId\", \"TrackId\"), \n",
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
"\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
")\n",
"\n",
"SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
"PlaylistId TrackId\n",
"1 3402\n",
"1 3389\n",
"1 3390\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both integers and are used to link Playlist and Track tables.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both integers and are used to link Playlist and Track tables.'"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"Describe the playlistsong table\")"
]
},
{
"cell_type": "markdown",
"id": "6fbc26af-97e4-4a21-82aa-48bdc992da26",
"metadata": {},
"source": [
"## Example: running queries"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "17bea710-4a23-4de0-b48e-21d57be48293",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
"Action Input: \"\"\u001b[0m\n",
"Observation: \u001b[38;5;200m\u001b[1;3mInvoice, MediaType, Artist, InvoiceLine, Genre, Playlist, Employee, Album, PlaylistTrack, Track, Customer\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the relevant tables to see what columns I can use.\n",
"Action: schema_sql_db\n",
"Action Input: \"Invoice, Customer\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m\n",
"CREATE TABLE \"Customer\" (\n",
"\t\"CustomerId\" INTEGER NOT NULL, \n",
"\t\"FirstName\" NVARCHAR(40) NOT NULL, \n",
"\t\"LastName\" NVARCHAR(20) NOT NULL, \n",
"\t\"Company\" NVARCHAR(80), \n",
"\t\"Address\" NVARCHAR(70), \n",
"\t\"City\" NVARCHAR(40), \n",
"\t\"State\" NVARCHAR(40), \n",
"\t\"Country\" NVARCHAR(40), \n",
"\t\"PostalCode\" NVARCHAR(10), \n",
"\t\"Phone\" NVARCHAR(24), \n",
"\t\"Fax\" NVARCHAR(24), \n",
"\t\"Email\" NVARCHAR(60) NOT NULL, \n",
"\t\"SupportRepId\" INTEGER, \n",
"\tPRIMARY KEY (\"CustomerId\"), \n",
"\tFOREIGN KEY(\"SupportRepId\") REFERENCES \"Employee\" (\"EmployeeId\")\n",
")\n",
"\n",
"SELECT * FROM 'Customer' LIMIT 3;\n",
"CustomerId FirstName LastName Company Address City State Country PostalCode Phone Fax Email SupportRepId\n",
"1 Luís Gonçalves Embraer - Empresa Brasileira de Aeronáutica S.A. Av. Brigadeiro Faria Lima, 2170 São José dos Campos SP Brazil 12227-000 +55 (12) 3923-5555 +55 (12) 3923-5566 luisg@embraer.com.br 3\n",
"2 Leonie Köhler None Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 +49 0711 2842222 None leonekohler@surfeu.de 5\n",
"3 François Tremblay None 1498 rue Bélanger Montréal QC Canada H2G 1A7 +1 (514) 721-4711 None ftremblay@gmail.com 3\n",
"\n",
"\n",
"CREATE TABLE \"Invoice\" (\n",
"\t\"InvoiceId\" INTEGER NOT NULL, \n",
"\t\"CustomerId\" INTEGER NOT NULL, \n",
"\t\"InvoiceDate\" DATETIME NOT NULL, \n",
"\t\"BillingAddress\" NVARCHAR(70), \n",
"\t\"BillingCity\" NVARCHAR(40), \n",
"\t\"BillingState\" NVARCHAR(40), \n",
"\t\"BillingCountry\" NVARCHAR(40), \n",
"\t\"BillingPostalCode\" NVARCHAR(10), \n",
"\t\"Total\" NUMERIC(10, 2) NOT NULL, \n",
"\tPRIMARY KEY (\"InvoiceId\"), \n",
"\tFOREIGN KEY(\"CustomerId\") REFERENCES \"Customer\" (\"CustomerId\")\n",
")\n",
"\n",
"SELECT * FROM 'Invoice' LIMIT 3;\n",
"InvoiceId CustomerId InvoiceDate BillingAddress BillingCity BillingState BillingCountry BillingPostalCode Total\n",
"1 2 2009-01-01 00:00:00 Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 1.98\n",
"2 4 2009-01-02 00:00:00 Ullevålsveien 14 Oslo None Norway 0171 3.96\n",
"3 8 2009-01-03 00:00:00 Grétrystraat 63 Brussels None Belgium 1000 5.94\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should query the Invoice and Customer tables to get the total sales per country.\n",
"Action: query_sql_db\n",
"Action Input: SELECT c.Country, SUM(i.Total) AS TotalSales FROM Invoice i INNER JOIN Customer c ON i.CustomerId = c.CustomerId GROUP BY c.Country ORDER BY TotalSales DESC LIMIT 10\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m[('USA', 523.0600000000003), ('Canada', 303.9599999999999), ('France', 195.09999999999994), ('Brazil', 190.09999999999997), ('Germany', 156.48), ('United Kingdom', 112.85999999999999), ('Czech Republic', 90.24000000000001), ('Portugal', 77.23999999999998), ('India', 75.25999999999999), ('Chile', 46.62)]\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The customers from the USA spent the most, with a total of $523.06.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The customers from the USA spent the most, with a total of $523.06.'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"List the total sales per country. Which country's customers spent the most?\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "474dddda-c067-4eeb-98b1-e763ee78b18c",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
"Action Input: \"\"\u001b[0m\n",
"Observation: \u001b[38;5;200m\u001b[1;3mInvoice, MediaType, Artist, InvoiceLine, Genre, Playlist, Employee, Album, PlaylistTrack, Track, Customer\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the Playlist and PlaylistTrack tables to see what columns I can use.\n",
"Action: schema_sql_db\n",
"Action Input: \"Playlist, PlaylistTrack\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m\n",
"CREATE TABLE \"Playlist\" (\n",
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
"\t\"Name\" NVARCHAR(120), \n",
"\tPRIMARY KEY (\"PlaylistId\")\n",
")\n",
"\n",
"SELECT * FROM 'Playlist' LIMIT 3;\n",
"PlaylistId Name\n",
"1 Music\n",
"2 Movies\n",
"3 TV Shows\n",
"\n",
"\n",
"CREATE TABLE \"PlaylistTrack\" (\n",
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"PlaylistId\", \"TrackId\"), \n",
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
"\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
")\n",
"\n",
"SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
"PlaylistId TrackId\n",
"1 3402\n",
"1 3389\n",
"1 3390\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I can use a SELECT statement to get the total number of tracks in each playlist.\n",
"Action: query_checker_sql_db\n",
"Action Input: SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name\u001b[0m\n",
"Observation: \u001b[31;1m\u001b[1;3m\n",
"\n",
"SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m The query looks correct, I can now execute it.\n",
"Action: query_sql_db\n",
"Action Input: SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name LIMIT 10\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m[('90s Music', 1477), ('Brazilian Music', 39), ('Classical', 75), ('Classical 101 - Deep Cuts', 25), ('Classical 101 - Next Steps', 25), ('Classical 101 - The Basics', 25), ('Grunge', 15), ('Heavy Metal Classic', 26), ('Music', 6580), ('Music Videos', 1)]\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: The total number of tracks in each playlist are: '90s Music' (1477), 'Brazilian Music' (39), 'Classical' (75), 'Classical 101 - Deep Cuts' (25), 'Classical 101 - Next Steps' (25), 'Classical 101 - The Basics' (25), 'Grunge' (15), 'Heavy Metal Classic' (26), 'Music' (6580), 'Music Videos' (1).\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"The total number of tracks in each playlist are: '90s Music' (1477), 'Brazilian Music' (39), 'Classical' (75), 'Classical 101 - Deep Cuts' (25), 'Classical 101 - Next Steps' (25), 'Classical 101 - The Basics' (25), 'Grunge' (15), 'Heavy Metal Classic' (26), 'Music' (6580), 'Music Videos' (1).\""
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"Show the total number of tracks in each playlist. The Playlist name should be included in the result.\")"
]
},
{
"cell_type": "markdown",
"id": "7c7503b5-d9d9-4faa-b064-29fcdb5ff213",
"metadata": {},
"source": [
"## Recovering from an error\n",
"\n",
"In this example, the agent is able to recover from an error after initially trying to access an attribute (`Track.ArtistId`) which doesn't exist."
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "9fe4901e-f9e1-4022-b6bc-80e2b2d6a3a4",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
"Action Input: \"\"\u001b[0m\n",
"Observation: \u001b[38;5;200m\u001b[1;3mMediaType, Track, Invoice, Album, Playlist, Customer, Employee, InvoiceLine, PlaylistTrack, Genre, Artist\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the Artist, InvoiceLine, and Track tables to see what columns I can use.\n",
"Action: schema_sql_db\n",
"Action Input: \"Artist, InvoiceLine, Track\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m\n",
"CREATE TABLE \"Artist\" (\n",
"\t\"ArtistId\" INTEGER NOT NULL, \n",
"\t\"Name\" NVARCHAR(120), \n",
"\tPRIMARY KEY (\"ArtistId\")\n",
")\n",
"\n",
"SELECT * FROM 'Artist' LIMIT 3;\n",
"ArtistId Name\n",
"1 AC/DC\n",
"2 Accept\n",
"3 Aerosmith\n",
"\n",
"\n",
"CREATE TABLE \"Track\" (\n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\t\"Name\" NVARCHAR(200) NOT NULL, \n",
"\t\"AlbumId\" INTEGER, \n",
"\t\"MediaTypeId\" INTEGER NOT NULL, \n",
"\t\"GenreId\" INTEGER, \n",
"\t\"Composer\" NVARCHAR(220), \n",
"\t\"Milliseconds\" INTEGER NOT NULL, \n",
"\t\"Bytes\" INTEGER, \n",
"\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
"\tPRIMARY KEY (\"TrackId\"), \n",
"\tFOREIGN KEY(\"MediaTypeId\") REFERENCES \"MediaType\" (\"MediaTypeId\"), \n",
"\tFOREIGN KEY(\"GenreId\") REFERENCES \"Genre\" (\"GenreId\"), \n",
"\tFOREIGN KEY(\"AlbumId\") REFERENCES \"Album\" (\"AlbumId\")\n",
")\n",
"\n",
"SELECT * FROM 'Track' LIMIT 3;\n",
"TrackId Name AlbumId MediaTypeId GenreId Composer Milliseconds Bytes UnitPrice\n",
"1 For Those About To Rock (We Salute You) 1 1 1 Angus Young, Malcolm Young, Brian Johnson 343719 11170334 0.99\n",
"2 Balls to the Wall 2 2 1 None 342562 5510424 0.99\n",
"3 Fast As a Shark 3 2 1 F. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman 230619 3990994 0.99\n",
"\n",
"\n",
"CREATE TABLE \"InvoiceLine\" (\n",
"\t\"InvoiceLineId\" INTEGER NOT NULL, \n",
"\t\"InvoiceId\" INTEGER NOT NULL, \n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
"\t\"Quantity\" INTEGER NOT NULL, \n",
"\tPRIMARY KEY (\"InvoiceLineId\"), \n",
"\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
"\tFOREIGN KEY(\"InvoiceId\") REFERENCES \"Invoice\" (\"InvoiceId\")\n",
")\n",
"\n",
"SELECT * FROM 'InvoiceLine' LIMIT 3;\n",
"InvoiceLineId InvoiceId TrackId UnitPrice Quantity\n",
"1 1 2 0.99 1\n",
"2 1 4 0.99 1\n",
"3 2 6 0.99 1\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should query the database to get the top 3 best selling artists.\n",
"Action: query_sql_db\n",
"Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mError: (sqlite3.OperationalError) no such column: Track.ArtistId\n",
"[SQL: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3]\n",
"(Background on this error at: https://sqlalche.me/e/14/e3q8)\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I should double check my query before executing it.\n",
"Action: query_checker_sql_db\n",
"Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3\u001b[0m\n",
"Observation: \u001b[31;1m\u001b[1;3m\n",
"\n",
"SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity \n",
"FROM Artist \n",
"INNER JOIN Track ON Artist.ArtistId = Track.ArtistId \n",
"INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId \n",
"GROUP BY Artist.Name \n",
"ORDER BY TotalQuantity DESC \n",
"LIMIT 3;\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Action: query_sql_db\n",
"Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Album ON Artist.ArtistId = Album.ArtistId INNER JOIN Track ON Album.AlbumId = Track.AlbumId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m[('Iron Maiden', 140), ('U2', 107), ('Metallica', 91)]\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: The top 3 best selling artists are Iron Maiden, U2, and Metallica.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The top 3 best selling artists are Iron Maiden, U2, and Metallica.'"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"Who are the top 3 best selling artists?\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@ -0,0 +1,892 @@
PassengerId,Survived,Pclass,Name,Sex,Age,SibSp,Parch,Ticket,Fare,Cabin,Embarked
1,0,3,"Braund, Mr. Owen Harris",male,22,1,0,A/5 21171,7.25,,S
2,1,1,"Cumings, Mrs. John Bradley (Florence Briggs Thayer)",female,38,1,0,PC 17599,71.2833,C85,C
3,1,3,"Heikkinen, Miss. Laina",female,26,0,0,STON/O2. 3101282,7.925,,S
4,1,1,"Futrelle, Mrs. Jacques Heath (Lily May Peel)",female,35,1,0,113803,53.1,C123,S
5,0,3,"Allen, Mr. William Henry",male,35,0,0,373450,8.05,,S
6,0,3,"Moran, Mr. James",male,,0,0,330877,8.4583,,Q
7,0,1,"McCarthy, Mr. Timothy J",male,54,0,0,17463,51.8625,E46,S
8,0,3,"Palsson, Master. Gosta Leonard",male,2,3,1,349909,21.075,,S
9,1,3,"Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg)",female,27,0,2,347742,11.1333,,S
10,1,2,"Nasser, Mrs. Nicholas (Adele Achem)",female,14,1,0,237736,30.0708,,C
11,1,3,"Sandstrom, Miss. Marguerite Rut",female,4,1,1,PP 9549,16.7,G6,S
12,1,1,"Bonnell, Miss. Elizabeth",female,58,0,0,113783,26.55,C103,S
13,0,3,"Saundercock, Mr. William Henry",male,20,0,0,A/5. 2151,8.05,,S
14,0,3,"Andersson, Mr. Anders Johan",male,39,1,5,347082,31.275,,S
15,0,3,"Vestrom, Miss. Hulda Amanda Adolfina",female,14,0,0,350406,7.8542,,S
16,1,2,"Hewlett, Mrs. (Mary D Kingcome) ",female,55,0,0,248706,16,,S
17,0,3,"Rice, Master. Eugene",male,2,4,1,382652,29.125,,Q
18,1,2,"Williams, Mr. Charles Eugene",male,,0,0,244373,13,,S
19,0,3,"Vander Planke, Mrs. Julius (Emelia Maria Vandemoortele)",female,31,1,0,345763,18,,S
20,1,3,"Masselmani, Mrs. Fatima",female,,0,0,2649,7.225,,C
21,0,2,"Fynney, Mr. Joseph J",male,35,0,0,239865,26,,S
22,1,2,"Beesley, Mr. Lawrence",male,34,0,0,248698,13,D56,S
23,1,3,"McGowan, Miss. Anna ""Annie""",female,15,0,0,330923,8.0292,,Q
24,1,1,"Sloper, Mr. William Thompson",male,28,0,0,113788,35.5,A6,S
25,0,3,"Palsson, Miss. Torborg Danira",female,8,3,1,349909,21.075,,S
26,1,3,"Asplund, Mrs. Carl Oscar (Selma Augusta Emilia Johansson)",female,38,1,5,347077,31.3875,,S
27,0,3,"Emir, Mr. Farred Chehab",male,,0,0,2631,7.225,,C
28,0,1,"Fortune, Mr. Charles Alexander",male,19,3,2,19950,263,C23 C25 C27,S
29,1,3,"O'Dwyer, Miss. Ellen ""Nellie""",female,,0,0,330959,7.8792,,Q
30,0,3,"Todoroff, Mr. Lalio",male,,0,0,349216,7.8958,,S
31,0,1,"Uruchurtu, Don. Manuel E",male,40,0,0,PC 17601,27.7208,,C
32,1,1,"Spencer, Mrs. William Augustus (Marie Eugenie)",female,,1,0,PC 17569,146.5208,B78,C
33,1,3,"Glynn, Miss. Mary Agatha",female,,0,0,335677,7.75,,Q
34,0,2,"Wheadon, Mr. Edward H",male,66,0,0,C.A. 24579,10.5,,S
35,0,1,"Meyer, Mr. Edgar Joseph",male,28,1,0,PC 17604,82.1708,,C
36,0,1,"Holverson, Mr. Alexander Oskar",male,42,1,0,113789,52,,S
37,1,3,"Mamee, Mr. Hanna",male,,0,0,2677,7.2292,,C
38,0,3,"Cann, Mr. Ernest Charles",male,21,0,0,A./5. 2152,8.05,,S
39,0,3,"Vander Planke, Miss. Augusta Maria",female,18,2,0,345764,18,,S
40,1,3,"Nicola-Yarred, Miss. Jamila",female,14,1,0,2651,11.2417,,C
41,0,3,"Ahlin, Mrs. Johan (Johanna Persdotter Larsson)",female,40,1,0,7546,9.475,,S
42,0,2,"Turpin, Mrs. William John Robert (Dorothy Ann Wonnacott)",female,27,1,0,11668,21,,S
43,0,3,"Kraeff, Mr. Theodor",male,,0,0,349253,7.8958,,C
44,1,2,"Laroche, Miss. Simonne Marie Anne Andree",female,3,1,2,SC/Paris 2123,41.5792,,C
45,1,3,"Devaney, Miss. Margaret Delia",female,19,0,0,330958,7.8792,,Q
46,0,3,"Rogers, Mr. William John",male,,0,0,S.C./A.4. 23567,8.05,,S
47,0,3,"Lennon, Mr. Denis",male,,1,0,370371,15.5,,Q
48,1,3,"O'Driscoll, Miss. Bridget",female,,0,0,14311,7.75,,Q
49,0,3,"Samaan, Mr. Youssef",male,,2,0,2662,21.6792,,C
50,0,3,"Arnold-Franchi, Mrs. Josef (Josefine Franchi)",female,18,1,0,349237,17.8,,S
51,0,3,"Panula, Master. Juha Niilo",male,7,4,1,3101295,39.6875,,S
52,0,3,"Nosworthy, Mr. Richard Cater",male,21,0,0,A/4. 39886,7.8,,S
53,1,1,"Harper, Mrs. Henry Sleeper (Myna Haxtun)",female,49,1,0,PC 17572,76.7292,D33,C
54,1,2,"Faunthorpe, Mrs. Lizzie (Elizabeth Anne Wilkinson)",female,29,1,0,2926,26,,S
55,0,1,"Ostby, Mr. Engelhart Cornelius",male,65,0,1,113509,61.9792,B30,C
56,1,1,"Woolner, Mr. Hugh",male,,0,0,19947,35.5,C52,S
57,1,2,"Rugg, Miss. Emily",female,21,0,0,C.A. 31026,10.5,,S
58,0,3,"Novel, Mr. Mansouer",male,28.5,0,0,2697,7.2292,,C
59,1,2,"West, Miss. Constance Mirium",female,5,1,2,C.A. 34651,27.75,,S
60,0,3,"Goodwin, Master. William Frederick",male,11,5,2,CA 2144,46.9,,S
61,0,3,"Sirayanian, Mr. Orsen",male,22,0,0,2669,7.2292,,C
62,1,1,"Icard, Miss. Amelie",female,38,0,0,113572,80,B28,
63,0,1,"Harris, Mr. Henry Birkhardt",male,45,1,0,36973,83.475,C83,S
64,0,3,"Skoog, Master. Harald",male,4,3,2,347088,27.9,,S
65,0,1,"Stewart, Mr. Albert A",male,,0,0,PC 17605,27.7208,,C
66,1,3,"Moubarek, Master. Gerios",male,,1,1,2661,15.2458,,C
67,1,2,"Nye, Mrs. (Elizabeth Ramell)",female,29,0,0,C.A. 29395,10.5,F33,S
68,0,3,"Crease, Mr. Ernest James",male,19,0,0,S.P. 3464,8.1583,,S
69,1,3,"Andersson, Miss. Erna Alexandra",female,17,4,2,3101281,7.925,,S
70,0,3,"Kink, Mr. Vincenz",male,26,2,0,315151,8.6625,,S
71,0,2,"Jenkin, Mr. Stephen Curnow",male,32,0,0,C.A. 33111,10.5,,S
72,0,3,"Goodwin, Miss. Lillian Amy",female,16,5,2,CA 2144,46.9,,S
73,0,2,"Hood, Mr. Ambrose Jr",male,21,0,0,S.O.C. 14879,73.5,,S
74,0,3,"Chronopoulos, Mr. Apostolos",male,26,1,0,2680,14.4542,,C
75,1,3,"Bing, Mr. Lee",male,32,0,0,1601,56.4958,,S
76,0,3,"Moen, Mr. Sigurd Hansen",male,25,0,0,348123,7.65,F G73,S
77,0,3,"Staneff, Mr. Ivan",male,,0,0,349208,7.8958,,S
78,0,3,"Moutal, Mr. Rahamin Haim",male,,0,0,374746,8.05,,S
79,1,2,"Caldwell, Master. Alden Gates",male,0.83,0,2,248738,29,,S
80,1,3,"Dowdell, Miss. Elizabeth",female,30,0,0,364516,12.475,,S
81,0,3,"Waelens, Mr. Achille",male,22,0,0,345767,9,,S
82,1,3,"Sheerlinck, Mr. Jan Baptist",male,29,0,0,345779,9.5,,S
83,1,3,"McDermott, Miss. Brigdet Delia",female,,0,0,330932,7.7875,,Q
84,0,1,"Carrau, Mr. Francisco M",male,28,0,0,113059,47.1,,S
85,1,2,"Ilett, Miss. Bertha",female,17,0,0,SO/C 14885,10.5,,S
86,1,3,"Backstrom, Mrs. Karl Alfred (Maria Mathilda Gustafsson)",female,33,3,0,3101278,15.85,,S
87,0,3,"Ford, Mr. William Neal",male,16,1,3,W./C. 6608,34.375,,S
88,0,3,"Slocovski, Mr. Selman Francis",male,,0,0,SOTON/OQ 392086,8.05,,S
89,1,1,"Fortune, Miss. Mabel Helen",female,23,3,2,19950,263,C23 C25 C27,S
90,0,3,"Celotti, Mr. Francesco",male,24,0,0,343275,8.05,,S
91,0,3,"Christmann, Mr. Emil",male,29,0,0,343276,8.05,,S
92,0,3,"Andreasson, Mr. Paul Edvin",male,20,0,0,347466,7.8542,,S
93,0,1,"Chaffee, Mr. Herbert Fuller",male,46,1,0,W.E.P. 5734,61.175,E31,S
94,0,3,"Dean, Mr. Bertram Frank",male,26,1,2,C.A. 2315,20.575,,S
95,0,3,"Coxon, Mr. Daniel",male,59,0,0,364500,7.25,,S
96,0,3,"Shorney, Mr. Charles Joseph",male,,0,0,374910,8.05,,S
97,0,1,"Goldschmidt, Mr. George B",male,71,0,0,PC 17754,34.6542,A5,C
98,1,1,"Greenfield, Mr. William Bertram",male,23,0,1,PC 17759,63.3583,D10 D12,C
99,1,2,"Doling, Mrs. John T (Ada Julia Bone)",female,34,0,1,231919,23,,S
100,0,2,"Kantor, Mr. Sinai",male,34,1,0,244367,26,,S
101,0,3,"Petranec, Miss. Matilda",female,28,0,0,349245,7.8958,,S
102,0,3,"Petroff, Mr. Pastcho (""Pentcho"")",male,,0,0,349215,7.8958,,S
103,0,1,"White, Mr. Richard Frasar",male,21,0,1,35281,77.2875,D26,S
104,0,3,"Johansson, Mr. Gustaf Joel",male,33,0,0,7540,8.6542,,S
105,0,3,"Gustafsson, Mr. Anders Vilhelm",male,37,2,0,3101276,7.925,,S
106,0,3,"Mionoff, Mr. Stoytcho",male,28,0,0,349207,7.8958,,S
107,1,3,"Salkjelsvik, Miss. Anna Kristine",female,21,0,0,343120,7.65,,S
108,1,3,"Moss, Mr. Albert Johan",male,,0,0,312991,7.775,,S
109,0,3,"Rekic, Mr. Tido",male,38,0,0,349249,7.8958,,S
110,1,3,"Moran, Miss. Bertha",female,,1,0,371110,24.15,,Q
111,0,1,"Porter, Mr. Walter Chamberlain",male,47,0,0,110465,52,C110,S
112,0,3,"Zabour, Miss. Hileni",female,14.5,1,0,2665,14.4542,,C
113,0,3,"Barton, Mr. David John",male,22,0,0,324669,8.05,,S
114,0,3,"Jussila, Miss. Katriina",female,20,1,0,4136,9.825,,S
115,0,3,"Attalah, Miss. Malake",female,17,0,0,2627,14.4583,,C
116,0,3,"Pekoniemi, Mr. Edvard",male,21,0,0,STON/O 2. 3101294,7.925,,S
117,0,3,"Connors, Mr. Patrick",male,70.5,0,0,370369,7.75,,Q
118,0,2,"Turpin, Mr. William John Robert",male,29,1,0,11668,21,,S
119,0,1,"Baxter, Mr. Quigg Edmond",male,24,0,1,PC 17558,247.5208,B58 B60,C
120,0,3,"Andersson, Miss. Ellis Anna Maria",female,2,4,2,347082,31.275,,S
121,0,2,"Hickman, Mr. Stanley George",male,21,2,0,S.O.C. 14879,73.5,,S
122,0,3,"Moore, Mr. Leonard Charles",male,,0,0,A4. 54510,8.05,,S
123,0,2,"Nasser, Mr. Nicholas",male,32.5,1,0,237736,30.0708,,C
124,1,2,"Webber, Miss. Susan",female,32.5,0,0,27267,13,E101,S
125,0,1,"White, Mr. Percival Wayland",male,54,0,1,35281,77.2875,D26,S
126,1,3,"Nicola-Yarred, Master. Elias",male,12,1,0,2651,11.2417,,C
127,0,3,"McMahon, Mr. Martin",male,,0,0,370372,7.75,,Q
128,1,3,"Madsen, Mr. Fridtjof Arne",male,24,0,0,C 17369,7.1417,,S
129,1,3,"Peter, Miss. Anna",female,,1,1,2668,22.3583,F E69,C
130,0,3,"Ekstrom, Mr. Johan",male,45,0,0,347061,6.975,,S
131,0,3,"Drazenoic, Mr. Jozef",male,33,0,0,349241,7.8958,,C
132,0,3,"Coelho, Mr. Domingos Fernandeo",male,20,0,0,SOTON/O.Q. 3101307,7.05,,S
133,0,3,"Robins, Mrs. Alexander A (Grace Charity Laury)",female,47,1,0,A/5. 3337,14.5,,S
134,1,2,"Weisz, Mrs. Leopold (Mathilde Francoise Pede)",female,29,1,0,228414,26,,S
135,0,2,"Sobey, Mr. Samuel James Hayden",male,25,0,0,C.A. 29178,13,,S
136,0,2,"Richard, Mr. Emile",male,23,0,0,SC/PARIS 2133,15.0458,,C
137,1,1,"Newsom, Miss. Helen Monypeny",female,19,0,2,11752,26.2833,D47,S
138,0,1,"Futrelle, Mr. Jacques Heath",male,37,1,0,113803,53.1,C123,S
139,0,3,"Osen, Mr. Olaf Elon",male,16,0,0,7534,9.2167,,S
140,0,1,"Giglio, Mr. Victor",male,24,0,0,PC 17593,79.2,B86,C
141,0,3,"Boulos, Mrs. Joseph (Sultana)",female,,0,2,2678,15.2458,,C
142,1,3,"Nysten, Miss. Anna Sofia",female,22,0,0,347081,7.75,,S
143,1,3,"Hakkarainen, Mrs. Pekka Pietari (Elin Matilda Dolck)",female,24,1,0,STON/O2. 3101279,15.85,,S
144,0,3,"Burke, Mr. Jeremiah",male,19,0,0,365222,6.75,,Q
145,0,2,"Andrew, Mr. Edgardo Samuel",male,18,0,0,231945,11.5,,S
146,0,2,"Nicholls, Mr. Joseph Charles",male,19,1,1,C.A. 33112,36.75,,S
147,1,3,"Andersson, Mr. August Edvard (""Wennerstrom"")",male,27,0,0,350043,7.7958,,S
148,0,3,"Ford, Miss. Robina Maggie ""Ruby""",female,9,2,2,W./C. 6608,34.375,,S
149,0,2,"Navratil, Mr. Michel (""Louis M Hoffman"")",male,36.5,0,2,230080,26,F2,S
150,0,2,"Byles, Rev. Thomas Roussel Davids",male,42,0,0,244310,13,,S
151,0,2,"Bateman, Rev. Robert James",male,51,0,0,S.O.P. 1166,12.525,,S
152,1,1,"Pears, Mrs. Thomas (Edith Wearne)",female,22,1,0,113776,66.6,C2,S
153,0,3,"Meo, Mr. Alfonzo",male,55.5,0,0,A.5. 11206,8.05,,S
154,0,3,"van Billiard, Mr. Austin Blyler",male,40.5,0,2,A/5. 851,14.5,,S
155,0,3,"Olsen, Mr. Ole Martin",male,,0,0,Fa 265302,7.3125,,S
156,0,1,"Williams, Mr. Charles Duane",male,51,0,1,PC 17597,61.3792,,C
157,1,3,"Gilnagh, Miss. Katherine ""Katie""",female,16,0,0,35851,7.7333,,Q
158,0,3,"Corn, Mr. Harry",male,30,0,0,SOTON/OQ 392090,8.05,,S
159,0,3,"Smiljanic, Mr. Mile",male,,0,0,315037,8.6625,,S
160,0,3,"Sage, Master. Thomas Henry",male,,8,2,CA. 2343,69.55,,S
161,0,3,"Cribb, Mr. John Hatfield",male,44,0,1,371362,16.1,,S
162,1,2,"Watt, Mrs. James (Elizabeth ""Bessie"" Inglis Milne)",female,40,0,0,C.A. 33595,15.75,,S
163,0,3,"Bengtsson, Mr. John Viktor",male,26,0,0,347068,7.775,,S
164,0,3,"Calic, Mr. Jovo",male,17,0,0,315093,8.6625,,S
165,0,3,"Panula, Master. Eino Viljami",male,1,4,1,3101295,39.6875,,S
166,1,3,"Goldsmith, Master. Frank John William ""Frankie""",male,9,0,2,363291,20.525,,S
167,1,1,"Chibnall, Mrs. (Edith Martha Bowerman)",female,,0,1,113505,55,E33,S
168,0,3,"Skoog, Mrs. William (Anna Bernhardina Karlsson)",female,45,1,4,347088,27.9,,S
169,0,1,"Baumann, Mr. John D",male,,0,0,PC 17318,25.925,,S
170,0,3,"Ling, Mr. Lee",male,28,0,0,1601,56.4958,,S
171,0,1,"Van der hoef, Mr. Wyckoff",male,61,0,0,111240,33.5,B19,S
172,0,3,"Rice, Master. Arthur",male,4,4,1,382652,29.125,,Q
173,1,3,"Johnson, Miss. Eleanor Ileen",female,1,1,1,347742,11.1333,,S
174,0,3,"Sivola, Mr. Antti Wilhelm",male,21,0,0,STON/O 2. 3101280,7.925,,S
175,0,1,"Smith, Mr. James Clinch",male,56,0,0,17764,30.6958,A7,C
176,0,3,"Klasen, Mr. Klas Albin",male,18,1,1,350404,7.8542,,S
177,0,3,"Lefebre, Master. Henry Forbes",male,,3,1,4133,25.4667,,S
178,0,1,"Isham, Miss. Ann Elizabeth",female,50,0,0,PC 17595,28.7125,C49,C
179,0,2,"Hale, Mr. Reginald",male,30,0,0,250653,13,,S
180,0,3,"Leonard, Mr. Lionel",male,36,0,0,LINE,0,,S
181,0,3,"Sage, Miss. Constance Gladys",female,,8,2,CA. 2343,69.55,,S
182,0,2,"Pernot, Mr. Rene",male,,0,0,SC/PARIS 2131,15.05,,C
183,0,3,"Asplund, Master. Clarence Gustaf Hugo",male,9,4,2,347077,31.3875,,S
184,1,2,"Becker, Master. Richard F",male,1,2,1,230136,39,F4,S
185,1,3,"Kink-Heilmann, Miss. Luise Gretchen",female,4,0,2,315153,22.025,,S
186,0,1,"Rood, Mr. Hugh Roscoe",male,,0,0,113767,50,A32,S
187,1,3,"O'Brien, Mrs. Thomas (Johanna ""Hannah"" Godfrey)",female,,1,0,370365,15.5,,Q
188,1,1,"Romaine, Mr. Charles Hallace (""Mr C Rolmane"")",male,45,0,0,111428,26.55,,S
189,0,3,"Bourke, Mr. John",male,40,1,1,364849,15.5,,Q
190,0,3,"Turcin, Mr. Stjepan",male,36,0,0,349247,7.8958,,S
191,1,2,"Pinsky, Mrs. (Rosa)",female,32,0,0,234604,13,,S
192,0,2,"Carbines, Mr. William",male,19,0,0,28424,13,,S
193,1,3,"Andersen-Jensen, Miss. Carla Christine Nielsine",female,19,1,0,350046,7.8542,,S
194,1,2,"Navratil, Master. Michel M",male,3,1,1,230080,26,F2,S
195,1,1,"Brown, Mrs. James Joseph (Margaret Tobin)",female,44,0,0,PC 17610,27.7208,B4,C
196,1,1,"Lurette, Miss. Elise",female,58,0,0,PC 17569,146.5208,B80,C
197,0,3,"Mernagh, Mr. Robert",male,,0,0,368703,7.75,,Q
198,0,3,"Olsen, Mr. Karl Siegwart Andreas",male,42,0,1,4579,8.4042,,S
199,1,3,"Madigan, Miss. Margaret ""Maggie""",female,,0,0,370370,7.75,,Q
200,0,2,"Yrois, Miss. Henriette (""Mrs Harbeck"")",female,24,0,0,248747,13,,S
201,0,3,"Vande Walle, Mr. Nestor Cyriel",male,28,0,0,345770,9.5,,S
202,0,3,"Sage, Mr. Frederick",male,,8,2,CA. 2343,69.55,,S
203,0,3,"Johanson, Mr. Jakob Alfred",male,34,0,0,3101264,6.4958,,S
204,0,3,"Youseff, Mr. Gerious",male,45.5,0,0,2628,7.225,,C
205,1,3,"Cohen, Mr. Gurshon ""Gus""",male,18,0,0,A/5 3540,8.05,,S
206,0,3,"Strom, Miss. Telma Matilda",female,2,0,1,347054,10.4625,G6,S
207,0,3,"Backstrom, Mr. Karl Alfred",male,32,1,0,3101278,15.85,,S
208,1,3,"Albimona, Mr. Nassef Cassem",male,26,0,0,2699,18.7875,,C
209,1,3,"Carr, Miss. Helen ""Ellen""",female,16,0,0,367231,7.75,,Q
210,1,1,"Blank, Mr. Henry",male,40,0,0,112277,31,A31,C
211,0,3,"Ali, Mr. Ahmed",male,24,0,0,SOTON/O.Q. 3101311,7.05,,S
212,1,2,"Cameron, Miss. Clear Annie",female,35,0,0,F.C.C. 13528,21,,S
213,0,3,"Perkin, Mr. John Henry",male,22,0,0,A/5 21174,7.25,,S
214,0,2,"Givard, Mr. Hans Kristensen",male,30,0,0,250646,13,,S
215,0,3,"Kiernan, Mr. Philip",male,,1,0,367229,7.75,,Q
216,1,1,"Newell, Miss. Madeleine",female,31,1,0,35273,113.275,D36,C
217,1,3,"Honkanen, Miss. Eliina",female,27,0,0,STON/O2. 3101283,7.925,,S
218,0,2,"Jacobsohn, Mr. Sidney Samuel",male,42,1,0,243847,27,,S
219,1,1,"Bazzani, Miss. Albina",female,32,0,0,11813,76.2917,D15,C
220,0,2,"Harris, Mr. Walter",male,30,0,0,W/C 14208,10.5,,S
221,1,3,"Sunderland, Mr. Victor Francis",male,16,0,0,SOTON/OQ 392089,8.05,,S
222,0,2,"Bracken, Mr. James H",male,27,0,0,220367,13,,S
223,0,3,"Green, Mr. George Henry",male,51,0,0,21440,8.05,,S
224,0,3,"Nenkoff, Mr. Christo",male,,0,0,349234,7.8958,,S
225,1,1,"Hoyt, Mr. Frederick Maxfield",male,38,1,0,19943,90,C93,S
226,0,3,"Berglund, Mr. Karl Ivar Sven",male,22,0,0,PP 4348,9.35,,S
227,1,2,"Mellors, Mr. William John",male,19,0,0,SW/PP 751,10.5,,S
228,0,3,"Lovell, Mr. John Hall (""Henry"")",male,20.5,0,0,A/5 21173,7.25,,S
229,0,2,"Fahlstrom, Mr. Arne Jonas",male,18,0,0,236171,13,,S
230,0,3,"Lefebre, Miss. Mathilde",female,,3,1,4133,25.4667,,S
231,1,1,"Harris, Mrs. Henry Birkhardt (Irene Wallach)",female,35,1,0,36973,83.475,C83,S
232,0,3,"Larsson, Mr. Bengt Edvin",male,29,0,0,347067,7.775,,S
233,0,2,"Sjostedt, Mr. Ernst Adolf",male,59,0,0,237442,13.5,,S
234,1,3,"Asplund, Miss. Lillian Gertrud",female,5,4,2,347077,31.3875,,S
235,0,2,"Leyson, Mr. Robert William Norman",male,24,0,0,C.A. 29566,10.5,,S
236,0,3,"Harknett, Miss. Alice Phoebe",female,,0,0,W./C. 6609,7.55,,S
237,0,2,"Hold, Mr. Stephen",male,44,1,0,26707,26,,S
238,1,2,"Collyer, Miss. Marjorie ""Lottie""",female,8,0,2,C.A. 31921,26.25,,S
239,0,2,"Pengelly, Mr. Frederick William",male,19,0,0,28665,10.5,,S
240,0,2,"Hunt, Mr. George Henry",male,33,0,0,SCO/W 1585,12.275,,S
241,0,3,"Zabour, Miss. Thamine",female,,1,0,2665,14.4542,,C
242,1,3,"Murphy, Miss. Katherine ""Kate""",female,,1,0,367230,15.5,,Q
243,0,2,"Coleridge, Mr. Reginald Charles",male,29,0,0,W./C. 14263,10.5,,S
244,0,3,"Maenpaa, Mr. Matti Alexanteri",male,22,0,0,STON/O 2. 3101275,7.125,,S
245,0,3,"Attalah, Mr. Sleiman",male,30,0,0,2694,7.225,,C
246,0,1,"Minahan, Dr. William Edward",male,44,2,0,19928,90,C78,Q
247,0,3,"Lindahl, Miss. Agda Thorilda Viktoria",female,25,0,0,347071,7.775,,S
248,1,2,"Hamalainen, Mrs. William (Anna)",female,24,0,2,250649,14.5,,S
249,1,1,"Beckwith, Mr. Richard Leonard",male,37,1,1,11751,52.5542,D35,S
250,0,2,"Carter, Rev. Ernest Courtenay",male,54,1,0,244252,26,,S
251,0,3,"Reed, Mr. James George",male,,0,0,362316,7.25,,S
252,0,3,"Strom, Mrs. Wilhelm (Elna Matilda Persson)",female,29,1,1,347054,10.4625,G6,S
253,0,1,"Stead, Mr. William Thomas",male,62,0,0,113514,26.55,C87,S
254,0,3,"Lobb, Mr. William Arthur",male,30,1,0,A/5. 3336,16.1,,S
255,0,3,"Rosblom, Mrs. Viktor (Helena Wilhelmina)",female,41,0,2,370129,20.2125,,S
256,1,3,"Touma, Mrs. Darwis (Hanne Youssef Razi)",female,29,0,2,2650,15.2458,,C
257,1,1,"Thorne, Mrs. Gertrude Maybelle",female,,0,0,PC 17585,79.2,,C
258,1,1,"Cherry, Miss. Gladys",female,30,0,0,110152,86.5,B77,S
259,1,1,"Ward, Miss. Anna",female,35,0,0,PC 17755,512.3292,,C
260,1,2,"Parrish, Mrs. (Lutie Davis)",female,50,0,1,230433,26,,S
261,0,3,"Smith, Mr. Thomas",male,,0,0,384461,7.75,,Q
262,1,3,"Asplund, Master. Edvin Rojj Felix",male,3,4,2,347077,31.3875,,S
263,0,1,"Taussig, Mr. Emil",male,52,1,1,110413,79.65,E67,S
264,0,1,"Harrison, Mr. William",male,40,0,0,112059,0,B94,S
265,0,3,"Henry, Miss. Delia",female,,0,0,382649,7.75,,Q
266,0,2,"Reeves, Mr. David",male,36,0,0,C.A. 17248,10.5,,S
267,0,3,"Panula, Mr. Ernesti Arvid",male,16,4,1,3101295,39.6875,,S
268,1,3,"Persson, Mr. Ernst Ulrik",male,25,1,0,347083,7.775,,S
269,1,1,"Graham, Mrs. William Thompson (Edith Junkins)",female,58,0,1,PC 17582,153.4625,C125,S
270,1,1,"Bissette, Miss. Amelia",female,35,0,0,PC 17760,135.6333,C99,S
271,0,1,"Cairns, Mr. Alexander",male,,0,0,113798,31,,S
272,1,3,"Tornquist, Mr. William Henry",male,25,0,0,LINE,0,,S
273,1,2,"Mellinger, Mrs. (Elizabeth Anne Maidment)",female,41,0,1,250644,19.5,,S
274,0,1,"Natsch, Mr. Charles H",male,37,0,1,PC 17596,29.7,C118,C
275,1,3,"Healy, Miss. Hanora ""Nora""",female,,0,0,370375,7.75,,Q
276,1,1,"Andrews, Miss. Kornelia Theodosia",female,63,1,0,13502,77.9583,D7,S
277,0,3,"Lindblom, Miss. Augusta Charlotta",female,45,0,0,347073,7.75,,S
278,0,2,"Parkes, Mr. Francis ""Frank""",male,,0,0,239853,0,,S
279,0,3,"Rice, Master. Eric",male,7,4,1,382652,29.125,,Q
280,1,3,"Abbott, Mrs. Stanton (Rosa Hunt)",female,35,1,1,C.A. 2673,20.25,,S
281,0,3,"Duane, Mr. Frank",male,65,0,0,336439,7.75,,Q
282,0,3,"Olsson, Mr. Nils Johan Goransson",male,28,0,0,347464,7.8542,,S
283,0,3,"de Pelsmaeker, Mr. Alfons",male,16,0,0,345778,9.5,,S
284,1,3,"Dorking, Mr. Edward Arthur",male,19,0,0,A/5. 10482,8.05,,S
285,0,1,"Smith, Mr. Richard William",male,,0,0,113056,26,A19,S
286,0,3,"Stankovic, Mr. Ivan",male,33,0,0,349239,8.6625,,C
287,1,3,"de Mulder, Mr. Theodore",male,30,0,0,345774,9.5,,S
288,0,3,"Naidenoff, Mr. Penko",male,22,0,0,349206,7.8958,,S
289,1,2,"Hosono, Mr. Masabumi",male,42,0,0,237798,13,,S
290,1,3,"Connolly, Miss. Kate",female,22,0,0,370373,7.75,,Q
291,1,1,"Barber, Miss. Ellen ""Nellie""",female,26,0,0,19877,78.85,,S
292,1,1,"Bishop, Mrs. Dickinson H (Helen Walton)",female,19,1,0,11967,91.0792,B49,C
293,0,2,"Levy, Mr. Rene Jacques",male,36,0,0,SC/Paris 2163,12.875,D,C
294,0,3,"Haas, Miss. Aloisia",female,24,0,0,349236,8.85,,S
295,0,3,"Mineff, Mr. Ivan",male,24,0,0,349233,7.8958,,S
296,0,1,"Lewy, Mr. Ervin G",male,,0,0,PC 17612,27.7208,,C
297,0,3,"Hanna, Mr. Mansour",male,23.5,0,0,2693,7.2292,,C
298,0,1,"Allison, Miss. Helen Loraine",female,2,1,2,113781,151.55,C22 C26,S
299,1,1,"Saalfeld, Mr. Adolphe",male,,0,0,19988,30.5,C106,S
300,1,1,"Baxter, Mrs. James (Helene DeLaudeniere Chaput)",female,50,0,1,PC 17558,247.5208,B58 B60,C
301,1,3,"Kelly, Miss. Anna Katherine ""Annie Kate""",female,,0,0,9234,7.75,,Q
302,1,3,"McCoy, Mr. Bernard",male,,2,0,367226,23.25,,Q
303,0,3,"Johnson, Mr. William Cahoone Jr",male,19,0,0,LINE,0,,S
304,1,2,"Keane, Miss. Nora A",female,,0,0,226593,12.35,E101,Q
305,0,3,"Williams, Mr. Howard Hugh ""Harry""",male,,0,0,A/5 2466,8.05,,S
306,1,1,"Allison, Master. Hudson Trevor",male,0.92,1,2,113781,151.55,C22 C26,S
307,1,1,"Fleming, Miss. Margaret",female,,0,0,17421,110.8833,,C
308,1,1,"Penasco y Castellana, Mrs. Victor de Satode (Maria Josefa Perez de Soto y Vallejo)",female,17,1,0,PC 17758,108.9,C65,C
309,0,2,"Abelson, Mr. Samuel",male,30,1,0,P/PP 3381,24,,C
310,1,1,"Francatelli, Miss. Laura Mabel",female,30,0,0,PC 17485,56.9292,E36,C
311,1,1,"Hays, Miss. Margaret Bechstein",female,24,0,0,11767,83.1583,C54,C
312,1,1,"Ryerson, Miss. Emily Borie",female,18,2,2,PC 17608,262.375,B57 B59 B63 B66,C
313,0,2,"Lahtinen, Mrs. William (Anna Sylfven)",female,26,1,1,250651,26,,S
314,0,3,"Hendekovic, Mr. Ignjac",male,28,0,0,349243,7.8958,,S
315,0,2,"Hart, Mr. Benjamin",male,43,1,1,F.C.C. 13529,26.25,,S
316,1,3,"Nilsson, Miss. Helmina Josefina",female,26,0,0,347470,7.8542,,S
317,1,2,"Kantor, Mrs. Sinai (Miriam Sternin)",female,24,1,0,244367,26,,S
318,0,2,"Moraweck, Dr. Ernest",male,54,0,0,29011,14,,S
319,1,1,"Wick, Miss. Mary Natalie",female,31,0,2,36928,164.8667,C7,S
320,1,1,"Spedden, Mrs. Frederic Oakley (Margaretta Corning Stone)",female,40,1,1,16966,134.5,E34,C
321,0,3,"Dennis, Mr. Samuel",male,22,0,0,A/5 21172,7.25,,S
322,0,3,"Danoff, Mr. Yoto",male,27,0,0,349219,7.8958,,S
323,1,2,"Slayter, Miss. Hilda Mary",female,30,0,0,234818,12.35,,Q
324,1,2,"Caldwell, Mrs. Albert Francis (Sylvia Mae Harbaugh)",female,22,1,1,248738,29,,S
325,0,3,"Sage, Mr. George John Jr",male,,8,2,CA. 2343,69.55,,S
326,1,1,"Young, Miss. Marie Grice",female,36,0,0,PC 17760,135.6333,C32,C
327,0,3,"Nysveen, Mr. Johan Hansen",male,61,0,0,345364,6.2375,,S
328,1,2,"Ball, Mrs. (Ada E Hall)",female,36,0,0,28551,13,D,S
329,1,3,"Goldsmith, Mrs. Frank John (Emily Alice Brown)",female,31,1,1,363291,20.525,,S
330,1,1,"Hippach, Miss. Jean Gertrude",female,16,0,1,111361,57.9792,B18,C
331,1,3,"McCoy, Miss. Agnes",female,,2,0,367226,23.25,,Q
332,0,1,"Partner, Mr. Austen",male,45.5,0,0,113043,28.5,C124,S
333,0,1,"Graham, Mr. George Edward",male,38,0,1,PC 17582,153.4625,C91,S
334,0,3,"Vander Planke, Mr. Leo Edmondus",male,16,2,0,345764,18,,S
335,1,1,"Frauenthal, Mrs. Henry William (Clara Heinsheimer)",female,,1,0,PC 17611,133.65,,S
336,0,3,"Denkoff, Mr. Mitto",male,,0,0,349225,7.8958,,S
337,0,1,"Pears, Mr. Thomas Clinton",male,29,1,0,113776,66.6,C2,S
338,1,1,"Burns, Miss. Elizabeth Margaret",female,41,0,0,16966,134.5,E40,C
339,1,3,"Dahl, Mr. Karl Edwart",male,45,0,0,7598,8.05,,S
340,0,1,"Blackwell, Mr. Stephen Weart",male,45,0,0,113784,35.5,T,S
341,1,2,"Navratil, Master. Edmond Roger",male,2,1,1,230080,26,F2,S
342,1,1,"Fortune, Miss. Alice Elizabeth",female,24,3,2,19950,263,C23 C25 C27,S
343,0,2,"Collander, Mr. Erik Gustaf",male,28,0,0,248740,13,,S
344,0,2,"Sedgwick, Mr. Charles Frederick Waddington",male,25,0,0,244361,13,,S
345,0,2,"Fox, Mr. Stanley Hubert",male,36,0,0,229236,13,,S
346,1,2,"Brown, Miss. Amelia ""Mildred""",female,24,0,0,248733,13,F33,S
347,1,2,"Smith, Miss. Marion Elsie",female,40,0,0,31418,13,,S
348,1,3,"Davison, Mrs. Thomas Henry (Mary E Finck)",female,,1,0,386525,16.1,,S
349,1,3,"Coutts, Master. William Loch ""William""",male,3,1,1,C.A. 37671,15.9,,S
350,0,3,"Dimic, Mr. Jovan",male,42,0,0,315088,8.6625,,S
351,0,3,"Odahl, Mr. Nils Martin",male,23,0,0,7267,9.225,,S
352,0,1,"Williams-Lambert, Mr. Fletcher Fellows",male,,0,0,113510,35,C128,S
353,0,3,"Elias, Mr. Tannous",male,15,1,1,2695,7.2292,,C
354,0,3,"Arnold-Franchi, Mr. Josef",male,25,1,0,349237,17.8,,S
355,0,3,"Yousif, Mr. Wazli",male,,0,0,2647,7.225,,C
356,0,3,"Vanden Steen, Mr. Leo Peter",male,28,0,0,345783,9.5,,S
357,1,1,"Bowerman, Miss. Elsie Edith",female,22,0,1,113505,55,E33,S
358,0,2,"Funk, Miss. Annie Clemmer",female,38,0,0,237671,13,,S
359,1,3,"McGovern, Miss. Mary",female,,0,0,330931,7.8792,,Q
360,1,3,"Mockler, Miss. Helen Mary ""Ellie""",female,,0,0,330980,7.8792,,Q
361,0,3,"Skoog, Mr. Wilhelm",male,40,1,4,347088,27.9,,S
362,0,2,"del Carlo, Mr. Sebastiano",male,29,1,0,SC/PARIS 2167,27.7208,,C
363,0,3,"Barbara, Mrs. (Catherine David)",female,45,0,1,2691,14.4542,,C
364,0,3,"Asim, Mr. Adola",male,35,0,0,SOTON/O.Q. 3101310,7.05,,S
365,0,3,"O'Brien, Mr. Thomas",male,,1,0,370365,15.5,,Q
366,0,3,"Adahl, Mr. Mauritz Nils Martin",male,30,0,0,C 7076,7.25,,S
367,1,1,"Warren, Mrs. Frank Manley (Anna Sophia Atkinson)",female,60,1,0,110813,75.25,D37,C
368,1,3,"Moussa, Mrs. (Mantoura Boulos)",female,,0,0,2626,7.2292,,C
369,1,3,"Jermyn, Miss. Annie",female,,0,0,14313,7.75,,Q
370,1,1,"Aubart, Mme. Leontine Pauline",female,24,0,0,PC 17477,69.3,B35,C
371,1,1,"Harder, Mr. George Achilles",male,25,1,0,11765,55.4417,E50,C
372,0,3,"Wiklund, Mr. Jakob Alfred",male,18,1,0,3101267,6.4958,,S
373,0,3,"Beavan, Mr. William Thomas",male,19,0,0,323951,8.05,,S
374,0,1,"Ringhini, Mr. Sante",male,22,0,0,PC 17760,135.6333,,C
375,0,3,"Palsson, Miss. Stina Viola",female,3,3,1,349909,21.075,,S
376,1,1,"Meyer, Mrs. Edgar Joseph (Leila Saks)",female,,1,0,PC 17604,82.1708,,C
377,1,3,"Landergren, Miss. Aurora Adelia",female,22,0,0,C 7077,7.25,,S
378,0,1,"Widener, Mr. Harry Elkins",male,27,0,2,113503,211.5,C82,C
379,0,3,"Betros, Mr. Tannous",male,20,0,0,2648,4.0125,,C
380,0,3,"Gustafsson, Mr. Karl Gideon",male,19,0,0,347069,7.775,,S
381,1,1,"Bidois, Miss. Rosalie",female,42,0,0,PC 17757,227.525,,C
382,1,3,"Nakid, Miss. Maria (""Mary"")",female,1,0,2,2653,15.7417,,C
383,0,3,"Tikkanen, Mr. Juho",male,32,0,0,STON/O 2. 3101293,7.925,,S
384,1,1,"Holverson, Mrs. Alexander Oskar (Mary Aline Towner)",female,35,1,0,113789,52,,S
385,0,3,"Plotcharsky, Mr. Vasil",male,,0,0,349227,7.8958,,S
386,0,2,"Davies, Mr. Charles Henry",male,18,0,0,S.O.C. 14879,73.5,,S
387,0,3,"Goodwin, Master. Sidney Leonard",male,1,5,2,CA 2144,46.9,,S
388,1,2,"Buss, Miss. Kate",female,36,0,0,27849,13,,S
389,0,3,"Sadlier, Mr. Matthew",male,,0,0,367655,7.7292,,Q
390,1,2,"Lehmann, Miss. Bertha",female,17,0,0,SC 1748,12,,C
391,1,1,"Carter, Mr. William Ernest",male,36,1,2,113760,120,B96 B98,S
392,1,3,"Jansson, Mr. Carl Olof",male,21,0,0,350034,7.7958,,S
393,0,3,"Gustafsson, Mr. Johan Birger",male,28,2,0,3101277,7.925,,S
394,1,1,"Newell, Miss. Marjorie",female,23,1,0,35273,113.275,D36,C
395,1,3,"Sandstrom, Mrs. Hjalmar (Agnes Charlotta Bengtsson)",female,24,0,2,PP 9549,16.7,G6,S
396,0,3,"Johansson, Mr. Erik",male,22,0,0,350052,7.7958,,S
397,0,3,"Olsson, Miss. Elina",female,31,0,0,350407,7.8542,,S
398,0,2,"McKane, Mr. Peter David",male,46,0,0,28403,26,,S
399,0,2,"Pain, Dr. Alfred",male,23,0,0,244278,10.5,,S
400,1,2,"Trout, Mrs. William H (Jessie L)",female,28,0,0,240929,12.65,,S
401,1,3,"Niskanen, Mr. Juha",male,39,0,0,STON/O 2. 3101289,7.925,,S
402,0,3,"Adams, Mr. John",male,26,0,0,341826,8.05,,S
403,0,3,"Jussila, Miss. Mari Aina",female,21,1,0,4137,9.825,,S
404,0,3,"Hakkarainen, Mr. Pekka Pietari",male,28,1,0,STON/O2. 3101279,15.85,,S
405,0,3,"Oreskovic, Miss. Marija",female,20,0,0,315096,8.6625,,S
406,0,2,"Gale, Mr. Shadrach",male,34,1,0,28664,21,,S
407,0,3,"Widegren, Mr. Carl/Charles Peter",male,51,0,0,347064,7.75,,S
408,1,2,"Richards, Master. William Rowe",male,3,1,1,29106,18.75,,S
409,0,3,"Birkeland, Mr. Hans Martin Monsen",male,21,0,0,312992,7.775,,S
410,0,3,"Lefebre, Miss. Ida",female,,3,1,4133,25.4667,,S
411,0,3,"Sdycoff, Mr. Todor",male,,0,0,349222,7.8958,,S
412,0,3,"Hart, Mr. Henry",male,,0,0,394140,6.8583,,Q
413,1,1,"Minahan, Miss. Daisy E",female,33,1,0,19928,90,C78,Q
414,0,2,"Cunningham, Mr. Alfred Fleming",male,,0,0,239853,0,,S
415,1,3,"Sundman, Mr. Johan Julian",male,44,0,0,STON/O 2. 3101269,7.925,,S
416,0,3,"Meek, Mrs. Thomas (Annie Louise Rowley)",female,,0,0,343095,8.05,,S
417,1,2,"Drew, Mrs. James Vivian (Lulu Thorne Christian)",female,34,1,1,28220,32.5,,S
418,1,2,"Silven, Miss. Lyyli Karoliina",female,18,0,2,250652,13,,S
419,0,2,"Matthews, Mr. William John",male,30,0,0,28228,13,,S
420,0,3,"Van Impe, Miss. Catharina",female,10,0,2,345773,24.15,,S
421,0,3,"Gheorgheff, Mr. Stanio",male,,0,0,349254,7.8958,,C
422,0,3,"Charters, Mr. David",male,21,0,0,A/5. 13032,7.7333,,Q
423,0,3,"Zimmerman, Mr. Leo",male,29,0,0,315082,7.875,,S
424,0,3,"Danbom, Mrs. Ernst Gilbert (Anna Sigrid Maria Brogren)",female,28,1,1,347080,14.4,,S
425,0,3,"Rosblom, Mr. Viktor Richard",male,18,1,1,370129,20.2125,,S
426,0,3,"Wiseman, Mr. Phillippe",male,,0,0,A/4. 34244,7.25,,S
427,1,2,"Clarke, Mrs. Charles V (Ada Maria Winfield)",female,28,1,0,2003,26,,S
428,1,2,"Phillips, Miss. Kate Florence (""Mrs Kate Louise Phillips Marshall"")",female,19,0,0,250655,26,,S
429,0,3,"Flynn, Mr. James",male,,0,0,364851,7.75,,Q
430,1,3,"Pickard, Mr. Berk (Berk Trembisky)",male,32,0,0,SOTON/O.Q. 392078,8.05,E10,S
431,1,1,"Bjornstrom-Steffansson, Mr. Mauritz Hakan",male,28,0,0,110564,26.55,C52,S
432,1,3,"Thorneycroft, Mrs. Percival (Florence Kate White)",female,,1,0,376564,16.1,,S
433,1,2,"Louch, Mrs. Charles Alexander (Alice Adelaide Slow)",female,42,1,0,SC/AH 3085,26,,S
434,0,3,"Kallio, Mr. Nikolai Erland",male,17,0,0,STON/O 2. 3101274,7.125,,S
435,0,1,"Silvey, Mr. William Baird",male,50,1,0,13507,55.9,E44,S
436,1,1,"Carter, Miss. Lucile Polk",female,14,1,2,113760,120,B96 B98,S
437,0,3,"Ford, Miss. Doolina Margaret ""Daisy""",female,21,2,2,W./C. 6608,34.375,,S
438,1,2,"Richards, Mrs. Sidney (Emily Hocking)",female,24,2,3,29106,18.75,,S
439,0,1,"Fortune, Mr. Mark",male,64,1,4,19950,263,C23 C25 C27,S
440,0,2,"Kvillner, Mr. Johan Henrik Johannesson",male,31,0,0,C.A. 18723,10.5,,S
441,1,2,"Hart, Mrs. Benjamin (Esther Ada Bloomfield)",female,45,1,1,F.C.C. 13529,26.25,,S
442,0,3,"Hampe, Mr. Leon",male,20,0,0,345769,9.5,,S
443,0,3,"Petterson, Mr. Johan Emil",male,25,1,0,347076,7.775,,S
444,1,2,"Reynaldo, Ms. Encarnacion",female,28,0,0,230434,13,,S
445,1,3,"Johannesen-Bratthammer, Mr. Bernt",male,,0,0,65306,8.1125,,S
446,1,1,"Dodge, Master. Washington",male,4,0,2,33638,81.8583,A34,S
447,1,2,"Mellinger, Miss. Madeleine Violet",female,13,0,1,250644,19.5,,S
448,1,1,"Seward, Mr. Frederic Kimber",male,34,0,0,113794,26.55,,S
449,1,3,"Baclini, Miss. Marie Catherine",female,5,2,1,2666,19.2583,,C
450,1,1,"Peuchen, Major. Arthur Godfrey",male,52,0,0,113786,30.5,C104,S
451,0,2,"West, Mr. Edwy Arthur",male,36,1,2,C.A. 34651,27.75,,S
452,0,3,"Hagland, Mr. Ingvald Olai Olsen",male,,1,0,65303,19.9667,,S
453,0,1,"Foreman, Mr. Benjamin Laventall",male,30,0,0,113051,27.75,C111,C
454,1,1,"Goldenberg, Mr. Samuel L",male,49,1,0,17453,89.1042,C92,C
455,0,3,"Peduzzi, Mr. Joseph",male,,0,0,A/5 2817,8.05,,S
456,1,3,"Jalsevac, Mr. Ivan",male,29,0,0,349240,7.8958,,C
457,0,1,"Millet, Mr. Francis Davis",male,65,0,0,13509,26.55,E38,S
458,1,1,"Kenyon, Mrs. Frederick R (Marion)",female,,1,0,17464,51.8625,D21,S
459,1,2,"Toomey, Miss. Ellen",female,50,0,0,F.C.C. 13531,10.5,,S
460,0,3,"O'Connor, Mr. Maurice",male,,0,0,371060,7.75,,Q
461,1,1,"Anderson, Mr. Harry",male,48,0,0,19952,26.55,E12,S
462,0,3,"Morley, Mr. William",male,34,0,0,364506,8.05,,S
463,0,1,"Gee, Mr. Arthur H",male,47,0,0,111320,38.5,E63,S
464,0,2,"Milling, Mr. Jacob Christian",male,48,0,0,234360,13,,S
465,0,3,"Maisner, Mr. Simon",male,,0,0,A/S 2816,8.05,,S
466,0,3,"Goncalves, Mr. Manuel Estanslas",male,38,0,0,SOTON/O.Q. 3101306,7.05,,S
467,0,2,"Campbell, Mr. William",male,,0,0,239853,0,,S
468,0,1,"Smart, Mr. John Montgomery",male,56,0,0,113792,26.55,,S
469,0,3,"Scanlan, Mr. James",male,,0,0,36209,7.725,,Q
470,1,3,"Baclini, Miss. Helene Barbara",female,0.75,2,1,2666,19.2583,,C
471,0,3,"Keefe, Mr. Arthur",male,,0,0,323592,7.25,,S
472,0,3,"Cacic, Mr. Luka",male,38,0,0,315089,8.6625,,S
473,1,2,"West, Mrs. Edwy Arthur (Ada Mary Worth)",female,33,1,2,C.A. 34651,27.75,,S
474,1,2,"Jerwan, Mrs. Amin S (Marie Marthe Thuillard)",female,23,0,0,SC/AH Basle 541,13.7917,D,C
475,0,3,"Strandberg, Miss. Ida Sofia",female,22,0,0,7553,9.8375,,S
476,0,1,"Clifford, Mr. George Quincy",male,,0,0,110465,52,A14,S
477,0,2,"Renouf, Mr. Peter Henry",male,34,1,0,31027,21,,S
478,0,3,"Braund, Mr. Lewis Richard",male,29,1,0,3460,7.0458,,S
479,0,3,"Karlsson, Mr. Nils August",male,22,0,0,350060,7.5208,,S
480,1,3,"Hirvonen, Miss. Hildur E",female,2,0,1,3101298,12.2875,,S
481,0,3,"Goodwin, Master. Harold Victor",male,9,5,2,CA 2144,46.9,,S
482,0,2,"Frost, Mr. Anthony Wood ""Archie""",male,,0,0,239854,0,,S
483,0,3,"Rouse, Mr. Richard Henry",male,50,0,0,A/5 3594,8.05,,S
484,1,3,"Turkula, Mrs. (Hedwig)",female,63,0,0,4134,9.5875,,S
485,1,1,"Bishop, Mr. Dickinson H",male,25,1,0,11967,91.0792,B49,C
486,0,3,"Lefebre, Miss. Jeannie",female,,3,1,4133,25.4667,,S
487,1,1,"Hoyt, Mrs. Frederick Maxfield (Jane Anne Forby)",female,35,1,0,19943,90,C93,S
488,0,1,"Kent, Mr. Edward Austin",male,58,0,0,11771,29.7,B37,C
489,0,3,"Somerton, Mr. Francis William",male,30,0,0,A.5. 18509,8.05,,S
490,1,3,"Coutts, Master. Eden Leslie ""Neville""",male,9,1,1,C.A. 37671,15.9,,S
491,0,3,"Hagland, Mr. Konrad Mathias Reiersen",male,,1,0,65304,19.9667,,S
492,0,3,"Windelov, Mr. Einar",male,21,0,0,SOTON/OQ 3101317,7.25,,S
493,0,1,"Molson, Mr. Harry Markland",male,55,0,0,113787,30.5,C30,S
494,0,1,"Artagaveytia, Mr. Ramon",male,71,0,0,PC 17609,49.5042,,C
495,0,3,"Stanley, Mr. Edward Roland",male,21,0,0,A/4 45380,8.05,,S
496,0,3,"Yousseff, Mr. Gerious",male,,0,0,2627,14.4583,,C
497,1,1,"Eustis, Miss. Elizabeth Mussey",female,54,1,0,36947,78.2667,D20,C
498,0,3,"Shellard, Mr. Frederick William",male,,0,0,C.A. 6212,15.1,,S
499,0,1,"Allison, Mrs. Hudson J C (Bessie Waldo Daniels)",female,25,1,2,113781,151.55,C22 C26,S
500,0,3,"Svensson, Mr. Olof",male,24,0,0,350035,7.7958,,S
501,0,3,"Calic, Mr. Petar",male,17,0,0,315086,8.6625,,S
502,0,3,"Canavan, Miss. Mary",female,21,0,0,364846,7.75,,Q
503,0,3,"O'Sullivan, Miss. Bridget Mary",female,,0,0,330909,7.6292,,Q
504,0,3,"Laitinen, Miss. Kristina Sofia",female,37,0,0,4135,9.5875,,S
505,1,1,"Maioni, Miss. Roberta",female,16,0,0,110152,86.5,B79,S
506,0,1,"Penasco y Castellana, Mr. Victor de Satode",male,18,1,0,PC 17758,108.9,C65,C
507,1,2,"Quick, Mrs. Frederick Charles (Jane Richards)",female,33,0,2,26360,26,,S
508,1,1,"Bradley, Mr. George (""George Arthur Brayton"")",male,,0,0,111427,26.55,,S
509,0,3,"Olsen, Mr. Henry Margido",male,28,0,0,C 4001,22.525,,S
510,1,3,"Lang, Mr. Fang",male,26,0,0,1601,56.4958,,S
511,1,3,"Daly, Mr. Eugene Patrick",male,29,0,0,382651,7.75,,Q
512,0,3,"Webber, Mr. James",male,,0,0,SOTON/OQ 3101316,8.05,,S
513,1,1,"McGough, Mr. James Robert",male,36,0,0,PC 17473,26.2875,E25,S
514,1,1,"Rothschild, Mrs. Martin (Elizabeth L. Barrett)",female,54,1,0,PC 17603,59.4,,C
515,0,3,"Coleff, Mr. Satio",male,24,0,0,349209,7.4958,,S
516,0,1,"Walker, Mr. William Anderson",male,47,0,0,36967,34.0208,D46,S
517,1,2,"Lemore, Mrs. (Amelia Milley)",female,34,0,0,C.A. 34260,10.5,F33,S
518,0,3,"Ryan, Mr. Patrick",male,,0,0,371110,24.15,,Q
519,1,2,"Angle, Mrs. William A (Florence ""Mary"" Agnes Hughes)",female,36,1,0,226875,26,,S
520,0,3,"Pavlovic, Mr. Stefo",male,32,0,0,349242,7.8958,,S
521,1,1,"Perreault, Miss. Anne",female,30,0,0,12749,93.5,B73,S
522,0,3,"Vovk, Mr. Janko",male,22,0,0,349252,7.8958,,S
523,0,3,"Lahoud, Mr. Sarkis",male,,0,0,2624,7.225,,C
524,1,1,"Hippach, Mrs. Louis Albert (Ida Sophia Fischer)",female,44,0,1,111361,57.9792,B18,C
525,0,3,"Kassem, Mr. Fared",male,,0,0,2700,7.2292,,C
526,0,3,"Farrell, Mr. James",male,40.5,0,0,367232,7.75,,Q
527,1,2,"Ridsdale, Miss. Lucy",female,50,0,0,W./C. 14258,10.5,,S
528,0,1,"Farthing, Mr. John",male,,0,0,PC 17483,221.7792,C95,S
529,0,3,"Salonen, Mr. Johan Werner",male,39,0,0,3101296,7.925,,S
530,0,2,"Hocking, Mr. Richard George",male,23,2,1,29104,11.5,,S
531,1,2,"Quick, Miss. Phyllis May",female,2,1,1,26360,26,,S
532,0,3,"Toufik, Mr. Nakli",male,,0,0,2641,7.2292,,C
533,0,3,"Elias, Mr. Joseph Jr",male,17,1,1,2690,7.2292,,C
534,1,3,"Peter, Mrs. Catherine (Catherine Rizk)",female,,0,2,2668,22.3583,,C
535,0,3,"Cacic, Miss. Marija",female,30,0,0,315084,8.6625,,S
536,1,2,"Hart, Miss. Eva Miriam",female,7,0,2,F.C.C. 13529,26.25,,S
537,0,1,"Butt, Major. Archibald Willingham",male,45,0,0,113050,26.55,B38,S
538,1,1,"LeRoy, Miss. Bertha",female,30,0,0,PC 17761,106.425,,C
539,0,3,"Risien, Mr. Samuel Beard",male,,0,0,364498,14.5,,S
540,1,1,"Frolicher, Miss. Hedwig Margaritha",female,22,0,2,13568,49.5,B39,C
541,1,1,"Crosby, Miss. Harriet R",female,36,0,2,WE/P 5735,71,B22,S
542,0,3,"Andersson, Miss. Ingeborg Constanzia",female,9,4,2,347082,31.275,,S
543,0,3,"Andersson, Miss. Sigrid Elisabeth",female,11,4,2,347082,31.275,,S
544,1,2,"Beane, Mr. Edward",male,32,1,0,2908,26,,S
545,0,1,"Douglas, Mr. Walter Donald",male,50,1,0,PC 17761,106.425,C86,C
546,0,1,"Nicholson, Mr. Arthur Ernest",male,64,0,0,693,26,,S
547,1,2,"Beane, Mrs. Edward (Ethel Clarke)",female,19,1,0,2908,26,,S
548,1,2,"Padro y Manent, Mr. Julian",male,,0,0,SC/PARIS 2146,13.8625,,C
549,0,3,"Goldsmith, Mr. Frank John",male,33,1,1,363291,20.525,,S
550,1,2,"Davies, Master. John Morgan Jr",male,8,1,1,C.A. 33112,36.75,,S
551,1,1,"Thayer, Mr. John Borland Jr",male,17,0,2,17421,110.8833,C70,C
552,0,2,"Sharp, Mr. Percival James R",male,27,0,0,244358,26,,S
553,0,3,"O'Brien, Mr. Timothy",male,,0,0,330979,7.8292,,Q
554,1,3,"Leeni, Mr. Fahim (""Philip Zenni"")",male,22,0,0,2620,7.225,,C
555,1,3,"Ohman, Miss. Velin",female,22,0,0,347085,7.775,,S
556,0,1,"Wright, Mr. George",male,62,0,0,113807,26.55,,S
557,1,1,"Duff Gordon, Lady. (Lucille Christiana Sutherland) (""Mrs Morgan"")",female,48,1,0,11755,39.6,A16,C
558,0,1,"Robbins, Mr. Victor",male,,0,0,PC 17757,227.525,,C
559,1,1,"Taussig, Mrs. Emil (Tillie Mandelbaum)",female,39,1,1,110413,79.65,E67,S
560,1,3,"de Messemaeker, Mrs. Guillaume Joseph (Emma)",female,36,1,0,345572,17.4,,S
561,0,3,"Morrow, Mr. Thomas Rowan",male,,0,0,372622,7.75,,Q
562,0,3,"Sivic, Mr. Husein",male,40,0,0,349251,7.8958,,S
563,0,2,"Norman, Mr. Robert Douglas",male,28,0,0,218629,13.5,,S
564,0,3,"Simmons, Mr. John",male,,0,0,SOTON/OQ 392082,8.05,,S
565,0,3,"Meanwell, Miss. (Marion Ogden)",female,,0,0,SOTON/O.Q. 392087,8.05,,S
566,0,3,"Davies, Mr. Alfred J",male,24,2,0,A/4 48871,24.15,,S
567,0,3,"Stoytcheff, Mr. Ilia",male,19,0,0,349205,7.8958,,S
568,0,3,"Palsson, Mrs. Nils (Alma Cornelia Berglund)",female,29,0,4,349909,21.075,,S
569,0,3,"Doharr, Mr. Tannous",male,,0,0,2686,7.2292,,C
570,1,3,"Jonsson, Mr. Carl",male,32,0,0,350417,7.8542,,S
571,1,2,"Harris, Mr. George",male,62,0,0,S.W./PP 752,10.5,,S
572,1,1,"Appleton, Mrs. Edward Dale (Charlotte Lamson)",female,53,2,0,11769,51.4792,C101,S
573,1,1,"Flynn, Mr. John Irwin (""Irving"")",male,36,0,0,PC 17474,26.3875,E25,S
574,1,3,"Kelly, Miss. Mary",female,,0,0,14312,7.75,,Q
575,0,3,"Rush, Mr. Alfred George John",male,16,0,0,A/4. 20589,8.05,,S
576,0,3,"Patchett, Mr. George",male,19,0,0,358585,14.5,,S
577,1,2,"Garside, Miss. Ethel",female,34,0,0,243880,13,,S
578,1,1,"Silvey, Mrs. William Baird (Alice Munger)",female,39,1,0,13507,55.9,E44,S
579,0,3,"Caram, Mrs. Joseph (Maria Elias)",female,,1,0,2689,14.4583,,C
580,1,3,"Jussila, Mr. Eiriik",male,32,0,0,STON/O 2. 3101286,7.925,,S
581,1,2,"Christy, Miss. Julie Rachel",female,25,1,1,237789,30,,S
582,1,1,"Thayer, Mrs. John Borland (Marian Longstreth Morris)",female,39,1,1,17421,110.8833,C68,C
583,0,2,"Downton, Mr. William James",male,54,0,0,28403,26,,S
584,0,1,"Ross, Mr. John Hugo",male,36,0,0,13049,40.125,A10,C
585,0,3,"Paulner, Mr. Uscher",male,,0,0,3411,8.7125,,C
586,1,1,"Taussig, Miss. Ruth",female,18,0,2,110413,79.65,E68,S
587,0,2,"Jarvis, Mr. John Denzil",male,47,0,0,237565,15,,S
588,1,1,"Frolicher-Stehli, Mr. Maxmillian",male,60,1,1,13567,79.2,B41,C
589,0,3,"Gilinski, Mr. Eliezer",male,22,0,0,14973,8.05,,S
590,0,3,"Murdlin, Mr. Joseph",male,,0,0,A./5. 3235,8.05,,S
591,0,3,"Rintamaki, Mr. Matti",male,35,0,0,STON/O 2. 3101273,7.125,,S
592,1,1,"Stephenson, Mrs. Walter Bertram (Martha Eustis)",female,52,1,0,36947,78.2667,D20,C
593,0,3,"Elsbury, Mr. William James",male,47,0,0,A/5 3902,7.25,,S
594,0,3,"Bourke, Miss. Mary",female,,0,2,364848,7.75,,Q
595,0,2,"Chapman, Mr. John Henry",male,37,1,0,SC/AH 29037,26,,S
596,0,3,"Van Impe, Mr. Jean Baptiste",male,36,1,1,345773,24.15,,S
597,1,2,"Leitch, Miss. Jessie Wills",female,,0,0,248727,33,,S
598,0,3,"Johnson, Mr. Alfred",male,49,0,0,LINE,0,,S
599,0,3,"Boulos, Mr. Hanna",male,,0,0,2664,7.225,,C
600,1,1,"Duff Gordon, Sir. Cosmo Edmund (""Mr Morgan"")",male,49,1,0,PC 17485,56.9292,A20,C
601,1,2,"Jacobsohn, Mrs. Sidney Samuel (Amy Frances Christy)",female,24,2,1,243847,27,,S
602,0,3,"Slabenoff, Mr. Petco",male,,0,0,349214,7.8958,,S
603,0,1,"Harrington, Mr. Charles H",male,,0,0,113796,42.4,,S
604,0,3,"Torber, Mr. Ernst William",male,44,0,0,364511,8.05,,S
605,1,1,"Homer, Mr. Harry (""Mr E Haven"")",male,35,0,0,111426,26.55,,C
606,0,3,"Lindell, Mr. Edvard Bengtsson",male,36,1,0,349910,15.55,,S
607,0,3,"Karaic, Mr. Milan",male,30,0,0,349246,7.8958,,S
608,1,1,"Daniel, Mr. Robert Williams",male,27,0,0,113804,30.5,,S
609,1,2,"Laroche, Mrs. Joseph (Juliette Marie Louise Lafargue)",female,22,1,2,SC/Paris 2123,41.5792,,C
610,1,1,"Shutes, Miss. Elizabeth W",female,40,0,0,PC 17582,153.4625,C125,S
611,0,3,"Andersson, Mrs. Anders Johan (Alfrida Konstantia Brogren)",female,39,1,5,347082,31.275,,S
612,0,3,"Jardin, Mr. Jose Neto",male,,0,0,SOTON/O.Q. 3101305,7.05,,S
613,1,3,"Murphy, Miss. Margaret Jane",female,,1,0,367230,15.5,,Q
614,0,3,"Horgan, Mr. John",male,,0,0,370377,7.75,,Q
615,0,3,"Brocklebank, Mr. William Alfred",male,35,0,0,364512,8.05,,S
616,1,2,"Herman, Miss. Alice",female,24,1,2,220845,65,,S
617,0,3,"Danbom, Mr. Ernst Gilbert",male,34,1,1,347080,14.4,,S
618,0,3,"Lobb, Mrs. William Arthur (Cordelia K Stanlick)",female,26,1,0,A/5. 3336,16.1,,S
619,1,2,"Becker, Miss. Marion Louise",female,4,2,1,230136,39,F4,S
620,0,2,"Gavey, Mr. Lawrence",male,26,0,0,31028,10.5,,S
621,0,3,"Yasbeck, Mr. Antoni",male,27,1,0,2659,14.4542,,C
622,1,1,"Kimball, Mr. Edwin Nelson Jr",male,42,1,0,11753,52.5542,D19,S
623,1,3,"Nakid, Mr. Sahid",male,20,1,1,2653,15.7417,,C
624,0,3,"Hansen, Mr. Henry Damsgaard",male,21,0,0,350029,7.8542,,S
625,0,3,"Bowen, Mr. David John ""Dai""",male,21,0,0,54636,16.1,,S
626,0,1,"Sutton, Mr. Frederick",male,61,0,0,36963,32.3208,D50,S
627,0,2,"Kirkland, Rev. Charles Leonard",male,57,0,0,219533,12.35,,Q
628,1,1,"Longley, Miss. Gretchen Fiske",female,21,0,0,13502,77.9583,D9,S
629,0,3,"Bostandyeff, Mr. Guentcho",male,26,0,0,349224,7.8958,,S
630,0,3,"O'Connell, Mr. Patrick D",male,,0,0,334912,7.7333,,Q
631,1,1,"Barkworth, Mr. Algernon Henry Wilson",male,80,0,0,27042,30,A23,S
632,0,3,"Lundahl, Mr. Johan Svensson",male,51,0,0,347743,7.0542,,S
633,1,1,"Stahelin-Maeglin, Dr. Max",male,32,0,0,13214,30.5,B50,C
634,0,1,"Parr, Mr. William Henry Marsh",male,,0,0,112052,0,,S
635,0,3,"Skoog, Miss. Mabel",female,9,3,2,347088,27.9,,S
636,1,2,"Davis, Miss. Mary",female,28,0,0,237668,13,,S
637,0,3,"Leinonen, Mr. Antti Gustaf",male,32,0,0,STON/O 2. 3101292,7.925,,S
638,0,2,"Collyer, Mr. Harvey",male,31,1,1,C.A. 31921,26.25,,S
639,0,3,"Panula, Mrs. Juha (Maria Emilia Ojala)",female,41,0,5,3101295,39.6875,,S
640,0,3,"Thorneycroft, Mr. Percival",male,,1,0,376564,16.1,,S
641,0,3,"Jensen, Mr. Hans Peder",male,20,0,0,350050,7.8542,,S
642,1,1,"Sagesser, Mlle. Emma",female,24,0,0,PC 17477,69.3,B35,C
643,0,3,"Skoog, Miss. Margit Elizabeth",female,2,3,2,347088,27.9,,S
644,1,3,"Foo, Mr. Choong",male,,0,0,1601,56.4958,,S
645,1,3,"Baclini, Miss. Eugenie",female,0.75,2,1,2666,19.2583,,C
646,1,1,"Harper, Mr. Henry Sleeper",male,48,1,0,PC 17572,76.7292,D33,C
647,0,3,"Cor, Mr. Liudevit",male,19,0,0,349231,7.8958,,S
648,1,1,"Simonius-Blumer, Col. Oberst Alfons",male,56,0,0,13213,35.5,A26,C
649,0,3,"Willey, Mr. Edward",male,,0,0,S.O./P.P. 751,7.55,,S
650,1,3,"Stanley, Miss. Amy Zillah Elsie",female,23,0,0,CA. 2314,7.55,,S
651,0,3,"Mitkoff, Mr. Mito",male,,0,0,349221,7.8958,,S
652,1,2,"Doling, Miss. Elsie",female,18,0,1,231919,23,,S
653,0,3,"Kalvik, Mr. Johannes Halvorsen",male,21,0,0,8475,8.4333,,S
654,1,3,"O'Leary, Miss. Hanora ""Norah""",female,,0,0,330919,7.8292,,Q
655,0,3,"Hegarty, Miss. Hanora ""Nora""",female,18,0,0,365226,6.75,,Q
656,0,2,"Hickman, Mr. Leonard Mark",male,24,2,0,S.O.C. 14879,73.5,,S
657,0,3,"Radeff, Mr. Alexander",male,,0,0,349223,7.8958,,S
658,0,3,"Bourke, Mrs. John (Catherine)",female,32,1,1,364849,15.5,,Q
659,0,2,"Eitemiller, Mr. George Floyd",male,23,0,0,29751,13,,S
660,0,1,"Newell, Mr. Arthur Webster",male,58,0,2,35273,113.275,D48,C
661,1,1,"Frauenthal, Dr. Henry William",male,50,2,0,PC 17611,133.65,,S
662,0,3,"Badt, Mr. Mohamed",male,40,0,0,2623,7.225,,C
663,0,1,"Colley, Mr. Edward Pomeroy",male,47,0,0,5727,25.5875,E58,S
664,0,3,"Coleff, Mr. Peju",male,36,0,0,349210,7.4958,,S
665,1,3,"Lindqvist, Mr. Eino William",male,20,1,0,STON/O 2. 3101285,7.925,,S
666,0,2,"Hickman, Mr. Lewis",male,32,2,0,S.O.C. 14879,73.5,,S
667,0,2,"Butler, Mr. Reginald Fenton",male,25,0,0,234686,13,,S
668,0,3,"Rommetvedt, Mr. Knud Paust",male,,0,0,312993,7.775,,S
669,0,3,"Cook, Mr. Jacob",male,43,0,0,A/5 3536,8.05,,S
670,1,1,"Taylor, Mrs. Elmer Zebley (Juliet Cummins Wright)",female,,1,0,19996,52,C126,S
671,1,2,"Brown, Mrs. Thomas William Solomon (Elizabeth Catherine Ford)",female,40,1,1,29750,39,,S
672,0,1,"Davidson, Mr. Thornton",male,31,1,0,F.C. 12750,52,B71,S
673,0,2,"Mitchell, Mr. Henry Michael",male,70,0,0,C.A. 24580,10.5,,S
674,1,2,"Wilhelms, Mr. Charles",male,31,0,0,244270,13,,S
675,0,2,"Watson, Mr. Ennis Hastings",male,,0,0,239856,0,,S
676,0,3,"Edvardsson, Mr. Gustaf Hjalmar",male,18,0,0,349912,7.775,,S
677,0,3,"Sawyer, Mr. Frederick Charles",male,24.5,0,0,342826,8.05,,S
678,1,3,"Turja, Miss. Anna Sofia",female,18,0,0,4138,9.8417,,S
679,0,3,"Goodwin, Mrs. Frederick (Augusta Tyler)",female,43,1,6,CA 2144,46.9,,S
680,1,1,"Cardeza, Mr. Thomas Drake Martinez",male,36,0,1,PC 17755,512.3292,B51 B53 B55,C
681,0,3,"Peters, Miss. Katie",female,,0,0,330935,8.1375,,Q
682,1,1,"Hassab, Mr. Hammad",male,27,0,0,PC 17572,76.7292,D49,C
683,0,3,"Olsvigen, Mr. Thor Anderson",male,20,0,0,6563,9.225,,S
684,0,3,"Goodwin, Mr. Charles Edward",male,14,5,2,CA 2144,46.9,,S
685,0,2,"Brown, Mr. Thomas William Solomon",male,60,1,1,29750,39,,S
686,0,2,"Laroche, Mr. Joseph Philippe Lemercier",male,25,1,2,SC/Paris 2123,41.5792,,C
687,0,3,"Panula, Mr. Jaako Arnold",male,14,4,1,3101295,39.6875,,S
688,0,3,"Dakic, Mr. Branko",male,19,0,0,349228,10.1708,,S
689,0,3,"Fischer, Mr. Eberhard Thelander",male,18,0,0,350036,7.7958,,S
690,1,1,"Madill, Miss. Georgette Alexandra",female,15,0,1,24160,211.3375,B5,S
691,1,1,"Dick, Mr. Albert Adrian",male,31,1,0,17474,57,B20,S
692,1,3,"Karun, Miss. Manca",female,4,0,1,349256,13.4167,,C
693,1,3,"Lam, Mr. Ali",male,,0,0,1601,56.4958,,S
694,0,3,"Saad, Mr. Khalil",male,25,0,0,2672,7.225,,C
695,0,1,"Weir, Col. John",male,60,0,0,113800,26.55,,S
696,0,2,"Chapman, Mr. Charles Henry",male,52,0,0,248731,13.5,,S
697,0,3,"Kelly, Mr. James",male,44,0,0,363592,8.05,,S
698,1,3,"Mullens, Miss. Katherine ""Katie""",female,,0,0,35852,7.7333,,Q
699,0,1,"Thayer, Mr. John Borland",male,49,1,1,17421,110.8833,C68,C
700,0,3,"Humblen, Mr. Adolf Mathias Nicolai Olsen",male,42,0,0,348121,7.65,F G63,S
701,1,1,"Astor, Mrs. John Jacob (Madeleine Talmadge Force)",female,18,1,0,PC 17757,227.525,C62 C64,C
702,1,1,"Silverthorne, Mr. Spencer Victor",male,35,0,0,PC 17475,26.2875,E24,S
703,0,3,"Barbara, Miss. Saiide",female,18,0,1,2691,14.4542,,C
704,0,3,"Gallagher, Mr. Martin",male,25,0,0,36864,7.7417,,Q
705,0,3,"Hansen, Mr. Henrik Juul",male,26,1,0,350025,7.8542,,S
706,0,2,"Morley, Mr. Henry Samuel (""Mr Henry Marshall"")",male,39,0,0,250655,26,,S
707,1,2,"Kelly, Mrs. Florence ""Fannie""",female,45,0,0,223596,13.5,,S
708,1,1,"Calderhead, Mr. Edward Pennington",male,42,0,0,PC 17476,26.2875,E24,S
709,1,1,"Cleaver, Miss. Alice",female,22,0,0,113781,151.55,,S
710,1,3,"Moubarek, Master. Halim Gonios (""William George"")",male,,1,1,2661,15.2458,,C
711,1,1,"Mayne, Mlle. Berthe Antonine (""Mrs de Villiers"")",female,24,0,0,PC 17482,49.5042,C90,C
712,0,1,"Klaber, Mr. Herman",male,,0,0,113028,26.55,C124,S
713,1,1,"Taylor, Mr. Elmer Zebley",male,48,1,0,19996,52,C126,S
714,0,3,"Larsson, Mr. August Viktor",male,29,0,0,7545,9.4833,,S
715,0,2,"Greenberg, Mr. Samuel",male,52,0,0,250647,13,,S
716,0,3,"Soholt, Mr. Peter Andreas Lauritz Andersen",male,19,0,0,348124,7.65,F G73,S
717,1,1,"Endres, Miss. Caroline Louise",female,38,0,0,PC 17757,227.525,C45,C
718,1,2,"Troutt, Miss. Edwina Celia ""Winnie""",female,27,0,0,34218,10.5,E101,S
719,0,3,"McEvoy, Mr. Michael",male,,0,0,36568,15.5,,Q
720,0,3,"Johnson, Mr. Malkolm Joackim",male,33,0,0,347062,7.775,,S
721,1,2,"Harper, Miss. Annie Jessie ""Nina""",female,6,0,1,248727,33,,S
722,0,3,"Jensen, Mr. Svend Lauritz",male,17,1,0,350048,7.0542,,S
723,0,2,"Gillespie, Mr. William Henry",male,34,0,0,12233,13,,S
724,0,2,"Hodges, Mr. Henry Price",male,50,0,0,250643,13,,S
725,1,1,"Chambers, Mr. Norman Campbell",male,27,1,0,113806,53.1,E8,S
726,0,3,"Oreskovic, Mr. Luka",male,20,0,0,315094,8.6625,,S
727,1,2,"Renouf, Mrs. Peter Henry (Lillian Jefferys)",female,30,3,0,31027,21,,S
728,1,3,"Mannion, Miss. Margareth",female,,0,0,36866,7.7375,,Q
729,0,2,"Bryhl, Mr. Kurt Arnold Gottfrid",male,25,1,0,236853,26,,S
730,0,3,"Ilmakangas, Miss. Pieta Sofia",female,25,1,0,STON/O2. 3101271,7.925,,S
731,1,1,"Allen, Miss. Elisabeth Walton",female,29,0,0,24160,211.3375,B5,S
732,0,3,"Hassan, Mr. Houssein G N",male,11,0,0,2699,18.7875,,C
733,0,2,"Knight, Mr. Robert J",male,,0,0,239855,0,,S
734,0,2,"Berriman, Mr. William John",male,23,0,0,28425,13,,S
735,0,2,"Troupiansky, Mr. Moses Aaron",male,23,0,0,233639,13,,S
736,0,3,"Williams, Mr. Leslie",male,28.5,0,0,54636,16.1,,S
737,0,3,"Ford, Mrs. Edward (Margaret Ann Watson)",female,48,1,3,W./C. 6608,34.375,,S
738,1,1,"Lesurer, Mr. Gustave J",male,35,0,0,PC 17755,512.3292,B101,C
739,0,3,"Ivanoff, Mr. Kanio",male,,0,0,349201,7.8958,,S
740,0,3,"Nankoff, Mr. Minko",male,,0,0,349218,7.8958,,S
741,1,1,"Hawksford, Mr. Walter James",male,,0,0,16988,30,D45,S
742,0,1,"Cavendish, Mr. Tyrell William",male,36,1,0,19877,78.85,C46,S
743,1,1,"Ryerson, Miss. Susan Parker ""Suzette""",female,21,2,2,PC 17608,262.375,B57 B59 B63 B66,C
744,0,3,"McNamee, Mr. Neal",male,24,1,0,376566,16.1,,S
745,1,3,"Stranden, Mr. Juho",male,31,0,0,STON/O 2. 3101288,7.925,,S
746,0,1,"Crosby, Capt. Edward Gifford",male,70,1,1,WE/P 5735,71,B22,S
747,0,3,"Abbott, Mr. Rossmore Edward",male,16,1,1,C.A. 2673,20.25,,S
748,1,2,"Sinkkonen, Miss. Anna",female,30,0,0,250648,13,,S
749,0,1,"Marvin, Mr. Daniel Warner",male,19,1,0,113773,53.1,D30,S
750,0,3,"Connaghton, Mr. Michael",male,31,0,0,335097,7.75,,Q
751,1,2,"Wells, Miss. Joan",female,4,1,1,29103,23,,S
752,1,3,"Moor, Master. Meier",male,6,0,1,392096,12.475,E121,S
753,0,3,"Vande Velde, Mr. Johannes Joseph",male,33,0,0,345780,9.5,,S
754,0,3,"Jonkoff, Mr. Lalio",male,23,0,0,349204,7.8958,,S
755,1,2,"Herman, Mrs. Samuel (Jane Laver)",female,48,1,2,220845,65,,S
756,1,2,"Hamalainen, Master. Viljo",male,0.67,1,1,250649,14.5,,S
757,0,3,"Carlsson, Mr. August Sigfrid",male,28,0,0,350042,7.7958,,S
758,0,2,"Bailey, Mr. Percy Andrew",male,18,0,0,29108,11.5,,S
759,0,3,"Theobald, Mr. Thomas Leonard",male,34,0,0,363294,8.05,,S
760,1,1,"Rothes, the Countess. of (Lucy Noel Martha Dyer-Edwards)",female,33,0,0,110152,86.5,B77,S
761,0,3,"Garfirth, Mr. John",male,,0,0,358585,14.5,,S
762,0,3,"Nirva, Mr. Iisakki Antino Aijo",male,41,0,0,SOTON/O2 3101272,7.125,,S
763,1,3,"Barah, Mr. Hanna Assi",male,20,0,0,2663,7.2292,,C
764,1,1,"Carter, Mrs. William Ernest (Lucile Polk)",female,36,1,2,113760,120,B96 B98,S
765,0,3,"Eklund, Mr. Hans Linus",male,16,0,0,347074,7.775,,S
766,1,1,"Hogeboom, Mrs. John C (Anna Andrews)",female,51,1,0,13502,77.9583,D11,S
767,0,1,"Brewe, Dr. Arthur Jackson",male,,0,0,112379,39.6,,C
768,0,3,"Mangan, Miss. Mary",female,30.5,0,0,364850,7.75,,Q
769,0,3,"Moran, Mr. Daniel J",male,,1,0,371110,24.15,,Q
770,0,3,"Gronnestad, Mr. Daniel Danielsen",male,32,0,0,8471,8.3625,,S
771,0,3,"Lievens, Mr. Rene Aime",male,24,0,0,345781,9.5,,S
772,0,3,"Jensen, Mr. Niels Peder",male,48,0,0,350047,7.8542,,S
773,0,2,"Mack, Mrs. (Mary)",female,57,0,0,S.O./P.P. 3,10.5,E77,S
774,0,3,"Elias, Mr. Dibo",male,,0,0,2674,7.225,,C
775,1,2,"Hocking, Mrs. Elizabeth (Eliza Needs)",female,54,1,3,29105,23,,S
776,0,3,"Myhrman, Mr. Pehr Fabian Oliver Malkolm",male,18,0,0,347078,7.75,,S
777,0,3,"Tobin, Mr. Roger",male,,0,0,383121,7.75,F38,Q
778,1,3,"Emanuel, Miss. Virginia Ethel",female,5,0,0,364516,12.475,,S
779,0,3,"Kilgannon, Mr. Thomas J",male,,0,0,36865,7.7375,,Q
780,1,1,"Robert, Mrs. Edward Scott (Elisabeth Walton McMillan)",female,43,0,1,24160,211.3375,B3,S
781,1,3,"Ayoub, Miss. Banoura",female,13,0,0,2687,7.2292,,C
782,1,1,"Dick, Mrs. Albert Adrian (Vera Gillespie)",female,17,1,0,17474,57,B20,S
783,0,1,"Long, Mr. Milton Clyde",male,29,0,0,113501,30,D6,S
784,0,3,"Johnston, Mr. Andrew G",male,,1,2,W./C. 6607,23.45,,S
785,0,3,"Ali, Mr. William",male,25,0,0,SOTON/O.Q. 3101312,7.05,,S
786,0,3,"Harmer, Mr. Abraham (David Lishin)",male,25,0,0,374887,7.25,,S
787,1,3,"Sjoblom, Miss. Anna Sofia",female,18,0,0,3101265,7.4958,,S
788,0,3,"Rice, Master. George Hugh",male,8,4,1,382652,29.125,,Q
789,1,3,"Dean, Master. Bertram Vere",male,1,1,2,C.A. 2315,20.575,,S
790,0,1,"Guggenheim, Mr. Benjamin",male,46,0,0,PC 17593,79.2,B82 B84,C
791,0,3,"Keane, Mr. Andrew ""Andy""",male,,0,0,12460,7.75,,Q
792,0,2,"Gaskell, Mr. Alfred",male,16,0,0,239865,26,,S
793,0,3,"Sage, Miss. Stella Anna",female,,8,2,CA. 2343,69.55,,S
794,0,1,"Hoyt, Mr. William Fisher",male,,0,0,PC 17600,30.6958,,C
795,0,3,"Dantcheff, Mr. Ristiu",male,25,0,0,349203,7.8958,,S
796,0,2,"Otter, Mr. Richard",male,39,0,0,28213,13,,S
797,1,1,"Leader, Dr. Alice (Farnham)",female,49,0,0,17465,25.9292,D17,S
798,1,3,"Osman, Mrs. Mara",female,31,0,0,349244,8.6833,,S
799,0,3,"Ibrahim Shawah, Mr. Yousseff",male,30,0,0,2685,7.2292,,C
800,0,3,"Van Impe, Mrs. Jean Baptiste (Rosalie Paula Govaert)",female,30,1,1,345773,24.15,,S
801,0,2,"Ponesell, Mr. Martin",male,34,0,0,250647,13,,S
802,1,2,"Collyer, Mrs. Harvey (Charlotte Annie Tate)",female,31,1,1,C.A. 31921,26.25,,S
803,1,1,"Carter, Master. William Thornton II",male,11,1,2,113760,120,B96 B98,S
804,1,3,"Thomas, Master. Assad Alexander",male,0.42,0,1,2625,8.5167,,C
805,1,3,"Hedman, Mr. Oskar Arvid",male,27,0,0,347089,6.975,,S
806,0,3,"Johansson, Mr. Karl Johan",male,31,0,0,347063,7.775,,S
807,0,1,"Andrews, Mr. Thomas Jr",male,39,0,0,112050,0,A36,S
808,0,3,"Pettersson, Miss. Ellen Natalia",female,18,0,0,347087,7.775,,S
809,0,2,"Meyer, Mr. August",male,39,0,0,248723,13,,S
810,1,1,"Chambers, Mrs. Norman Campbell (Bertha Griggs)",female,33,1,0,113806,53.1,E8,S
811,0,3,"Alexander, Mr. William",male,26,0,0,3474,7.8875,,S
812,0,3,"Lester, Mr. James",male,39,0,0,A/4 48871,24.15,,S
813,0,2,"Slemen, Mr. Richard James",male,35,0,0,28206,10.5,,S
814,0,3,"Andersson, Miss. Ebba Iris Alfrida",female,6,4,2,347082,31.275,,S
815,0,3,"Tomlin, Mr. Ernest Portage",male,30.5,0,0,364499,8.05,,S
816,0,1,"Fry, Mr. Richard",male,,0,0,112058,0,B102,S
817,0,3,"Heininen, Miss. Wendla Maria",female,23,0,0,STON/O2. 3101290,7.925,,S
818,0,2,"Mallet, Mr. Albert",male,31,1,1,S.C./PARIS 2079,37.0042,,C
819,0,3,"Holm, Mr. John Fredrik Alexander",male,43,0,0,C 7075,6.45,,S
820,0,3,"Skoog, Master. Karl Thorsten",male,10,3,2,347088,27.9,,S
821,1,1,"Hays, Mrs. Charles Melville (Clara Jennings Gregg)",female,52,1,1,12749,93.5,B69,S
822,1,3,"Lulic, Mr. Nikola",male,27,0,0,315098,8.6625,,S
823,0,1,"Reuchlin, Jonkheer. John George",male,38,0,0,19972,0,,S
824,1,3,"Moor, Mrs. (Beila)",female,27,0,1,392096,12.475,E121,S
825,0,3,"Panula, Master. Urho Abraham",male,2,4,1,3101295,39.6875,,S
826,0,3,"Flynn, Mr. John",male,,0,0,368323,6.95,,Q
827,0,3,"Lam, Mr. Len",male,,0,0,1601,56.4958,,S
828,1,2,"Mallet, Master. Andre",male,1,0,2,S.C./PARIS 2079,37.0042,,C
829,1,3,"McCormack, Mr. Thomas Joseph",male,,0,0,367228,7.75,,Q
830,1,1,"Stone, Mrs. George Nelson (Martha Evelyn)",female,62,0,0,113572,80,B28,
831,1,3,"Yasbeck, Mrs. Antoni (Selini Alexander)",female,15,1,0,2659,14.4542,,C
832,1,2,"Richards, Master. George Sibley",male,0.83,1,1,29106,18.75,,S
833,0,3,"Saad, Mr. Amin",male,,0,0,2671,7.2292,,C
834,0,3,"Augustsson, Mr. Albert",male,23,0,0,347468,7.8542,,S
835,0,3,"Allum, Mr. Owen George",male,18,0,0,2223,8.3,,S
836,1,1,"Compton, Miss. Sara Rebecca",female,39,1,1,PC 17756,83.1583,E49,C
837,0,3,"Pasic, Mr. Jakob",male,21,0,0,315097,8.6625,,S
838,0,3,"Sirota, Mr. Maurice",male,,0,0,392092,8.05,,S
839,1,3,"Chip, Mr. Chang",male,32,0,0,1601,56.4958,,S
840,1,1,"Marechal, Mr. Pierre",male,,0,0,11774,29.7,C47,C
841,0,3,"Alhomaki, Mr. Ilmari Rudolf",male,20,0,0,SOTON/O2 3101287,7.925,,S
842,0,2,"Mudd, Mr. Thomas Charles",male,16,0,0,S.O./P.P. 3,10.5,,S
843,1,1,"Serepeca, Miss. Augusta",female,30,0,0,113798,31,,C
844,0,3,"Lemberopolous, Mr. Peter L",male,34.5,0,0,2683,6.4375,,C
845,0,3,"Culumovic, Mr. Jeso",male,17,0,0,315090,8.6625,,S
846,0,3,"Abbing, Mr. Anthony",male,42,0,0,C.A. 5547,7.55,,S
847,0,3,"Sage, Mr. Douglas Bullen",male,,8,2,CA. 2343,69.55,,S
848,0,3,"Markoff, Mr. Marin",male,35,0,0,349213,7.8958,,C
849,0,2,"Harper, Rev. John",male,28,0,1,248727,33,,S
850,1,1,"Goldenberg, Mrs. Samuel L (Edwiga Grabowska)",female,,1,0,17453,89.1042,C92,C
851,0,3,"Andersson, Master. Sigvard Harald Elias",male,4,4,2,347082,31.275,,S
852,0,3,"Svensson, Mr. Johan",male,74,0,0,347060,7.775,,S
853,0,3,"Boulos, Miss. Nourelain",female,9,1,1,2678,15.2458,,C
854,1,1,"Lines, Miss. Mary Conover",female,16,0,1,PC 17592,39.4,D28,S
855,0,2,"Carter, Mrs. Ernest Courtenay (Lilian Hughes)",female,44,1,0,244252,26,,S
856,1,3,"Aks, Mrs. Sam (Leah Rosen)",female,18,0,1,392091,9.35,,S
857,1,1,"Wick, Mrs. George Dennick (Mary Hitchcock)",female,45,1,1,36928,164.8667,,S
858,1,1,"Daly, Mr. Peter Denis ",male,51,0,0,113055,26.55,E17,S
859,1,3,"Baclini, Mrs. Solomon (Latifa Qurban)",female,24,0,3,2666,19.2583,,C
860,0,3,"Razi, Mr. Raihed",male,,0,0,2629,7.2292,,C
861,0,3,"Hansen, Mr. Claus Peter",male,41,2,0,350026,14.1083,,S
862,0,2,"Giles, Mr. Frederick Edward",male,21,1,0,28134,11.5,,S
863,1,1,"Swift, Mrs. Frederick Joel (Margaret Welles Barron)",female,48,0,0,17466,25.9292,D17,S
864,0,3,"Sage, Miss. Dorothy Edith ""Dolly""",female,,8,2,CA. 2343,69.55,,S
865,0,2,"Gill, Mr. John William",male,24,0,0,233866,13,,S
866,1,2,"Bystrom, Mrs. (Karolina)",female,42,0,0,236852,13,,S
867,1,2,"Duran y More, Miss. Asuncion",female,27,1,0,SC/PARIS 2149,13.8583,,C
868,0,1,"Roebling, Mr. Washington Augustus II",male,31,0,0,PC 17590,50.4958,A24,S
869,0,3,"van Melkebeke, Mr. Philemon",male,,0,0,345777,9.5,,S
870,1,3,"Johnson, Master. Harold Theodor",male,4,1,1,347742,11.1333,,S
871,0,3,"Balkic, Mr. Cerin",male,26,0,0,349248,7.8958,,S
872,1,1,"Beckwith, Mrs. Richard Leonard (Sallie Monypeny)",female,47,1,1,11751,52.5542,D35,S
873,0,1,"Carlsson, Mr. Frans Olof",male,33,0,0,695,5,B51 B53 B55,S
874,0,3,"Vander Cruyssen, Mr. Victor",male,47,0,0,345765,9,,S
875,1,2,"Abelson, Mrs. Samuel (Hannah Wizosky)",female,28,1,0,P/PP 3381,24,,C
876,1,3,"Najib, Miss. Adele Kiamie ""Jane""",female,15,0,0,2667,7.225,,C
877,0,3,"Gustafsson, Mr. Alfred Ossian",male,20,0,0,7534,9.8458,,S
878,0,3,"Petroff, Mr. Nedelio",male,19,0,0,349212,7.8958,,S
879,0,3,"Laleff, Mr. Kristo",male,,0,0,349217,7.8958,,S
880,1,1,"Potter, Mrs. Thomas Jr (Lily Alexenia Wilson)",female,56,0,1,11767,83.1583,C50,C
881,1,2,"Shelley, Mrs. William (Imanita Parrish Hall)",female,25,0,1,230433,26,,S
882,0,3,"Markun, Mr. Johann",male,33,0,0,349257,7.8958,,S
883,0,3,"Dahlberg, Miss. Gerda Ulrika",female,22,0,0,7552,10.5167,,S
884,0,2,"Banfield, Mr. Frederick James",male,28,0,0,C.A./SOTON 34068,10.5,,S
885,0,3,"Sutehall, Mr. Henry Jr",male,25,0,0,SOTON/OQ 392076,7.05,,S
886,0,3,"Rice, Mrs. William (Margaret Norton)",female,39,0,5,382652,29.125,,Q
887,0,2,"Montvila, Rev. Juozas",male,27,0,0,211536,13,,S
888,1,1,"Graham, Miss. Margaret Edith",female,19,0,0,112053,30,B42,S
889,0,3,"Johnston, Miss. Catherine Helen ""Carrie""",female,,1,2,W./C. 6607,23.45,,S
890,1,1,"Behr, Mr. Karl Howell",male,26,0,0,111369,30,C148,C
891,0,3,"Dooley, Mr. Patrick",male,32,0,0,370376,7.75,,Q
1 PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked
2 1 0 3 Braund, Mr. Owen Harris male 22 1 0 A/5 21171 7.25 S
3 2 1 1 Cumings, Mrs. John Bradley (Florence Briggs Thayer) female 38 1 0 PC 17599 71.2833 C85 C
4 3 1 3 Heikkinen, Miss. Laina female 26 0 0 STON/O2. 3101282 7.925 S
5 4 1 1 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35 1 0 113803 53.1 C123 S
6 5 0 3 Allen, Mr. William Henry male 35 0 0 373450 8.05 S
7 6 0 3 Moran, Mr. James male 0 0 330877 8.4583 Q
8 7 0 1 McCarthy, Mr. Timothy J male 54 0 0 17463 51.8625 E46 S
9 8 0 3 Palsson, Master. Gosta Leonard male 2 3 1 349909 21.075 S
10 9 1 3 Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg) female 27 0 2 347742 11.1333 S
11 10 1 2 Nasser, Mrs. Nicholas (Adele Achem) female 14 1 0 237736 30.0708 C
12 11 1 3 Sandstrom, Miss. Marguerite Rut female 4 1 1 PP 9549 16.7 G6 S
13 12 1 1 Bonnell, Miss. Elizabeth female 58 0 0 113783 26.55 C103 S
14 13 0 3 Saundercock, Mr. William Henry male 20 0 0 A/5. 2151 8.05 S
15 14 0 3 Andersson, Mr. Anders Johan male 39 1 5 347082 31.275 S
16 15 0 3 Vestrom, Miss. Hulda Amanda Adolfina female 14 0 0 350406 7.8542 S
17 16 1 2 Hewlett, Mrs. (Mary D Kingcome) female 55 0 0 248706 16 S
18 17 0 3 Rice, Master. Eugene male 2 4 1 382652 29.125 Q
19 18 1 2 Williams, Mr. Charles Eugene male 0 0 244373 13 S
20 19 0 3 Vander Planke, Mrs. Julius (Emelia Maria Vandemoortele) female 31 1 0 345763 18 S
21 20 1 3 Masselmani, Mrs. Fatima female 0 0 2649 7.225 C
22 21 0 2 Fynney, Mr. Joseph J male 35 0 0 239865 26 S
23 22 1 2 Beesley, Mr. Lawrence male 34 0 0 248698 13 D56 S
24 23 1 3 McGowan, Miss. Anna "Annie" female 15 0 0 330923 8.0292 Q
25 24 1 1 Sloper, Mr. William Thompson male 28 0 0 113788 35.5 A6 S
26 25 0 3 Palsson, Miss. Torborg Danira female 8 3 1 349909 21.075 S
27 26 1 3 Asplund, Mrs. Carl Oscar (Selma Augusta Emilia Johansson) female 38 1 5 347077 31.3875 S
28 27 0 3 Emir, Mr. Farred Chehab male 0 0 2631 7.225 C
29 28 0 1 Fortune, Mr. Charles Alexander male 19 3 2 19950 263 C23 C25 C27 S
30 29 1 3 O'Dwyer, Miss. Ellen "Nellie" female 0 0 330959 7.8792 Q
31 30 0 3 Todoroff, Mr. Lalio male 0 0 349216 7.8958 S
32 31 0 1 Uruchurtu, Don. Manuel E male 40 0 0 PC 17601 27.7208 C
33 32 1 1 Spencer, Mrs. William Augustus (Marie Eugenie) female 1 0 PC 17569 146.5208 B78 C
34 33 1 3 Glynn, Miss. Mary Agatha female 0 0 335677 7.75 Q
35 34 0 2 Wheadon, Mr. Edward H male 66 0 0 C.A. 24579 10.5 S
36 35 0 1 Meyer, Mr. Edgar Joseph male 28 1 0 PC 17604 82.1708 C
37 36 0 1 Holverson, Mr. Alexander Oskar male 42 1 0 113789 52 S
38 37 1 3 Mamee, Mr. Hanna male 0 0 2677 7.2292 C
39 38 0 3 Cann, Mr. Ernest Charles male 21 0 0 A./5. 2152 8.05 S
40 39 0 3 Vander Planke, Miss. Augusta Maria female 18 2 0 345764 18 S
41 40 1 3 Nicola-Yarred, Miss. Jamila female 14 1 0 2651 11.2417 C
42 41 0 3 Ahlin, Mrs. Johan (Johanna Persdotter Larsson) female 40 1 0 7546 9.475 S
43 42 0 2 Turpin, Mrs. William John Robert (Dorothy Ann Wonnacott) female 27 1 0 11668 21 S
44 43 0 3 Kraeff, Mr. Theodor male 0 0 349253 7.8958 C
45 44 1 2 Laroche, Miss. Simonne Marie Anne Andree female 3 1 2 SC/Paris 2123 41.5792 C
46 45 1 3 Devaney, Miss. Margaret Delia female 19 0 0 330958 7.8792 Q
47 46 0 3 Rogers, Mr. William John male 0 0 S.C./A.4. 23567 8.05 S
48 47 0 3 Lennon, Mr. Denis male 1 0 370371 15.5 Q
49 48 1 3 O'Driscoll, Miss. Bridget female 0 0 14311 7.75 Q
50 49 0 3 Samaan, Mr. Youssef male 2 0 2662 21.6792 C
51 50 0 3 Arnold-Franchi, Mrs. Josef (Josefine Franchi) female 18 1 0 349237 17.8 S
52 51 0 3 Panula, Master. Juha Niilo male 7 4 1 3101295 39.6875 S
53 52 0 3 Nosworthy, Mr. Richard Cater male 21 0 0 A/4. 39886 7.8 S
54 53 1 1 Harper, Mrs. Henry Sleeper (Myna Haxtun) female 49 1 0 PC 17572 76.7292 D33 C
55 54 1 2 Faunthorpe, Mrs. Lizzie (Elizabeth Anne Wilkinson) female 29 1 0 2926 26 S
56 55 0 1 Ostby, Mr. Engelhart Cornelius male 65 0 1 113509 61.9792 B30 C
57 56 1 1 Woolner, Mr. Hugh male 0 0 19947 35.5 C52 S
58 57 1 2 Rugg, Miss. Emily female 21 0 0 C.A. 31026 10.5 S
59 58 0 3 Novel, Mr. Mansouer male 28.5 0 0 2697 7.2292 C
60 59 1 2 West, Miss. Constance Mirium female 5 1 2 C.A. 34651 27.75 S
61 60 0 3 Goodwin, Master. William Frederick male 11 5 2 CA 2144 46.9 S
62 61 0 3 Sirayanian, Mr. Orsen male 22 0 0 2669 7.2292 C
63 62 1 1 Icard, Miss. Amelie female 38 0 0 113572 80 B28
64 63 0 1 Harris, Mr. Henry Birkhardt male 45 1 0 36973 83.475 C83 S
65 64 0 3 Skoog, Master. Harald male 4 3 2 347088 27.9 S
66 65 0 1 Stewart, Mr. Albert A male 0 0 PC 17605 27.7208 C
67 66 1 3 Moubarek, Master. Gerios male 1 1 2661 15.2458 C
68 67 1 2 Nye, Mrs. (Elizabeth Ramell) female 29 0 0 C.A. 29395 10.5 F33 S
69 68 0 3 Crease, Mr. Ernest James male 19 0 0 S.P. 3464 8.1583 S
70 69 1 3 Andersson, Miss. Erna Alexandra female 17 4 2 3101281 7.925 S
71 70 0 3 Kink, Mr. Vincenz male 26 2 0 315151 8.6625 S
72 71 0 2 Jenkin, Mr. Stephen Curnow male 32 0 0 C.A. 33111 10.5 S
73 72 0 3 Goodwin, Miss. Lillian Amy female 16 5 2 CA 2144 46.9 S
74 73 0 2 Hood, Mr. Ambrose Jr male 21 0 0 S.O.C. 14879 73.5 S
75 74 0 3 Chronopoulos, Mr. Apostolos male 26 1 0 2680 14.4542 C
76 75 1 3 Bing, Mr. Lee male 32 0 0 1601 56.4958 S
77 76 0 3 Moen, Mr. Sigurd Hansen male 25 0 0 348123 7.65 F G73 S
78 77 0 3 Staneff, Mr. Ivan male 0 0 349208 7.8958 S
79 78 0 3 Moutal, Mr. Rahamin Haim male 0 0 374746 8.05 S
80 79 1 2 Caldwell, Master. Alden Gates male 0.83 0 2 248738 29 S
81 80 1 3 Dowdell, Miss. Elizabeth female 30 0 0 364516 12.475 S
82 81 0 3 Waelens, Mr. Achille male 22 0 0 345767 9 S
83 82 1 3 Sheerlinck, Mr. Jan Baptist male 29 0 0 345779 9.5 S
84 83 1 3 McDermott, Miss. Brigdet Delia female 0 0 330932 7.7875 Q
85 84 0 1 Carrau, Mr. Francisco M male 28 0 0 113059 47.1 S
86 85 1 2 Ilett, Miss. Bertha female 17 0 0 SO/C 14885 10.5 S
87 86 1 3 Backstrom, Mrs. Karl Alfred (Maria Mathilda Gustafsson) female 33 3 0 3101278 15.85 S
88 87 0 3 Ford, Mr. William Neal male 16 1 3 W./C. 6608 34.375 S
89 88 0 3 Slocovski, Mr. Selman Francis male 0 0 SOTON/OQ 392086 8.05 S
90 89 1 1 Fortune, Miss. Mabel Helen female 23 3 2 19950 263 C23 C25 C27 S
91 90 0 3 Celotti, Mr. Francesco male 24 0 0 343275 8.05 S
92 91 0 3 Christmann, Mr. Emil male 29 0 0 343276 8.05 S
93 92 0 3 Andreasson, Mr. Paul Edvin male 20 0 0 347466 7.8542 S
94 93 0 1 Chaffee, Mr. Herbert Fuller male 46 1 0 W.E.P. 5734 61.175 E31 S
95 94 0 3 Dean, Mr. Bertram Frank male 26 1 2 C.A. 2315 20.575 S
96 95 0 3 Coxon, Mr. Daniel male 59 0 0 364500 7.25 S
97 96 0 3 Shorney, Mr. Charles Joseph male 0 0 374910 8.05 S
98 97 0 1 Goldschmidt, Mr. George B male 71 0 0 PC 17754 34.6542 A5 C
99 98 1 1 Greenfield, Mr. William Bertram male 23 0 1 PC 17759 63.3583 D10 D12 C
100 99 1 2 Doling, Mrs. John T (Ada Julia Bone) female 34 0 1 231919 23 S
101 100 0 2 Kantor, Mr. Sinai male 34 1 0 244367 26 S
102 101 0 3 Petranec, Miss. Matilda female 28 0 0 349245 7.8958 S
103 102 0 3 Petroff, Mr. Pastcho ("Pentcho") male 0 0 349215 7.8958 S
104 103 0 1 White, Mr. Richard Frasar male 21 0 1 35281 77.2875 D26 S
105 104 0 3 Johansson, Mr. Gustaf Joel male 33 0 0 7540 8.6542 S
106 105 0 3 Gustafsson, Mr. Anders Vilhelm male 37 2 0 3101276 7.925 S
107 106 0 3 Mionoff, Mr. Stoytcho male 28 0 0 349207 7.8958 S
108 107 1 3 Salkjelsvik, Miss. Anna Kristine female 21 0 0 343120 7.65 S
109 108 1 3 Moss, Mr. Albert Johan male 0 0 312991 7.775 S
110 109 0 3 Rekic, Mr. Tido male 38 0 0 349249 7.8958 S
111 110 1 3 Moran, Miss. Bertha female 1 0 371110 24.15 Q
112 111 0 1 Porter, Mr. Walter Chamberlain male 47 0 0 110465 52 C110 S
113 112 0 3 Zabour, Miss. Hileni female 14.5 1 0 2665 14.4542 C
114 113 0 3 Barton, Mr. David John male 22 0 0 324669 8.05 S
115 114 0 3 Jussila, Miss. Katriina female 20 1 0 4136 9.825 S
116 115 0 3 Attalah, Miss. Malake female 17 0 0 2627 14.4583 C
117 116 0 3 Pekoniemi, Mr. Edvard male 21 0 0 STON/O 2. 3101294 7.925 S
118 117 0 3 Connors, Mr. Patrick male 70.5 0 0 370369 7.75 Q
119 118 0 2 Turpin, Mr. William John Robert male 29 1 0 11668 21 S
120 119 0 1 Baxter, Mr. Quigg Edmond male 24 0 1 PC 17558 247.5208 B58 B60 C
121 120 0 3 Andersson, Miss. Ellis Anna Maria female 2 4 2 347082 31.275 S
122 121 0 2 Hickman, Mr. Stanley George male 21 2 0 S.O.C. 14879 73.5 S
123 122 0 3 Moore, Mr. Leonard Charles male 0 0 A4. 54510 8.05 S
124 123 0 2 Nasser, Mr. Nicholas male 32.5 1 0 237736 30.0708 C
125 124 1 2 Webber, Miss. Susan female 32.5 0 0 27267 13 E101 S
126 125 0 1 White, Mr. Percival Wayland male 54 0 1 35281 77.2875 D26 S
127 126 1 3 Nicola-Yarred, Master. Elias male 12 1 0 2651 11.2417 C
128 127 0 3 McMahon, Mr. Martin male 0 0 370372 7.75 Q
129 128 1 3 Madsen, Mr. Fridtjof Arne male 24 0 0 C 17369 7.1417 S
130 129 1 3 Peter, Miss. Anna female 1 1 2668 22.3583 F E69 C
131 130 0 3 Ekstrom, Mr. Johan male 45 0 0 347061 6.975 S
132 131 0 3 Drazenoic, Mr. Jozef male 33 0 0 349241 7.8958 C
133 132 0 3 Coelho, Mr. Domingos Fernandeo male 20 0 0 SOTON/O.Q. 3101307 7.05 S
134 133 0 3 Robins, Mrs. Alexander A (Grace Charity Laury) female 47 1 0 A/5. 3337 14.5 S
135 134 1 2 Weisz, Mrs. Leopold (Mathilde Francoise Pede) female 29 1 0 228414 26 S
136 135 0 2 Sobey, Mr. Samuel James Hayden male 25 0 0 C.A. 29178 13 S
137 136 0 2 Richard, Mr. Emile male 23 0 0 SC/PARIS 2133 15.0458 C
138 137 1 1 Newsom, Miss. Helen Monypeny female 19 0 2 11752 26.2833 D47 S
139 138 0 1 Futrelle, Mr. Jacques Heath male 37 1 0 113803 53.1 C123 S
140 139 0 3 Osen, Mr. Olaf Elon male 16 0 0 7534 9.2167 S
141 140 0 1 Giglio, Mr. Victor male 24 0 0 PC 17593 79.2 B86 C
142 141 0 3 Boulos, Mrs. Joseph (Sultana) female 0 2 2678 15.2458 C
143 142 1 3 Nysten, Miss. Anna Sofia female 22 0 0 347081 7.75 S
144 143 1 3 Hakkarainen, Mrs. Pekka Pietari (Elin Matilda Dolck) female 24 1 0 STON/O2. 3101279 15.85 S
145 144 0 3 Burke, Mr. Jeremiah male 19 0 0 365222 6.75 Q
146 145 0 2 Andrew, Mr. Edgardo Samuel male 18 0 0 231945 11.5 S
147 146 0 2 Nicholls, Mr. Joseph Charles male 19 1 1 C.A. 33112 36.75 S
148 147 1 3 Andersson, Mr. August Edvard ("Wennerstrom") male 27 0 0 350043 7.7958 S
149 148 0 3 Ford, Miss. Robina Maggie "Ruby" female 9 2 2 W./C. 6608 34.375 S
150 149 0 2 Navratil, Mr. Michel ("Louis M Hoffman") male 36.5 0 2 230080 26 F2 S
151 150 0 2 Byles, Rev. Thomas Roussel Davids male 42 0 0 244310 13 S
152 151 0 2 Bateman, Rev. Robert James male 51 0 0 S.O.P. 1166 12.525 S
153 152 1 1 Pears, Mrs. Thomas (Edith Wearne) female 22 1 0 113776 66.6 C2 S
154 153 0 3 Meo, Mr. Alfonzo male 55.5 0 0 A.5. 11206 8.05 S
155 154 0 3 van Billiard, Mr. Austin Blyler male 40.5 0 2 A/5. 851 14.5 S
156 155 0 3 Olsen, Mr. Ole Martin male 0 0 Fa 265302 7.3125 S
157 156 0 1 Williams, Mr. Charles Duane male 51 0 1 PC 17597 61.3792 C
158 157 1 3 Gilnagh, Miss. Katherine "Katie" female 16 0 0 35851 7.7333 Q
159 158 0 3 Corn, Mr. Harry male 30 0 0 SOTON/OQ 392090 8.05 S
160 159 0 3 Smiljanic, Mr. Mile male 0 0 315037 8.6625 S
161 160 0 3 Sage, Master. Thomas Henry male 8 2 CA. 2343 69.55 S
162 161 0 3 Cribb, Mr. John Hatfield male 44 0 1 371362 16.1 S
163 162 1 2 Watt, Mrs. James (Elizabeth "Bessie" Inglis Milne) female 40 0 0 C.A. 33595 15.75 S
164 163 0 3 Bengtsson, Mr. John Viktor male 26 0 0 347068 7.775 S
165 164 0 3 Calic, Mr. Jovo male 17 0 0 315093 8.6625 S
166 165 0 3 Panula, Master. Eino Viljami male 1 4 1 3101295 39.6875 S
167 166 1 3 Goldsmith, Master. Frank John William "Frankie" male 9 0 2 363291 20.525 S
168 167 1 1 Chibnall, Mrs. (Edith Martha Bowerman) female 0 1 113505 55 E33 S
169 168 0 3 Skoog, Mrs. William (Anna Bernhardina Karlsson) female 45 1 4 347088 27.9 S
170 169 0 1 Baumann, Mr. John D male 0 0 PC 17318 25.925 S
171 170 0 3 Ling, Mr. Lee male 28 0 0 1601 56.4958 S
172 171 0 1 Van der hoef, Mr. Wyckoff male 61 0 0 111240 33.5 B19 S
173 172 0 3 Rice, Master. Arthur male 4 4 1 382652 29.125 Q
174 173 1 3 Johnson, Miss. Eleanor Ileen female 1 1 1 347742 11.1333 S
175 174 0 3 Sivola, Mr. Antti Wilhelm male 21 0 0 STON/O 2. 3101280 7.925 S
176 175 0 1 Smith, Mr. James Clinch male 56 0 0 17764 30.6958 A7 C
177 176 0 3 Klasen, Mr. Klas Albin male 18 1 1 350404 7.8542 S
178 177 0 3 Lefebre, Master. Henry Forbes male 3 1 4133 25.4667 S
179 178 0 1 Isham, Miss. Ann Elizabeth female 50 0 0 PC 17595 28.7125 C49 C
180 179 0 2 Hale, Mr. Reginald male 30 0 0 250653 13 S
181 180 0 3 Leonard, Mr. Lionel male 36 0 0 LINE 0 S
182 181 0 3 Sage, Miss. Constance Gladys female 8 2 CA. 2343 69.55 S
183 182 0 2 Pernot, Mr. Rene male 0 0 SC/PARIS 2131 15.05 C
184 183 0 3 Asplund, Master. Clarence Gustaf Hugo male 9 4 2 347077 31.3875 S
185 184 1 2 Becker, Master. Richard F male 1 2 1 230136 39 F4 S
186 185 1 3 Kink-Heilmann, Miss. Luise Gretchen female 4 0 2 315153 22.025 S
187 186 0 1 Rood, Mr. Hugh Roscoe male 0 0 113767 50 A32 S
188 187 1 3 O'Brien, Mrs. Thomas (Johanna "Hannah" Godfrey) female 1 0 370365 15.5 Q
189 188 1 1 Romaine, Mr. Charles Hallace ("Mr C Rolmane") male 45 0 0 111428 26.55 S
190 189 0 3 Bourke, Mr. John male 40 1 1 364849 15.5 Q
191 190 0 3 Turcin, Mr. Stjepan male 36 0 0 349247 7.8958 S
192 191 1 2 Pinsky, Mrs. (Rosa) female 32 0 0 234604 13 S
193 192 0 2 Carbines, Mr. William male 19 0 0 28424 13 S
194 193 1 3 Andersen-Jensen, Miss. Carla Christine Nielsine female 19 1 0 350046 7.8542 S
195 194 1 2 Navratil, Master. Michel M male 3 1 1 230080 26 F2 S
196 195 1 1 Brown, Mrs. James Joseph (Margaret Tobin) female 44 0 0 PC 17610 27.7208 B4 C
197 196 1 1 Lurette, Miss. Elise female 58 0 0 PC 17569 146.5208 B80 C
198 197 0 3 Mernagh, Mr. Robert male 0 0 368703 7.75 Q
199 198 0 3 Olsen, Mr. Karl Siegwart Andreas male 42 0 1 4579 8.4042 S
200 199 1 3 Madigan, Miss. Margaret "Maggie" female 0 0 370370 7.75 Q
201 200 0 2 Yrois, Miss. Henriette ("Mrs Harbeck") female 24 0 0 248747 13 S
202 201 0 3 Vande Walle, Mr. Nestor Cyriel male 28 0 0 345770 9.5 S
203 202 0 3 Sage, Mr. Frederick male 8 2 CA. 2343 69.55 S
204 203 0 3 Johanson, Mr. Jakob Alfred male 34 0 0 3101264 6.4958 S
205 204 0 3 Youseff, Mr. Gerious male 45.5 0 0 2628 7.225 C
206 205 1 3 Cohen, Mr. Gurshon "Gus" male 18 0 0 A/5 3540 8.05 S
207 206 0 3 Strom, Miss. Telma Matilda female 2 0 1 347054 10.4625 G6 S
208 207 0 3 Backstrom, Mr. Karl Alfred male 32 1 0 3101278 15.85 S
209 208 1 3 Albimona, Mr. Nassef Cassem male 26 0 0 2699 18.7875 C
210 209 1 3 Carr, Miss. Helen "Ellen" female 16 0 0 367231 7.75 Q
211 210 1 1 Blank, Mr. Henry male 40 0 0 112277 31 A31 C
212 211 0 3 Ali, Mr. Ahmed male 24 0 0 SOTON/O.Q. 3101311 7.05 S
213 212 1 2 Cameron, Miss. Clear Annie female 35 0 0 F.C.C. 13528 21 S
214 213 0 3 Perkin, Mr. John Henry male 22 0 0 A/5 21174 7.25 S
215 214 0 2 Givard, Mr. Hans Kristensen male 30 0 0 250646 13 S
216 215 0 3 Kiernan, Mr. Philip male 1 0 367229 7.75 Q
217 216 1 1 Newell, Miss. Madeleine female 31 1 0 35273 113.275 D36 C
218 217 1 3 Honkanen, Miss. Eliina female 27 0 0 STON/O2. 3101283 7.925 S
219 218 0 2 Jacobsohn, Mr. Sidney Samuel male 42 1 0 243847 27 S
220 219 1 1 Bazzani, Miss. Albina female 32 0 0 11813 76.2917 D15 C
221 220 0 2 Harris, Mr. Walter male 30 0 0 W/C 14208 10.5 S
222 221 1 3 Sunderland, Mr. Victor Francis male 16 0 0 SOTON/OQ 392089 8.05 S
223 222 0 2 Bracken, Mr. James H male 27 0 0 220367 13 S
224 223 0 3 Green, Mr. George Henry male 51 0 0 21440 8.05 S
225 224 0 3 Nenkoff, Mr. Christo male 0 0 349234 7.8958 S
226 225 1 1 Hoyt, Mr. Frederick Maxfield male 38 1 0 19943 90 C93 S
227 226 0 3 Berglund, Mr. Karl Ivar Sven male 22 0 0 PP 4348 9.35 S
228 227 1 2 Mellors, Mr. William John male 19 0 0 SW/PP 751 10.5 S
229 228 0 3 Lovell, Mr. John Hall ("Henry") male 20.5 0 0 A/5 21173 7.25 S
230 229 0 2 Fahlstrom, Mr. Arne Jonas male 18 0 0 236171 13 S
231 230 0 3 Lefebre, Miss. Mathilde female 3 1 4133 25.4667 S
232 231 1 1 Harris, Mrs. Henry Birkhardt (Irene Wallach) female 35 1 0 36973 83.475 C83 S
233 232 0 3 Larsson, Mr. Bengt Edvin male 29 0 0 347067 7.775 S
234 233 0 2 Sjostedt, Mr. Ernst Adolf male 59 0 0 237442 13.5 S
235 234 1 3 Asplund, Miss. Lillian Gertrud female 5 4 2 347077 31.3875 S
236 235 0 2 Leyson, Mr. Robert William Norman male 24 0 0 C.A. 29566 10.5 S
237 236 0 3 Harknett, Miss. Alice Phoebe female 0 0 W./C. 6609 7.55 S
238 237 0 2 Hold, Mr. Stephen male 44 1 0 26707 26 S
239 238 1 2 Collyer, Miss. Marjorie "Lottie" female 8 0 2 C.A. 31921 26.25 S
240 239 0 2 Pengelly, Mr. Frederick William male 19 0 0 28665 10.5 S
241 240 0 2 Hunt, Mr. George Henry male 33 0 0 SCO/W 1585 12.275 S
242 241 0 3 Zabour, Miss. Thamine female 1 0 2665 14.4542 C
243 242 1 3 Murphy, Miss. Katherine "Kate" female 1 0 367230 15.5 Q
244 243 0 2 Coleridge, Mr. Reginald Charles male 29 0 0 W./C. 14263 10.5 S
245 244 0 3 Maenpaa, Mr. Matti Alexanteri male 22 0 0 STON/O 2. 3101275 7.125 S
246 245 0 3 Attalah, Mr. Sleiman male 30 0 0 2694 7.225 C
247 246 0 1 Minahan, Dr. William Edward male 44 2 0 19928 90 C78 Q
248 247 0 3 Lindahl, Miss. Agda Thorilda Viktoria female 25 0 0 347071 7.775 S
249 248 1 2 Hamalainen, Mrs. William (Anna) female 24 0 2 250649 14.5 S
250 249 1 1 Beckwith, Mr. Richard Leonard male 37 1 1 11751 52.5542 D35 S
251 250 0 2 Carter, Rev. Ernest Courtenay male 54 1 0 244252 26 S
252 251 0 3 Reed, Mr. James George male 0 0 362316 7.25 S
253 252 0 3 Strom, Mrs. Wilhelm (Elna Matilda Persson) female 29 1 1 347054 10.4625 G6 S
254 253 0 1 Stead, Mr. William Thomas male 62 0 0 113514 26.55 C87 S
255 254 0 3 Lobb, Mr. William Arthur male 30 1 0 A/5. 3336 16.1 S
256 255 0 3 Rosblom, Mrs. Viktor (Helena Wilhelmina) female 41 0 2 370129 20.2125 S
257 256 1 3 Touma, Mrs. Darwis (Hanne Youssef Razi) female 29 0 2 2650 15.2458 C
258 257 1 1 Thorne, Mrs. Gertrude Maybelle female 0 0 PC 17585 79.2 C
259 258 1 1 Cherry, Miss. Gladys female 30 0 0 110152 86.5 B77 S
260 259 1 1 Ward, Miss. Anna female 35 0 0 PC 17755 512.3292 C
261 260 1 2 Parrish, Mrs. (Lutie Davis) female 50 0 1 230433 26 S
262 261 0 3 Smith, Mr. Thomas male 0 0 384461 7.75 Q
263 262 1 3 Asplund, Master. Edvin Rojj Felix male 3 4 2 347077 31.3875 S
264 263 0 1 Taussig, Mr. Emil male 52 1 1 110413 79.65 E67 S
265 264 0 1 Harrison, Mr. William male 40 0 0 112059 0 B94 S
266 265 0 3 Henry, Miss. Delia female 0 0 382649 7.75 Q
267 266 0 2 Reeves, Mr. David male 36 0 0 C.A. 17248 10.5 S
268 267 0 3 Panula, Mr. Ernesti Arvid male 16 4 1 3101295 39.6875 S
269 268 1 3 Persson, Mr. Ernst Ulrik male 25 1 0 347083 7.775 S
270 269 1 1 Graham, Mrs. William Thompson (Edith Junkins) female 58 0 1 PC 17582 153.4625 C125 S
271 270 1 1 Bissette, Miss. Amelia female 35 0 0 PC 17760 135.6333 C99 S
272 271 0 1 Cairns, Mr. Alexander male 0 0 113798 31 S
273 272 1 3 Tornquist, Mr. William Henry male 25 0 0 LINE 0 S
274 273 1 2 Mellinger, Mrs. (Elizabeth Anne Maidment) female 41 0 1 250644 19.5 S
275 274 0 1 Natsch, Mr. Charles H male 37 0 1 PC 17596 29.7 C118 C
276 275 1 3 Healy, Miss. Hanora "Nora" female 0 0 370375 7.75 Q
277 276 1 1 Andrews, Miss. Kornelia Theodosia female 63 1 0 13502 77.9583 D7 S
278 277 0 3 Lindblom, Miss. Augusta Charlotta female 45 0 0 347073 7.75 S
279 278 0 2 Parkes, Mr. Francis "Frank" male 0 0 239853 0 S
280 279 0 3 Rice, Master. Eric male 7 4 1 382652 29.125 Q
281 280 1 3 Abbott, Mrs. Stanton (Rosa Hunt) female 35 1 1 C.A. 2673 20.25 S
282 281 0 3 Duane, Mr. Frank male 65 0 0 336439 7.75 Q
283 282 0 3 Olsson, Mr. Nils Johan Goransson male 28 0 0 347464 7.8542 S
284 283 0 3 de Pelsmaeker, Mr. Alfons male 16 0 0 345778 9.5 S
285 284 1 3 Dorking, Mr. Edward Arthur male 19 0 0 A/5. 10482 8.05 S
286 285 0 1 Smith, Mr. Richard William male 0 0 113056 26 A19 S
287 286 0 3 Stankovic, Mr. Ivan male 33 0 0 349239 8.6625 C
288 287 1 3 de Mulder, Mr. Theodore male 30 0 0 345774 9.5 S
289 288 0 3 Naidenoff, Mr. Penko male 22 0 0 349206 7.8958 S
290 289 1 2 Hosono, Mr. Masabumi male 42 0 0 237798 13 S
291 290 1 3 Connolly, Miss. Kate female 22 0 0 370373 7.75 Q
292 291 1 1 Barber, Miss. Ellen "Nellie" female 26 0 0 19877 78.85 S
293 292 1 1 Bishop, Mrs. Dickinson H (Helen Walton) female 19 1 0 11967 91.0792 B49 C
294 293 0 2 Levy, Mr. Rene Jacques male 36 0 0 SC/Paris 2163 12.875 D C
295 294 0 3 Haas, Miss. Aloisia female 24 0 0 349236 8.85 S
296 295 0 3 Mineff, Mr. Ivan male 24 0 0 349233 7.8958 S
297 296 0 1 Lewy, Mr. Ervin G male 0 0 PC 17612 27.7208 C
298 297 0 3 Hanna, Mr. Mansour male 23.5 0 0 2693 7.2292 C
299 298 0 1 Allison, Miss. Helen Loraine female 2 1 2 113781 151.55 C22 C26 S
300 299 1 1 Saalfeld, Mr. Adolphe male 0 0 19988 30.5 C106 S
301 300 1 1 Baxter, Mrs. James (Helene DeLaudeniere Chaput) female 50 0 1 PC 17558 247.5208 B58 B60 C
302 301 1 3 Kelly, Miss. Anna Katherine "Annie Kate" female 0 0 9234 7.75 Q
303 302 1 3 McCoy, Mr. Bernard male 2 0 367226 23.25 Q
304 303 0 3 Johnson, Mr. William Cahoone Jr male 19 0 0 LINE 0 S
305 304 1 2 Keane, Miss. Nora A female 0 0 226593 12.35 E101 Q
306 305 0 3 Williams, Mr. Howard Hugh "Harry" male 0 0 A/5 2466 8.05 S
307 306 1 1 Allison, Master. Hudson Trevor male 0.92 1 2 113781 151.55 C22 C26 S
308 307 1 1 Fleming, Miss. Margaret female 0 0 17421 110.8833 C
309 308 1 1 Penasco y Castellana, Mrs. Victor de Satode (Maria Josefa Perez de Soto y Vallejo) female 17 1 0 PC 17758 108.9 C65 C
310 309 0 2 Abelson, Mr. Samuel male 30 1 0 P/PP 3381 24 C
311 310 1 1 Francatelli, Miss. Laura Mabel female 30 0 0 PC 17485 56.9292 E36 C
312 311 1 1 Hays, Miss. Margaret Bechstein female 24 0 0 11767 83.1583 C54 C
313 312 1 1 Ryerson, Miss. Emily Borie female 18 2 2 PC 17608 262.375 B57 B59 B63 B66 C
314 313 0 2 Lahtinen, Mrs. William (Anna Sylfven) female 26 1 1 250651 26 S
315 314 0 3 Hendekovic, Mr. Ignjac male 28 0 0 349243 7.8958 S
316 315 0 2 Hart, Mr. Benjamin male 43 1 1 F.C.C. 13529 26.25 S
317 316 1 3 Nilsson, Miss. Helmina Josefina female 26 0 0 347470 7.8542 S
318 317 1 2 Kantor, Mrs. Sinai (Miriam Sternin) female 24 1 0 244367 26 S
319 318 0 2 Moraweck, Dr. Ernest male 54 0 0 29011 14 S
320 319 1 1 Wick, Miss. Mary Natalie female 31 0 2 36928 164.8667 C7 S
321 320 1 1 Spedden, Mrs. Frederic Oakley (Margaretta Corning Stone) female 40 1 1 16966 134.5 E34 C
322 321 0 3 Dennis, Mr. Samuel male 22 0 0 A/5 21172 7.25 S
323 322 0 3 Danoff, Mr. Yoto male 27 0 0 349219 7.8958 S
324 323 1 2 Slayter, Miss. Hilda Mary female 30 0 0 234818 12.35 Q
325 324 1 2 Caldwell, Mrs. Albert Francis (Sylvia Mae Harbaugh) female 22 1 1 248738 29 S
326 325 0 3 Sage, Mr. George John Jr male 8 2 CA. 2343 69.55 S
327 326 1 1 Young, Miss. Marie Grice female 36 0 0 PC 17760 135.6333 C32 C
328 327 0 3 Nysveen, Mr. Johan Hansen male 61 0 0 345364 6.2375 S
329 328 1 2 Ball, Mrs. (Ada E Hall) female 36 0 0 28551 13 D S
330 329 1 3 Goldsmith, Mrs. Frank John (Emily Alice Brown) female 31 1 1 363291 20.525 S
331 330 1 1 Hippach, Miss. Jean Gertrude female 16 0 1 111361 57.9792 B18 C
332 331 1 3 McCoy, Miss. Agnes female 2 0 367226 23.25 Q
333 332 0 1 Partner, Mr. Austen male 45.5 0 0 113043 28.5 C124 S
334 333 0 1 Graham, Mr. George Edward male 38 0 1 PC 17582 153.4625 C91 S
335 334 0 3 Vander Planke, Mr. Leo Edmondus male 16 2 0 345764 18 S
336 335 1 1 Frauenthal, Mrs. Henry William (Clara Heinsheimer) female 1 0 PC 17611 133.65 S
337 336 0 3 Denkoff, Mr. Mitto male 0 0 349225 7.8958 S
338 337 0 1 Pears, Mr. Thomas Clinton male 29 1 0 113776 66.6 C2 S
339 338 1 1 Burns, Miss. Elizabeth Margaret female 41 0 0 16966 134.5 E40 C
340 339 1 3 Dahl, Mr. Karl Edwart male 45 0 0 7598 8.05 S
341 340 0 1 Blackwell, Mr. Stephen Weart male 45 0 0 113784 35.5 T S
342 341 1 2 Navratil, Master. Edmond Roger male 2 1 1 230080 26 F2 S
343 342 1 1 Fortune, Miss. Alice Elizabeth female 24 3 2 19950 263 C23 C25 C27 S
344 343 0 2 Collander, Mr. Erik Gustaf male 28 0 0 248740 13 S
345 344 0 2 Sedgwick, Mr. Charles Frederick Waddington male 25 0 0 244361 13 S
346 345 0 2 Fox, Mr. Stanley Hubert male 36 0 0 229236 13 S
347 346 1 2 Brown, Miss. Amelia "Mildred" female 24 0 0 248733 13 F33 S
348 347 1 2 Smith, Miss. Marion Elsie female 40 0 0 31418 13 S
349 348 1 3 Davison, Mrs. Thomas Henry (Mary E Finck) female 1 0 386525 16.1 S
350 349 1 3 Coutts, Master. William Loch "William" male 3 1 1 C.A. 37671 15.9 S
351 350 0 3 Dimic, Mr. Jovan male 42 0 0 315088 8.6625 S
352 351 0 3 Odahl, Mr. Nils Martin male 23 0 0 7267 9.225 S
353 352 0 1 Williams-Lambert, Mr. Fletcher Fellows male 0 0 113510 35 C128 S
354 353 0 3 Elias, Mr. Tannous male 15 1 1 2695 7.2292 C
355 354 0 3 Arnold-Franchi, Mr. Josef male 25 1 0 349237 17.8 S
356 355 0 3 Yousif, Mr. Wazli male 0 0 2647 7.225 C
357 356 0 3 Vanden Steen, Mr. Leo Peter male 28 0 0 345783 9.5 S
358 357 1 1 Bowerman, Miss. Elsie Edith female 22 0 1 113505 55 E33 S
359 358 0 2 Funk, Miss. Annie Clemmer female 38 0 0 237671 13 S
360 359 1 3 McGovern, Miss. Mary female 0 0 330931 7.8792 Q
361 360 1 3 Mockler, Miss. Helen Mary "Ellie" female 0 0 330980 7.8792 Q
362 361 0 3 Skoog, Mr. Wilhelm male 40 1 4 347088 27.9 S
363 362 0 2 del Carlo, Mr. Sebastiano male 29 1 0 SC/PARIS 2167 27.7208 C
364 363 0 3 Barbara, Mrs. (Catherine David) female 45 0 1 2691 14.4542 C
365 364 0 3 Asim, Mr. Adola male 35 0 0 SOTON/O.Q. 3101310 7.05 S
366 365 0 3 O'Brien, Mr. Thomas male 1 0 370365 15.5 Q
367 366 0 3 Adahl, Mr. Mauritz Nils Martin male 30 0 0 C 7076 7.25 S
368 367 1 1 Warren, Mrs. Frank Manley (Anna Sophia Atkinson) female 60 1 0 110813 75.25 D37 C
369 368 1 3 Moussa, Mrs. (Mantoura Boulos) female 0 0 2626 7.2292 C
370 369 1 3 Jermyn, Miss. Annie female 0 0 14313 7.75 Q
371 370 1 1 Aubart, Mme. Leontine Pauline female 24 0 0 PC 17477 69.3 B35 C
372 371 1 1 Harder, Mr. George Achilles male 25 1 0 11765 55.4417 E50 C
373 372 0 3 Wiklund, Mr. Jakob Alfred male 18 1 0 3101267 6.4958 S
374 373 0 3 Beavan, Mr. William Thomas male 19 0 0 323951 8.05 S
375 374 0 1 Ringhini, Mr. Sante male 22 0 0 PC 17760 135.6333 C
376 375 0 3 Palsson, Miss. Stina Viola female 3 3 1 349909 21.075 S
377 376 1 1 Meyer, Mrs. Edgar Joseph (Leila Saks) female 1 0 PC 17604 82.1708 C
378 377 1 3 Landergren, Miss. Aurora Adelia female 22 0 0 C 7077 7.25 S
379 378 0 1 Widener, Mr. Harry Elkins male 27 0 2 113503 211.5 C82 C
380 379 0 3 Betros, Mr. Tannous male 20 0 0 2648 4.0125 C
381 380 0 3 Gustafsson, Mr. Karl Gideon male 19 0 0 347069 7.775 S
382 381 1 1 Bidois, Miss. Rosalie female 42 0 0 PC 17757 227.525 C
383 382 1 3 Nakid, Miss. Maria ("Mary") female 1 0 2 2653 15.7417 C
384 383 0 3 Tikkanen, Mr. Juho male 32 0 0 STON/O 2. 3101293 7.925 S
385 384 1 1 Holverson, Mrs. Alexander Oskar (Mary Aline Towner) female 35 1 0 113789 52 S
386 385 0 3 Plotcharsky, Mr. Vasil male 0 0 349227 7.8958 S
387 386 0 2 Davies, Mr. Charles Henry male 18 0 0 S.O.C. 14879 73.5 S
388 387 0 3 Goodwin, Master. Sidney Leonard male 1 5 2 CA 2144 46.9 S
389 388 1 2 Buss, Miss. Kate female 36 0 0 27849 13 S
390 389 0 3 Sadlier, Mr. Matthew male 0 0 367655 7.7292 Q
391 390 1 2 Lehmann, Miss. Bertha female 17 0 0 SC 1748 12 C
392 391 1 1 Carter, Mr. William Ernest male 36 1 2 113760 120 B96 B98 S
393 392 1 3 Jansson, Mr. Carl Olof male 21 0 0 350034 7.7958 S
394 393 0 3 Gustafsson, Mr. Johan Birger male 28 2 0 3101277 7.925 S
395 394 1 1 Newell, Miss. Marjorie female 23 1 0 35273 113.275 D36 C
396 395 1 3 Sandstrom, Mrs. Hjalmar (Agnes Charlotta Bengtsson) female 24 0 2 PP 9549 16.7 G6 S
397 396 0 3 Johansson, Mr. Erik male 22 0 0 350052 7.7958 S
398 397 0 3 Olsson, Miss. Elina female 31 0 0 350407 7.8542 S
399 398 0 2 McKane, Mr. Peter David male 46 0 0 28403 26 S
400 399 0 2 Pain, Dr. Alfred male 23 0 0 244278 10.5 S
401 400 1 2 Trout, Mrs. William H (Jessie L) female 28 0 0 240929 12.65 S
402 401 1 3 Niskanen, Mr. Juha male 39 0 0 STON/O 2. 3101289 7.925 S
403 402 0 3 Adams, Mr. John male 26 0 0 341826 8.05 S
404 403 0 3 Jussila, Miss. Mari Aina female 21 1 0 4137 9.825 S
405 404 0 3 Hakkarainen, Mr. Pekka Pietari male 28 1 0 STON/O2. 3101279 15.85 S
406 405 0 3 Oreskovic, Miss. Marija female 20 0 0 315096 8.6625 S
407 406 0 2 Gale, Mr. Shadrach male 34 1 0 28664 21 S
408 407 0 3 Widegren, Mr. Carl/Charles Peter male 51 0 0 347064 7.75 S
409 408 1 2 Richards, Master. William Rowe male 3 1 1 29106 18.75 S
410 409 0 3 Birkeland, Mr. Hans Martin Monsen male 21 0 0 312992 7.775 S
411 410 0 3 Lefebre, Miss. Ida female 3 1 4133 25.4667 S
412 411 0 3 Sdycoff, Mr. Todor male 0 0 349222 7.8958 S
413 412 0 3 Hart, Mr. Henry male 0 0 394140 6.8583 Q
414 413 1 1 Minahan, Miss. Daisy E female 33 1 0 19928 90 C78 Q
415 414 0 2 Cunningham, Mr. Alfred Fleming male 0 0 239853 0 S
416 415 1 3 Sundman, Mr. Johan Julian male 44 0 0 STON/O 2. 3101269 7.925 S
417 416 0 3 Meek, Mrs. Thomas (Annie Louise Rowley) female 0 0 343095 8.05 S
418 417 1 2 Drew, Mrs. James Vivian (Lulu Thorne Christian) female 34 1 1 28220 32.5 S
419 418 1 2 Silven, Miss. Lyyli Karoliina female 18 0 2 250652 13 S
420 419 0 2 Matthews, Mr. William John male 30 0 0 28228 13 S
421 420 0 3 Van Impe, Miss. Catharina female 10 0 2 345773 24.15 S
422 421 0 3 Gheorgheff, Mr. Stanio male 0 0 349254 7.8958 C
423 422 0 3 Charters, Mr. David male 21 0 0 A/5. 13032 7.7333 Q
424 423 0 3 Zimmerman, Mr. Leo male 29 0 0 315082 7.875 S
425 424 0 3 Danbom, Mrs. Ernst Gilbert (Anna Sigrid Maria Brogren) female 28 1 1 347080 14.4 S
426 425 0 3 Rosblom, Mr. Viktor Richard male 18 1 1 370129 20.2125 S
427 426 0 3 Wiseman, Mr. Phillippe male 0 0 A/4. 34244 7.25 S
428 427 1 2 Clarke, Mrs. Charles V (Ada Maria Winfield) female 28 1 0 2003 26 S
429 428 1 2 Phillips, Miss. Kate Florence ("Mrs Kate Louise Phillips Marshall") female 19 0 0 250655 26 S
430 429 0 3 Flynn, Mr. James male 0 0 364851 7.75 Q
431 430 1 3 Pickard, Mr. Berk (Berk Trembisky) male 32 0 0 SOTON/O.Q. 392078 8.05 E10 S
432 431 1 1 Bjornstrom-Steffansson, Mr. Mauritz Hakan male 28 0 0 110564 26.55 C52 S
433 432 1 3 Thorneycroft, Mrs. Percival (Florence Kate White) female 1 0 376564 16.1 S
434 433 1 2 Louch, Mrs. Charles Alexander (Alice Adelaide Slow) female 42 1 0 SC/AH 3085 26 S
435 434 0 3 Kallio, Mr. Nikolai Erland male 17 0 0 STON/O 2. 3101274 7.125 S
436 435 0 1 Silvey, Mr. William Baird male 50 1 0 13507 55.9 E44 S
437 436 1 1 Carter, Miss. Lucile Polk female 14 1 2 113760 120 B96 B98 S
438 437 0 3 Ford, Miss. Doolina Margaret "Daisy" female 21 2 2 W./C. 6608 34.375 S
439 438 1 2 Richards, Mrs. Sidney (Emily Hocking) female 24 2 3 29106 18.75 S
440 439 0 1 Fortune, Mr. Mark male 64 1 4 19950 263 C23 C25 C27 S
441 440 0 2 Kvillner, Mr. Johan Henrik Johannesson male 31 0 0 C.A. 18723 10.5 S
442 441 1 2 Hart, Mrs. Benjamin (Esther Ada Bloomfield) female 45 1 1 F.C.C. 13529 26.25 S
443 442 0 3 Hampe, Mr. Leon male 20 0 0 345769 9.5 S
444 443 0 3 Petterson, Mr. Johan Emil male 25 1 0 347076 7.775 S
445 444 1 2 Reynaldo, Ms. Encarnacion female 28 0 0 230434 13 S
446 445 1 3 Johannesen-Bratthammer, Mr. Bernt male 0 0 65306 8.1125 S
447 446 1 1 Dodge, Master. Washington male 4 0 2 33638 81.8583 A34 S
448 447 1 2 Mellinger, Miss. Madeleine Violet female 13 0 1 250644 19.5 S
449 448 1 1 Seward, Mr. Frederic Kimber male 34 0 0 113794 26.55 S
450 449 1 3 Baclini, Miss. Marie Catherine female 5 2 1 2666 19.2583 C
451 450 1 1 Peuchen, Major. Arthur Godfrey male 52 0 0 113786 30.5 C104 S
452 451 0 2 West, Mr. Edwy Arthur male 36 1 2 C.A. 34651 27.75 S
453 452 0 3 Hagland, Mr. Ingvald Olai Olsen male 1 0 65303 19.9667 S
454 453 0 1 Foreman, Mr. Benjamin Laventall male 30 0 0 113051 27.75 C111 C
455 454 1 1 Goldenberg, Mr. Samuel L male 49 1 0 17453 89.1042 C92 C
456 455 0 3 Peduzzi, Mr. Joseph male 0 0 A/5 2817 8.05 S
457 456 1 3 Jalsevac, Mr. Ivan male 29 0 0 349240 7.8958 C
458 457 0 1 Millet, Mr. Francis Davis male 65 0 0 13509 26.55 E38 S
459 458 1 1 Kenyon, Mrs. Frederick R (Marion) female 1 0 17464 51.8625 D21 S
460 459 1 2 Toomey, Miss. Ellen female 50 0 0 F.C.C. 13531 10.5 S
461 460 0 3 O'Connor, Mr. Maurice male 0 0 371060 7.75 Q
462 461 1 1 Anderson, Mr. Harry male 48 0 0 19952 26.55 E12 S
463 462 0 3 Morley, Mr. William male 34 0 0 364506 8.05 S
464 463 0 1 Gee, Mr. Arthur H male 47 0 0 111320 38.5 E63 S
465 464 0 2 Milling, Mr. Jacob Christian male 48 0 0 234360 13 S
466 465 0 3 Maisner, Mr. Simon male 0 0 A/S 2816 8.05 S
467 466 0 3 Goncalves, Mr. Manuel Estanslas male 38 0 0 SOTON/O.Q. 3101306 7.05 S
468 467 0 2 Campbell, Mr. William male 0 0 239853 0 S
469 468 0 1 Smart, Mr. John Montgomery male 56 0 0 113792 26.55 S
470 469 0 3 Scanlan, Mr. James male 0 0 36209 7.725 Q
471 470 1 3 Baclini, Miss. Helene Barbara female 0.75 2 1 2666 19.2583 C
472 471 0 3 Keefe, Mr. Arthur male 0 0 323592 7.25 S
473 472 0 3 Cacic, Mr. Luka male 38 0 0 315089 8.6625 S
474 473 1 2 West, Mrs. Edwy Arthur (Ada Mary Worth) female 33 1 2 C.A. 34651 27.75 S
475 474 1 2 Jerwan, Mrs. Amin S (Marie Marthe Thuillard) female 23 0 0 SC/AH Basle 541 13.7917 D C
476 475 0 3 Strandberg, Miss. Ida Sofia female 22 0 0 7553 9.8375 S
477 476 0 1 Clifford, Mr. George Quincy male 0 0 110465 52 A14 S
478 477 0 2 Renouf, Mr. Peter Henry male 34 1 0 31027 21 S
479 478 0 3 Braund, Mr. Lewis Richard male 29 1 0 3460 7.0458 S
480 479 0 3 Karlsson, Mr. Nils August male 22 0 0 350060 7.5208 S
481 480 1 3 Hirvonen, Miss. Hildur E female 2 0 1 3101298 12.2875 S
482 481 0 3 Goodwin, Master. Harold Victor male 9 5 2 CA 2144 46.9 S
483 482 0 2 Frost, Mr. Anthony Wood "Archie" male 0 0 239854 0 S
484 483 0 3 Rouse, Mr. Richard Henry male 50 0 0 A/5 3594 8.05 S
485 484 1 3 Turkula, Mrs. (Hedwig) female 63 0 0 4134 9.5875 S
486 485 1 1 Bishop, Mr. Dickinson H male 25 1 0 11967 91.0792 B49 C
487 486 0 3 Lefebre, Miss. Jeannie female 3 1 4133 25.4667 S
488 487 1 1 Hoyt, Mrs. Frederick Maxfield (Jane Anne Forby) female 35 1 0 19943 90 C93 S
489 488 0 1 Kent, Mr. Edward Austin male 58 0 0 11771 29.7 B37 C
490 489 0 3 Somerton, Mr. Francis William male 30 0 0 A.5. 18509 8.05 S
491 490 1 3 Coutts, Master. Eden Leslie "Neville" male 9 1 1 C.A. 37671 15.9 S
492 491 0 3 Hagland, Mr. Konrad Mathias Reiersen male 1 0 65304 19.9667 S
493 492 0 3 Windelov, Mr. Einar male 21 0 0 SOTON/OQ 3101317 7.25 S
494 493 0 1 Molson, Mr. Harry Markland male 55 0 0 113787 30.5 C30 S
495 494 0 1 Artagaveytia, Mr. Ramon male 71 0 0 PC 17609 49.5042 C
496 495 0 3 Stanley, Mr. Edward Roland male 21 0 0 A/4 45380 8.05 S
497 496 0 3 Yousseff, Mr. Gerious male 0 0 2627 14.4583 C
498 497 1 1 Eustis, Miss. Elizabeth Mussey female 54 1 0 36947 78.2667 D20 C
499 498 0 3 Shellard, Mr. Frederick William male 0 0 C.A. 6212 15.1 S
500 499 0 1 Allison, Mrs. Hudson J C (Bessie Waldo Daniels) female 25 1 2 113781 151.55 C22 C26 S
501 500 0 3 Svensson, Mr. Olof male 24 0 0 350035 7.7958 S
502 501 0 3 Calic, Mr. Petar male 17 0 0 315086 8.6625 S
503 502 0 3 Canavan, Miss. Mary female 21 0 0 364846 7.75 Q
504 503 0 3 O'Sullivan, Miss. Bridget Mary female 0 0 330909 7.6292 Q
505 504 0 3 Laitinen, Miss. Kristina Sofia female 37 0 0 4135 9.5875 S
506 505 1 1 Maioni, Miss. Roberta female 16 0 0 110152 86.5 B79 S
507 506 0 1 Penasco y Castellana, Mr. Victor de Satode male 18 1 0 PC 17758 108.9 C65 C
508 507 1 2 Quick, Mrs. Frederick Charles (Jane Richards) female 33 0 2 26360 26 S
509 508 1 1 Bradley, Mr. George ("George Arthur Brayton") male 0 0 111427 26.55 S
510 509 0 3 Olsen, Mr. Henry Margido male 28 0 0 C 4001 22.525 S
511 510 1 3 Lang, Mr. Fang male 26 0 0 1601 56.4958 S
512 511 1 3 Daly, Mr. Eugene Patrick male 29 0 0 382651 7.75 Q
513 512 0 3 Webber, Mr. James male 0 0 SOTON/OQ 3101316 8.05 S
514 513 1 1 McGough, Mr. James Robert male 36 0 0 PC 17473 26.2875 E25 S
515 514 1 1 Rothschild, Mrs. Martin (Elizabeth L. Barrett) female 54 1 0 PC 17603 59.4 C
516 515 0 3 Coleff, Mr. Satio male 24 0 0 349209 7.4958 S
517 516 0 1 Walker, Mr. William Anderson male 47 0 0 36967 34.0208 D46 S
518 517 1 2 Lemore, Mrs. (Amelia Milley) female 34 0 0 C.A. 34260 10.5 F33 S
519 518 0 3 Ryan, Mr. Patrick male 0 0 371110 24.15 Q
520 519 1 2 Angle, Mrs. William A (Florence "Mary" Agnes Hughes) female 36 1 0 226875 26 S
521 520 0 3 Pavlovic, Mr. Stefo male 32 0 0 349242 7.8958 S
522 521 1 1 Perreault, Miss. Anne female 30 0 0 12749 93.5 B73 S
523 522 0 3 Vovk, Mr. Janko male 22 0 0 349252 7.8958 S
524 523 0 3 Lahoud, Mr. Sarkis male 0 0 2624 7.225 C
525 524 1 1 Hippach, Mrs. Louis Albert (Ida Sophia Fischer) female 44 0 1 111361 57.9792 B18 C
526 525 0 3 Kassem, Mr. Fared male 0 0 2700 7.2292 C
527 526 0 3 Farrell, Mr. James male 40.5 0 0 367232 7.75 Q
528 527 1 2 Ridsdale, Miss. Lucy female 50 0 0 W./C. 14258 10.5 S
529 528 0 1 Farthing, Mr. John male 0 0 PC 17483 221.7792 C95 S
530 529 0 3 Salonen, Mr. Johan Werner male 39 0 0 3101296 7.925 S
531 530 0 2 Hocking, Mr. Richard George male 23 2 1 29104 11.5 S
532 531 1 2 Quick, Miss. Phyllis May female 2 1 1 26360 26 S
533 532 0 3 Toufik, Mr. Nakli male 0 0 2641 7.2292 C
534 533 0 3 Elias, Mr. Joseph Jr male 17 1 1 2690 7.2292 C
535 534 1 3 Peter, Mrs. Catherine (Catherine Rizk) female 0 2 2668 22.3583 C
536 535 0 3 Cacic, Miss. Marija female 30 0 0 315084 8.6625 S
537 536 1 2 Hart, Miss. Eva Miriam female 7 0 2 F.C.C. 13529 26.25 S
538 537 0 1 Butt, Major. Archibald Willingham male 45 0 0 113050 26.55 B38 S
539 538 1 1 LeRoy, Miss. Bertha female 30 0 0 PC 17761 106.425 C
540 539 0 3 Risien, Mr. Samuel Beard male 0 0 364498 14.5 S
541 540 1 1 Frolicher, Miss. Hedwig Margaritha female 22 0 2 13568 49.5 B39 C
542 541 1 1 Crosby, Miss. Harriet R female 36 0 2 WE/P 5735 71 B22 S
543 542 0 3 Andersson, Miss. Ingeborg Constanzia female 9 4 2 347082 31.275 S
544 543 0 3 Andersson, Miss. Sigrid Elisabeth female 11 4 2 347082 31.275 S
545 544 1 2 Beane, Mr. Edward male 32 1 0 2908 26 S
546 545 0 1 Douglas, Mr. Walter Donald male 50 1 0 PC 17761 106.425 C86 C
547 546 0 1 Nicholson, Mr. Arthur Ernest male 64 0 0 693 26 S
548 547 1 2 Beane, Mrs. Edward (Ethel Clarke) female 19 1 0 2908 26 S
549 548 1 2 Padro y Manent, Mr. Julian male 0 0 SC/PARIS 2146 13.8625 C
550 549 0 3 Goldsmith, Mr. Frank John male 33 1 1 363291 20.525 S
551 550 1 2 Davies, Master. John Morgan Jr male 8 1 1 C.A. 33112 36.75 S
552 551 1 1 Thayer, Mr. John Borland Jr male 17 0 2 17421 110.8833 C70 C
553 552 0 2 Sharp, Mr. Percival James R male 27 0 0 244358 26 S
554 553 0 3 O'Brien, Mr. Timothy male 0 0 330979 7.8292 Q
555 554 1 3 Leeni, Mr. Fahim ("Philip Zenni") male 22 0 0 2620 7.225 C
556 555 1 3 Ohman, Miss. Velin female 22 0 0 347085 7.775 S
557 556 0 1 Wright, Mr. George male 62 0 0 113807 26.55 S
558 557 1 1 Duff Gordon, Lady. (Lucille Christiana Sutherland) ("Mrs Morgan") female 48 1 0 11755 39.6 A16 C
559 558 0 1 Robbins, Mr. Victor male 0 0 PC 17757 227.525 C
560 559 1 1 Taussig, Mrs. Emil (Tillie Mandelbaum) female 39 1 1 110413 79.65 E67 S
561 560 1 3 de Messemaeker, Mrs. Guillaume Joseph (Emma) female 36 1 0 345572 17.4 S
562 561 0 3 Morrow, Mr. Thomas Rowan male 0 0 372622 7.75 Q
563 562 0 3 Sivic, Mr. Husein male 40 0 0 349251 7.8958 S
564 563 0 2 Norman, Mr. Robert Douglas male 28 0 0 218629 13.5 S
565 564 0 3 Simmons, Mr. John male 0 0 SOTON/OQ 392082 8.05 S
566 565 0 3 Meanwell, Miss. (Marion Ogden) female 0 0 SOTON/O.Q. 392087 8.05 S
567 566 0 3 Davies, Mr. Alfred J male 24 2 0 A/4 48871 24.15 S
568 567 0 3 Stoytcheff, Mr. Ilia male 19 0 0 349205 7.8958 S
569 568 0 3 Palsson, Mrs. Nils (Alma Cornelia Berglund) female 29 0 4 349909 21.075 S
570 569 0 3 Doharr, Mr. Tannous male 0 0 2686 7.2292 C
571 570 1 3 Jonsson, Mr. Carl male 32 0 0 350417 7.8542 S
572 571 1 2 Harris, Mr. George male 62 0 0 S.W./PP 752 10.5 S
573 572 1 1 Appleton, Mrs. Edward Dale (Charlotte Lamson) female 53 2 0 11769 51.4792 C101 S
574 573 1 1 Flynn, Mr. John Irwin ("Irving") male 36 0 0 PC 17474 26.3875 E25 S
575 574 1 3 Kelly, Miss. Mary female 0 0 14312 7.75 Q
576 575 0 3 Rush, Mr. Alfred George John male 16 0 0 A/4. 20589 8.05 S
577 576 0 3 Patchett, Mr. George male 19 0 0 358585 14.5 S
578 577 1 2 Garside, Miss. Ethel female 34 0 0 243880 13 S
579 578 1 1 Silvey, Mrs. William Baird (Alice Munger) female 39 1 0 13507 55.9 E44 S
580 579 0 3 Caram, Mrs. Joseph (Maria Elias) female 1 0 2689 14.4583 C
581 580 1 3 Jussila, Mr. Eiriik male 32 0 0 STON/O 2. 3101286 7.925 S
582 581 1 2 Christy, Miss. Julie Rachel female 25 1 1 237789 30 S
583 582 1 1 Thayer, Mrs. John Borland (Marian Longstreth Morris) female 39 1 1 17421 110.8833 C68 C
584 583 0 2 Downton, Mr. William James male 54 0 0 28403 26 S
585 584 0 1 Ross, Mr. John Hugo male 36 0 0 13049 40.125 A10 C
586 585 0 3 Paulner, Mr. Uscher male 0 0 3411 8.7125 C
587 586 1 1 Taussig, Miss. Ruth female 18 0 2 110413 79.65 E68 S
588 587 0 2 Jarvis, Mr. John Denzil male 47 0 0 237565 15 S
589 588 1 1 Frolicher-Stehli, Mr. Maxmillian male 60 1 1 13567 79.2 B41 C
590 589 0 3 Gilinski, Mr. Eliezer male 22 0 0 14973 8.05 S
591 590 0 3 Murdlin, Mr. Joseph male 0 0 A./5. 3235 8.05 S
592 591 0 3 Rintamaki, Mr. Matti male 35 0 0 STON/O 2. 3101273 7.125 S
593 592 1 1 Stephenson, Mrs. Walter Bertram (Martha Eustis) female 52 1 0 36947 78.2667 D20 C
594 593 0 3 Elsbury, Mr. William James male 47 0 0 A/5 3902 7.25 S
595 594 0 3 Bourke, Miss. Mary female 0 2 364848 7.75 Q
596 595 0 2 Chapman, Mr. John Henry male 37 1 0 SC/AH 29037 26 S
597 596 0 3 Van Impe, Mr. Jean Baptiste male 36 1 1 345773 24.15 S
598 597 1 2 Leitch, Miss. Jessie Wills female 0 0 248727 33 S
599 598 0 3 Johnson, Mr. Alfred male 49 0 0 LINE 0 S
600 599 0 3 Boulos, Mr. Hanna male 0 0 2664 7.225 C
601 600 1 1 Duff Gordon, Sir. Cosmo Edmund ("Mr Morgan") male 49 1 0 PC 17485 56.9292 A20 C
602 601 1 2 Jacobsohn, Mrs. Sidney Samuel (Amy Frances Christy) female 24 2 1 243847 27 S
603 602 0 3 Slabenoff, Mr. Petco male 0 0 349214 7.8958 S
604 603 0 1 Harrington, Mr. Charles H male 0 0 113796 42.4 S
605 604 0 3 Torber, Mr. Ernst William male 44 0 0 364511 8.05 S
606 605 1 1 Homer, Mr. Harry ("Mr E Haven") male 35 0 0 111426 26.55 C
607 606 0 3 Lindell, Mr. Edvard Bengtsson male 36 1 0 349910 15.55 S
608 607 0 3 Karaic, Mr. Milan male 30 0 0 349246 7.8958 S
609 608 1 1 Daniel, Mr. Robert Williams male 27 0 0 113804 30.5 S
610 609 1 2 Laroche, Mrs. Joseph (Juliette Marie Louise Lafargue) female 22 1 2 SC/Paris 2123 41.5792 C
611 610 1 1 Shutes, Miss. Elizabeth W female 40 0 0 PC 17582 153.4625 C125 S
612 611 0 3 Andersson, Mrs. Anders Johan (Alfrida Konstantia Brogren) female 39 1 5 347082 31.275 S
613 612 0 3 Jardin, Mr. Jose Neto male 0 0 SOTON/O.Q. 3101305 7.05 S
614 613 1 3 Murphy, Miss. Margaret Jane female 1 0 367230 15.5 Q
615 614 0 3 Horgan, Mr. John male 0 0 370377 7.75 Q
616 615 0 3 Brocklebank, Mr. William Alfred male 35 0 0 364512 8.05 S
617 616 1 2 Herman, Miss. Alice female 24 1 2 220845 65 S
618 617 0 3 Danbom, Mr. Ernst Gilbert male 34 1 1 347080 14.4 S
619 618 0 3 Lobb, Mrs. William Arthur (Cordelia K Stanlick) female 26 1 0 A/5. 3336 16.1 S
620 619 1 2 Becker, Miss. Marion Louise female 4 2 1 230136 39 F4 S
621 620 0 2 Gavey, Mr. Lawrence male 26 0 0 31028 10.5 S
622 621 0 3 Yasbeck, Mr. Antoni male 27 1 0 2659 14.4542 C
623 622 1 1 Kimball, Mr. Edwin Nelson Jr male 42 1 0 11753 52.5542 D19 S
624 623 1 3 Nakid, Mr. Sahid male 20 1 1 2653 15.7417 C
625 624 0 3 Hansen, Mr. Henry Damsgaard male 21 0 0 350029 7.8542 S
626 625 0 3 Bowen, Mr. David John "Dai" male 21 0 0 54636 16.1 S
627 626 0 1 Sutton, Mr. Frederick male 61 0 0 36963 32.3208 D50 S
628 627 0 2 Kirkland, Rev. Charles Leonard male 57 0 0 219533 12.35 Q
629 628 1 1 Longley, Miss. Gretchen Fiske female 21 0 0 13502 77.9583 D9 S
630 629 0 3 Bostandyeff, Mr. Guentcho male 26 0 0 349224 7.8958 S
631 630 0 3 O'Connell, Mr. Patrick D male 0 0 334912 7.7333 Q
632 631 1 1 Barkworth, Mr. Algernon Henry Wilson male 80 0 0 27042 30 A23 S
633 632 0 3 Lundahl, Mr. Johan Svensson male 51 0 0 347743 7.0542 S
634 633 1 1 Stahelin-Maeglin, Dr. Max male 32 0 0 13214 30.5 B50 C
635 634 0 1 Parr, Mr. William Henry Marsh male 0 0 112052 0 S
636 635 0 3 Skoog, Miss. Mabel female 9 3 2 347088 27.9 S
637 636 1 2 Davis, Miss. Mary female 28 0 0 237668 13 S
638 637 0 3 Leinonen, Mr. Antti Gustaf male 32 0 0 STON/O 2. 3101292 7.925 S
639 638 0 2 Collyer, Mr. Harvey male 31 1 1 C.A. 31921 26.25 S
640 639 0 3 Panula, Mrs. Juha (Maria Emilia Ojala) female 41 0 5 3101295 39.6875 S
641 640 0 3 Thorneycroft, Mr. Percival male 1 0 376564 16.1 S
642 641 0 3 Jensen, Mr. Hans Peder male 20 0 0 350050 7.8542 S
643 642 1 1 Sagesser, Mlle. Emma female 24 0 0 PC 17477 69.3 B35 C
644 643 0 3 Skoog, Miss. Margit Elizabeth female 2 3 2 347088 27.9 S
645 644 1 3 Foo, Mr. Choong male 0 0 1601 56.4958 S
646 645 1 3 Baclini, Miss. Eugenie female 0.75 2 1 2666 19.2583 C
647 646 1 1 Harper, Mr. Henry Sleeper male 48 1 0 PC 17572 76.7292 D33 C
648 647 0 3 Cor, Mr. Liudevit male 19 0 0 349231 7.8958 S
649 648 1 1 Simonius-Blumer, Col. Oberst Alfons male 56 0 0 13213 35.5 A26 C
650 649 0 3 Willey, Mr. Edward male 0 0 S.O./P.P. 751 7.55 S
651 650 1 3 Stanley, Miss. Amy Zillah Elsie female 23 0 0 CA. 2314 7.55 S
652 651 0 3 Mitkoff, Mr. Mito male 0 0 349221 7.8958 S
653 652 1 2 Doling, Miss. Elsie female 18 0 1 231919 23 S
654 653 0 3 Kalvik, Mr. Johannes Halvorsen male 21 0 0 8475 8.4333 S
655 654 1 3 O'Leary, Miss. Hanora "Norah" female 0 0 330919 7.8292 Q
656 655 0 3 Hegarty, Miss. Hanora "Nora" female 18 0 0 365226 6.75 Q
657 656 0 2 Hickman, Mr. Leonard Mark male 24 2 0 S.O.C. 14879 73.5 S
658 657 0 3 Radeff, Mr. Alexander male 0 0 349223 7.8958 S
659 658 0 3 Bourke, Mrs. John (Catherine) female 32 1 1 364849 15.5 Q
660 659 0 2 Eitemiller, Mr. George Floyd male 23 0 0 29751 13 S
661 660 0 1 Newell, Mr. Arthur Webster male 58 0 2 35273 113.275 D48 C
662 661 1 1 Frauenthal, Dr. Henry William male 50 2 0 PC 17611 133.65 S
663 662 0 3 Badt, Mr. Mohamed male 40 0 0 2623 7.225 C
664 663 0 1 Colley, Mr. Edward Pomeroy male 47 0 0 5727 25.5875 E58 S
665 664 0 3 Coleff, Mr. Peju male 36 0 0 349210 7.4958 S
666 665 1 3 Lindqvist, Mr. Eino William male 20 1 0 STON/O 2. 3101285 7.925 S
667 666 0 2 Hickman, Mr. Lewis male 32 2 0 S.O.C. 14879 73.5 S
668 667 0 2 Butler, Mr. Reginald Fenton male 25 0 0 234686 13 S
669 668 0 3 Rommetvedt, Mr. Knud Paust male 0 0 312993 7.775 S
670 669 0 3 Cook, Mr. Jacob male 43 0 0 A/5 3536 8.05 S
671 670 1 1 Taylor, Mrs. Elmer Zebley (Juliet Cummins Wright) female 1 0 19996 52 C126 S
672 671 1 2 Brown, Mrs. Thomas William Solomon (Elizabeth Catherine Ford) female 40 1 1 29750 39 S
673 672 0 1 Davidson, Mr. Thornton male 31 1 0 F.C. 12750 52 B71 S
674 673 0 2 Mitchell, Mr. Henry Michael male 70 0 0 C.A. 24580 10.5 S
675 674 1 2 Wilhelms, Mr. Charles male 31 0 0 244270 13 S
676 675 0 2 Watson, Mr. Ennis Hastings male 0 0 239856 0 S
677 676 0 3 Edvardsson, Mr. Gustaf Hjalmar male 18 0 0 349912 7.775 S
678 677 0 3 Sawyer, Mr. Frederick Charles male 24.5 0 0 342826 8.05 S
679 678 1 3 Turja, Miss. Anna Sofia female 18 0 0 4138 9.8417 S
680 679 0 3 Goodwin, Mrs. Frederick (Augusta Tyler) female 43 1 6 CA 2144 46.9 S
681 680 1 1 Cardeza, Mr. Thomas Drake Martinez male 36 0 1 PC 17755 512.3292 B51 B53 B55 C
682 681 0 3 Peters, Miss. Katie female 0 0 330935 8.1375 Q
683 682 1 1 Hassab, Mr. Hammad male 27 0 0 PC 17572 76.7292 D49 C
684 683 0 3 Olsvigen, Mr. Thor Anderson male 20 0 0 6563 9.225 S
685 684 0 3 Goodwin, Mr. Charles Edward male 14 5 2 CA 2144 46.9 S
686 685 0 2 Brown, Mr. Thomas William Solomon male 60 1 1 29750 39 S
687 686 0 2 Laroche, Mr. Joseph Philippe Lemercier male 25 1 2 SC/Paris 2123 41.5792 C
688 687 0 3 Panula, Mr. Jaako Arnold male 14 4 1 3101295 39.6875 S
689 688 0 3 Dakic, Mr. Branko male 19 0 0 349228 10.1708 S
690 689 0 3 Fischer, Mr. Eberhard Thelander male 18 0 0 350036 7.7958 S
691 690 1 1 Madill, Miss. Georgette Alexandra female 15 0 1 24160 211.3375 B5 S
692 691 1 1 Dick, Mr. Albert Adrian male 31 1 0 17474 57 B20 S
693 692 1 3 Karun, Miss. Manca female 4 0 1 349256 13.4167 C
694 693 1 3 Lam, Mr. Ali male 0 0 1601 56.4958 S
695 694 0 3 Saad, Mr. Khalil male 25 0 0 2672 7.225 C
696 695 0 1 Weir, Col. John male 60 0 0 113800 26.55 S
697 696 0 2 Chapman, Mr. Charles Henry male 52 0 0 248731 13.5 S
698 697 0 3 Kelly, Mr. James male 44 0 0 363592 8.05 S
699 698 1 3 Mullens, Miss. Katherine "Katie" female 0 0 35852 7.7333 Q
700 699 0 1 Thayer, Mr. John Borland male 49 1 1 17421 110.8833 C68 C
701 700 0 3 Humblen, Mr. Adolf Mathias Nicolai Olsen male 42 0 0 348121 7.65 F G63 S
702 701 1 1 Astor, Mrs. John Jacob (Madeleine Talmadge Force) female 18 1 0 PC 17757 227.525 C62 C64 C
703 702 1 1 Silverthorne, Mr. Spencer Victor male 35 0 0 PC 17475 26.2875 E24 S
704 703 0 3 Barbara, Miss. Saiide female 18 0 1 2691 14.4542 C
705 704 0 3 Gallagher, Mr. Martin male 25 0 0 36864 7.7417 Q
706 705 0 3 Hansen, Mr. Henrik Juul male 26 1 0 350025 7.8542 S
707 706 0 2 Morley, Mr. Henry Samuel ("Mr Henry Marshall") male 39 0 0 250655 26 S
708 707 1 2 Kelly, Mrs. Florence "Fannie" female 45 0 0 223596 13.5 S
709 708 1 1 Calderhead, Mr. Edward Pennington male 42 0 0 PC 17476 26.2875 E24 S
710 709 1 1 Cleaver, Miss. Alice female 22 0 0 113781 151.55 S
711 710 1 3 Moubarek, Master. Halim Gonios ("William George") male 1 1 2661 15.2458 C
712 711 1 1 Mayne, Mlle. Berthe Antonine ("Mrs de Villiers") female 24 0 0 PC 17482 49.5042 C90 C
713 712 0 1 Klaber, Mr. Herman male 0 0 113028 26.55 C124 S
714 713 1 1 Taylor, Mr. Elmer Zebley male 48 1 0 19996 52 C126 S
715 714 0 3 Larsson, Mr. August Viktor male 29 0 0 7545 9.4833 S
716 715 0 2 Greenberg, Mr. Samuel male 52 0 0 250647 13 S
717 716 0 3 Soholt, Mr. Peter Andreas Lauritz Andersen male 19 0 0 348124 7.65 F G73 S
718 717 1 1 Endres, Miss. Caroline Louise female 38 0 0 PC 17757 227.525 C45 C
719 718 1 2 Troutt, Miss. Edwina Celia "Winnie" female 27 0 0 34218 10.5 E101 S
720 719 0 3 McEvoy, Mr. Michael male 0 0 36568 15.5 Q
721 720 0 3 Johnson, Mr. Malkolm Joackim male 33 0 0 347062 7.775 S
722 721 1 2 Harper, Miss. Annie Jessie "Nina" female 6 0 1 248727 33 S
723 722 0 3 Jensen, Mr. Svend Lauritz male 17 1 0 350048 7.0542 S
724 723 0 2 Gillespie, Mr. William Henry male 34 0 0 12233 13 S
725 724 0 2 Hodges, Mr. Henry Price male 50 0 0 250643 13 S
726 725 1 1 Chambers, Mr. Norman Campbell male 27 1 0 113806 53.1 E8 S
727 726 0 3 Oreskovic, Mr. Luka male 20 0 0 315094 8.6625 S
728 727 1 2 Renouf, Mrs. Peter Henry (Lillian Jefferys) female 30 3 0 31027 21 S
729 728 1 3 Mannion, Miss. Margareth female 0 0 36866 7.7375 Q
730 729 0 2 Bryhl, Mr. Kurt Arnold Gottfrid male 25 1 0 236853 26 S
731 730 0 3 Ilmakangas, Miss. Pieta Sofia female 25 1 0 STON/O2. 3101271 7.925 S
732 731 1 1 Allen, Miss. Elisabeth Walton female 29 0 0 24160 211.3375 B5 S
733 732 0 3 Hassan, Mr. Houssein G N male 11 0 0 2699 18.7875 C
734 733 0 2 Knight, Mr. Robert J male 0 0 239855 0 S
735 734 0 2 Berriman, Mr. William John male 23 0 0 28425 13 S
736 735 0 2 Troupiansky, Mr. Moses Aaron male 23 0 0 233639 13 S
737 736 0 3 Williams, Mr. Leslie male 28.5 0 0 54636 16.1 S
738 737 0 3 Ford, Mrs. Edward (Margaret Ann Watson) female 48 1 3 W./C. 6608 34.375 S
739 738 1 1 Lesurer, Mr. Gustave J male 35 0 0 PC 17755 512.3292 B101 C
740 739 0 3 Ivanoff, Mr. Kanio male 0 0 349201 7.8958 S
741 740 0 3 Nankoff, Mr. Minko male 0 0 349218 7.8958 S
742 741 1 1 Hawksford, Mr. Walter James male 0 0 16988 30 D45 S
743 742 0 1 Cavendish, Mr. Tyrell William male 36 1 0 19877 78.85 C46 S
744 743 1 1 Ryerson, Miss. Susan Parker "Suzette" female 21 2 2 PC 17608 262.375 B57 B59 B63 B66 C
745 744 0 3 McNamee, Mr. Neal male 24 1 0 376566 16.1 S
746 745 1 3 Stranden, Mr. Juho male 31 0 0 STON/O 2. 3101288 7.925 S
747 746 0 1 Crosby, Capt. Edward Gifford male 70 1 1 WE/P 5735 71 B22 S
748 747 0 3 Abbott, Mr. Rossmore Edward male 16 1 1 C.A. 2673 20.25 S
749 748 1 2 Sinkkonen, Miss. Anna female 30 0 0 250648 13 S
750 749 0 1 Marvin, Mr. Daniel Warner male 19 1 0 113773 53.1 D30 S
751 750 0 3 Connaghton, Mr. Michael male 31 0 0 335097 7.75 Q
752 751 1 2 Wells, Miss. Joan female 4 1 1 29103 23 S
753 752 1 3 Moor, Master. Meier male 6 0 1 392096 12.475 E121 S
754 753 0 3 Vande Velde, Mr. Johannes Joseph male 33 0 0 345780 9.5 S
755 754 0 3 Jonkoff, Mr. Lalio male 23 0 0 349204 7.8958 S
756 755 1 2 Herman, Mrs. Samuel (Jane Laver) female 48 1 2 220845 65 S
757 756 1 2 Hamalainen, Master. Viljo male 0.67 1 1 250649 14.5 S
758 757 0 3 Carlsson, Mr. August Sigfrid male 28 0 0 350042 7.7958 S
759 758 0 2 Bailey, Mr. Percy Andrew male 18 0 0 29108 11.5 S
760 759 0 3 Theobald, Mr. Thomas Leonard male 34 0 0 363294 8.05 S
761 760 1 1 Rothes, the Countess. of (Lucy Noel Martha Dyer-Edwards) female 33 0 0 110152 86.5 B77 S
762 761 0 3 Garfirth, Mr. John male 0 0 358585 14.5 S
763 762 0 3 Nirva, Mr. Iisakki Antino Aijo male 41 0 0 SOTON/O2 3101272 7.125 S
764 763 1 3 Barah, Mr. Hanna Assi male 20 0 0 2663 7.2292 C
765 764 1 1 Carter, Mrs. William Ernest (Lucile Polk) female 36 1 2 113760 120 B96 B98 S
766 765 0 3 Eklund, Mr. Hans Linus male 16 0 0 347074 7.775 S
767 766 1 1 Hogeboom, Mrs. John C (Anna Andrews) female 51 1 0 13502 77.9583 D11 S
768 767 0 1 Brewe, Dr. Arthur Jackson male 0 0 112379 39.6 C
769 768 0 3 Mangan, Miss. Mary female 30.5 0 0 364850 7.75 Q
770 769 0 3 Moran, Mr. Daniel J male 1 0 371110 24.15 Q
771 770 0 3 Gronnestad, Mr. Daniel Danielsen male 32 0 0 8471 8.3625 S
772 771 0 3 Lievens, Mr. Rene Aime male 24 0 0 345781 9.5 S
773 772 0 3 Jensen, Mr. Niels Peder male 48 0 0 350047 7.8542 S
774 773 0 2 Mack, Mrs. (Mary) female 57 0 0 S.O./P.P. 3 10.5 E77 S
775 774 0 3 Elias, Mr. Dibo male 0 0 2674 7.225 C
776 775 1 2 Hocking, Mrs. Elizabeth (Eliza Needs) female 54 1 3 29105 23 S
777 776 0 3 Myhrman, Mr. Pehr Fabian Oliver Malkolm male 18 0 0 347078 7.75 S
778 777 0 3 Tobin, Mr. Roger male 0 0 383121 7.75 F38 Q
779 778 1 3 Emanuel, Miss. Virginia Ethel female 5 0 0 364516 12.475 S
780 779 0 3 Kilgannon, Mr. Thomas J male 0 0 36865 7.7375 Q
781 780 1 1 Robert, Mrs. Edward Scott (Elisabeth Walton McMillan) female 43 0 1 24160 211.3375 B3 S
782 781 1 3 Ayoub, Miss. Banoura female 13 0 0 2687 7.2292 C
783 782 1 1 Dick, Mrs. Albert Adrian (Vera Gillespie) female 17 1 0 17474 57 B20 S
784 783 0 1 Long, Mr. Milton Clyde male 29 0 0 113501 30 D6 S
785 784 0 3 Johnston, Mr. Andrew G male 1 2 W./C. 6607 23.45 S
786 785 0 3 Ali, Mr. William male 25 0 0 SOTON/O.Q. 3101312 7.05 S
787 786 0 3 Harmer, Mr. Abraham (David Lishin) male 25 0 0 374887 7.25 S
788 787 1 3 Sjoblom, Miss. Anna Sofia female 18 0 0 3101265 7.4958 S
789 788 0 3 Rice, Master. George Hugh male 8 4 1 382652 29.125 Q
790 789 1 3 Dean, Master. Bertram Vere male 1 1 2 C.A. 2315 20.575 S
791 790 0 1 Guggenheim, Mr. Benjamin male 46 0 0 PC 17593 79.2 B82 B84 C
792 791 0 3 Keane, Mr. Andrew "Andy" male 0 0 12460 7.75 Q
793 792 0 2 Gaskell, Mr. Alfred male 16 0 0 239865 26 S
794 793 0 3 Sage, Miss. Stella Anna female 8 2 CA. 2343 69.55 S
795 794 0 1 Hoyt, Mr. William Fisher male 0 0 PC 17600 30.6958 C
796 795 0 3 Dantcheff, Mr. Ristiu male 25 0 0 349203 7.8958 S
797 796 0 2 Otter, Mr. Richard male 39 0 0 28213 13 S
798 797 1 1 Leader, Dr. Alice (Farnham) female 49 0 0 17465 25.9292 D17 S
799 798 1 3 Osman, Mrs. Mara female 31 0 0 349244 8.6833 S
800 799 0 3 Ibrahim Shawah, Mr. Yousseff male 30 0 0 2685 7.2292 C
801 800 0 3 Van Impe, Mrs. Jean Baptiste (Rosalie Paula Govaert) female 30 1 1 345773 24.15 S
802 801 0 2 Ponesell, Mr. Martin male 34 0 0 250647 13 S
803 802 1 2 Collyer, Mrs. Harvey (Charlotte Annie Tate) female 31 1 1 C.A. 31921 26.25 S
804 803 1 1 Carter, Master. William Thornton II male 11 1 2 113760 120 B96 B98 S
805 804 1 3 Thomas, Master. Assad Alexander male 0.42 0 1 2625 8.5167 C
806 805 1 3 Hedman, Mr. Oskar Arvid male 27 0 0 347089 6.975 S
807 806 0 3 Johansson, Mr. Karl Johan male 31 0 0 347063 7.775 S
808 807 0 1 Andrews, Mr. Thomas Jr male 39 0 0 112050 0 A36 S
809 808 0 3 Pettersson, Miss. Ellen Natalia female 18 0 0 347087 7.775 S
810 809 0 2 Meyer, Mr. August male 39 0 0 248723 13 S
811 810 1 1 Chambers, Mrs. Norman Campbell (Bertha Griggs) female 33 1 0 113806 53.1 E8 S
812 811 0 3 Alexander, Mr. William male 26 0 0 3474 7.8875 S
813 812 0 3 Lester, Mr. James male 39 0 0 A/4 48871 24.15 S
814 813 0 2 Slemen, Mr. Richard James male 35 0 0 28206 10.5 S
815 814 0 3 Andersson, Miss. Ebba Iris Alfrida female 6 4 2 347082 31.275 S
816 815 0 3 Tomlin, Mr. Ernest Portage male 30.5 0 0 364499 8.05 S
817 816 0 1 Fry, Mr. Richard male 0 0 112058 0 B102 S
818 817 0 3 Heininen, Miss. Wendla Maria female 23 0 0 STON/O2. 3101290 7.925 S
819 818 0 2 Mallet, Mr. Albert male 31 1 1 S.C./PARIS 2079 37.0042 C
820 819 0 3 Holm, Mr. John Fredrik Alexander male 43 0 0 C 7075 6.45 S
821 820 0 3 Skoog, Master. Karl Thorsten male 10 3 2 347088 27.9 S
822 821 1 1 Hays, Mrs. Charles Melville (Clara Jennings Gregg) female 52 1 1 12749 93.5 B69 S
823 822 1 3 Lulic, Mr. Nikola male 27 0 0 315098 8.6625 S
824 823 0 1 Reuchlin, Jonkheer. John George male 38 0 0 19972 0 S
825 824 1 3 Moor, Mrs. (Beila) female 27 0 1 392096 12.475 E121 S
826 825 0 3 Panula, Master. Urho Abraham male 2 4 1 3101295 39.6875 S
827 826 0 3 Flynn, Mr. John male 0 0 368323 6.95 Q
828 827 0 3 Lam, Mr. Len male 0 0 1601 56.4958 S
829 828 1 2 Mallet, Master. Andre male 1 0 2 S.C./PARIS 2079 37.0042 C
830 829 1 3 McCormack, Mr. Thomas Joseph male 0 0 367228 7.75 Q
831 830 1 1 Stone, Mrs. George Nelson (Martha Evelyn) female 62 0 0 113572 80 B28
832 831 1 3 Yasbeck, Mrs. Antoni (Selini Alexander) female 15 1 0 2659 14.4542 C
833 832 1 2 Richards, Master. George Sibley male 0.83 1 1 29106 18.75 S
834 833 0 3 Saad, Mr. Amin male 0 0 2671 7.2292 C
835 834 0 3 Augustsson, Mr. Albert male 23 0 0 347468 7.8542 S
836 835 0 3 Allum, Mr. Owen George male 18 0 0 2223 8.3 S
837 836 1 1 Compton, Miss. Sara Rebecca female 39 1 1 PC 17756 83.1583 E49 C
838 837 0 3 Pasic, Mr. Jakob male 21 0 0 315097 8.6625 S
839 838 0 3 Sirota, Mr. Maurice male 0 0 392092 8.05 S
840 839 1 3 Chip, Mr. Chang male 32 0 0 1601 56.4958 S
841 840 1 1 Marechal, Mr. Pierre male 0 0 11774 29.7 C47 C
842 841 0 3 Alhomaki, Mr. Ilmari Rudolf male 20 0 0 SOTON/O2 3101287 7.925 S
843 842 0 2 Mudd, Mr. Thomas Charles male 16 0 0 S.O./P.P. 3 10.5 S
844 843 1 1 Serepeca, Miss. Augusta female 30 0 0 113798 31 C
845 844 0 3 Lemberopolous, Mr. Peter L male 34.5 0 0 2683 6.4375 C
846 845 0 3 Culumovic, Mr. Jeso male 17 0 0 315090 8.6625 S
847 846 0 3 Abbing, Mr. Anthony male 42 0 0 C.A. 5547 7.55 S
848 847 0 3 Sage, Mr. Douglas Bullen male 8 2 CA. 2343 69.55 S
849 848 0 3 Markoff, Mr. Marin male 35 0 0 349213 7.8958 C
850 849 0 2 Harper, Rev. John male 28 0 1 248727 33 S
851 850 1 1 Goldenberg, Mrs. Samuel L (Edwiga Grabowska) female 1 0 17453 89.1042 C92 C
852 851 0 3 Andersson, Master. Sigvard Harald Elias male 4 4 2 347082 31.275 S
853 852 0 3 Svensson, Mr. Johan male 74 0 0 347060 7.775 S
854 853 0 3 Boulos, Miss. Nourelain female 9 1 1 2678 15.2458 C
855 854 1 1 Lines, Miss. Mary Conover female 16 0 1 PC 17592 39.4 D28 S
856 855 0 2 Carter, Mrs. Ernest Courtenay (Lilian Hughes) female 44 1 0 244252 26 S
857 856 1 3 Aks, Mrs. Sam (Leah Rosen) female 18 0 1 392091 9.35 S
858 857 1 1 Wick, Mrs. George Dennick (Mary Hitchcock) female 45 1 1 36928 164.8667 S
859 858 1 1 Daly, Mr. Peter Denis male 51 0 0 113055 26.55 E17 S
860 859 1 3 Baclini, Mrs. Solomon (Latifa Qurban) female 24 0 3 2666 19.2583 C
861 860 0 3 Razi, Mr. Raihed male 0 0 2629 7.2292 C
862 861 0 3 Hansen, Mr. Claus Peter male 41 2 0 350026 14.1083 S
863 862 0 2 Giles, Mr. Frederick Edward male 21 1 0 28134 11.5 S
864 863 1 1 Swift, Mrs. Frederick Joel (Margaret Welles Barron) female 48 0 0 17466 25.9292 D17 S
865 864 0 3 Sage, Miss. Dorothy Edith "Dolly" female 8 2 CA. 2343 69.55 S
866 865 0 2 Gill, Mr. John William male 24 0 0 233866 13 S
867 866 1 2 Bystrom, Mrs. (Karolina) female 42 0 0 236852 13 S
868 867 1 2 Duran y More, Miss. Asuncion female 27 1 0 SC/PARIS 2149 13.8583 C
869 868 0 1 Roebling, Mr. Washington Augustus II male 31 0 0 PC 17590 50.4958 A24 S
870 869 0 3 van Melkebeke, Mr. Philemon male 0 0 345777 9.5 S
871 870 1 3 Johnson, Master. Harold Theodor male 4 1 1 347742 11.1333 S
872 871 0 3 Balkic, Mr. Cerin male 26 0 0 349248 7.8958 S
873 872 1 1 Beckwith, Mrs. Richard Leonard (Sallie Monypeny) female 47 1 1 11751 52.5542 D35 S
874 873 0 1 Carlsson, Mr. Frans Olof male 33 0 0 695 5 B51 B53 B55 S
875 874 0 3 Vander Cruyssen, Mr. Victor male 47 0 0 345765 9 S
876 875 1 2 Abelson, Mrs. Samuel (Hannah Wizosky) female 28 1 0 P/PP 3381 24 C
877 876 1 3 Najib, Miss. Adele Kiamie "Jane" female 15 0 0 2667 7.225 C
878 877 0 3 Gustafsson, Mr. Alfred Ossian male 20 0 0 7534 9.8458 S
879 878 0 3 Petroff, Mr. Nedelio male 19 0 0 349212 7.8958 S
880 879 0 3 Laleff, Mr. Kristo male 0 0 349217 7.8958 S
881 880 1 1 Potter, Mrs. Thomas Jr (Lily Alexenia Wilson) female 56 0 1 11767 83.1583 C50 C
882 881 1 2 Shelley, Mrs. William (Imanita Parrish Hall) female 25 0 1 230433 26 S
883 882 0 3 Markun, Mr. Johann male 33 0 0 349257 7.8958 S
884 883 0 3 Dahlberg, Miss. Gerda Ulrika female 22 0 0 7552 10.5167 S
885 884 0 2 Banfield, Mr. Frederick James male 28 0 0 C.A./SOTON 34068 10.5 S
886 885 0 3 Sutehall, Mr. Henry Jr male 25 0 0 SOTON/OQ 392076 7.05 S
887 886 0 3 Rice, Mrs. William (Margaret Norton) female 39 0 5 382652 29.125 Q
888 887 0 2 Montvila, Rev. Juozas male 27 0 0 211536 13 S
889 888 1 1 Graham, Miss. Margaret Edith female 19 0 0 112053 30 B42 S
890 889 0 3 Johnston, Miss. Catherine Helen "Carrie" female 1 2 W./C. 6607 23.45 S
891 890 1 1 Behr, Mr. Karl Howell male 26 0 0 111369 30 C148 C
892 891 0 3 Dooley, Mr. Patrick male 32 0 0 370376 7.75 Q

View File

@ -0,0 +1,417 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "18ada398-dce6-4049-9b56-fc0ede63da9c",
"metadata": {},
"source": [
"# Vectorstore Agent\n",
"\n",
"This notebook showcases an agent designed to retrieve information from one or more vectorstores, either with or without sources."
]
},
{
"cell_type": "markdown",
"id": "eecb683b-3a46-4b9d-81a3-7caefbfec1a1",
"metadata": {},
"source": [
"## Create the Vectorstores"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "9bfd0ed8-a5eb-443e-8e92-90be8cabb0a7",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.vectorstores import Chroma\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain import OpenAI, VectorDBQA\n",
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "345bb078-4ec1-4e3a-827b-cd238c49054d",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"from langchain.document_loaders import TextLoader\n",
"loader = TextLoader('../../state_of_the_union.txt')\n",
"documents = loader.load()\n",
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"texts = text_splitter.split_documents(documents)\n",
"\n",
"embeddings = OpenAIEmbeddings()\n",
"state_of_union_store = Chroma.from_documents(texts, embeddings, collection_name=\"state-of-union\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "5f50eb82-e1a5-4252-8306-8ec1b478d9b4",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running Chroma using direct local API.\n",
"Using DuckDB in-memory for database. Data will be transient.\n"
]
}
],
"source": [
"from langchain.document_loaders import WebBaseLoader\n",
"loader = WebBaseLoader(\"https://beta.ruff.rs/docs/faq/\")\n",
"docs = loader.load()\n",
"ruff_texts = text_splitter.split_documents(docs)\n",
"ruff_store = Chroma.from_documents(ruff_texts, embeddings, collection_name=\"ruff\")"
]
},
{
"cell_type": "markdown",
"id": "f4814175-964d-42f1-aa9d-22801ce1e912",
"metadata": {},
"source": [
"## Initalize Toolkit and Agent\n",
"\n",
"First, we'll create an agent with a single vectorstore."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "5b3b3206",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents.agent_toolkits import (\n",
" create_vectorstore_agent,\n",
" VectorStoreToolkit,\n",
" VectorStoreInfo,\n",
")\n",
"vectorstore_info = VectorStoreInfo(\n",
" name=\"state_of_union_address\",\n",
" description=\"the most recent state of the Union adress\",\n",
" vectorstore=state_of_union_store\n",
")\n",
"toolkit = VectorStoreToolkit(vectorstore_info=vectorstore_info)\n",
"agent_executor = create_vectorstore_agent(\n",
" llm=llm,\n",
" toolkit=toolkit,\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "8a38ad10",
"metadata": {},
"source": [
"## Examples"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "3f2f455c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find the answer in the state of the union address\n",
"Action: state_of_union_address\n",
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address?\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "d61e1e63",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to use the state_of_union_address_with_sources tool to answer this question.\n",
"Action: state_of_union_address_with_sources\n",
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m{\"answer\": \" Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\\n\", \"sources\": \"../../state_of_the_union.txt\"}\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence. Sources: ../../state_of_the_union.txt\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Biden said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to the United States Supreme Court, and that she is one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence. Sources: ../../state_of_the_union.txt\""
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address? List the source.\")"
]
},
{
"cell_type": "markdown",
"id": "7ca07707",
"metadata": {},
"source": [
"## Multiple Vectorstores\n",
"We can also easily use this initialize an agent with multiple vectorstores and use the agent to route between them. To do this. This agent is optimized for routing, so it is a different toolkit and initializer."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "c3209fd3",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents.agent_toolkits import (\n",
" create_vectorstore_router_agent,\n",
" VectorStoreRouterToolkit,\n",
" VectorStoreInfo,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "815c4f39-308d-4949-b992-1361036e6e09",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"ruff_vectorstore_info = VectorStoreInfo(\n",
" name=\"ruff\",\n",
" description=\"Information about the Ruff python linting library\",\n",
" vectorstore=ruff_store\n",
")\n",
"router_toolkit = VectorStoreRouterToolkit(\n",
" vectorstores=[vectorstore_info, ruff_vectorstore_info],\n",
" llm=llm\n",
")\n",
"agent_executor = create_vectorstore_agent(\n",
" llm=llm,\n",
" toolkit=router_toolkit,\n",
" verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "71680984-edaf-4a63-90f5-94edbd263550",
"metadata": {},
"source": [
"## Examples"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "3cd1bf3e-e3df-4e69-bbe1-71c64b1af947",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to use the state_of_union_address tool to answer this question.\n",
"Action: state_of_union_address\n",
"Action Input: What did biden say about ketanji brown jackson\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\"Biden said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What did biden say about ketanji brown jackson is the state of the union address?\")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "c5998b8d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out what tool ruff uses to run over Jupyter Notebooks\n",
"Action: ruff\n",
"Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb'"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What tool does ruff use to run over Jupyter Notebooks?\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "744e9b51-fbd9-4778-b594-ea957d0f3467",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out what tool ruff uses and if the president mentioned it in the state of the union.\n",
"Action: ruff\n",
"Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.ipynb\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out if the president mentioned nbQA in the state of the union.\n",
"Action: state_of_union_address\n",
"Action Input: Did the president mention nbQA in the state of the union?\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'No, the president did not mention nbQA in the state of the union.'"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent_executor.run(\"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "92203aa9-f63a-4ce1-b562-fadf4474ad9d",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@ -1,7 +1,7 @@
# Agents
Agents use an LLM to determine which actions to take and in what order.
An action can either be using a tool and observing its output, or returning to the user.
An action can either be using a tool and observing its output, or returning a response to the user.
For a list of easily loadable tools, see [here](tools.md).
Here are the agents available in LangChain.

View File

@ -403,7 +403,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
"version": "3.10.9"
}
},
"nbformat": 4,

View File

@ -29,16 +29,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m Yes.\n",
"Follow up: Who is the reigning men's U.S. Open champion?\u001b[0m\n",
"Intermediate answer: \u001b[36;1m\u001b[1;3m2016 · SUI · Stan Wawrinka ; 2017 · ESP · Rafael Nadal ; 2018 · SRB · Novak Djokovic ; 2019 · ESP · Rafael Nadal.\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mSo the reigning men's U.S. Open champion is Rafael Nadal.\n",
"Follow up: What is Rafael Nadal's hometown?\u001b[0m\n",
"Intermediate answer: \u001b[36;1m\u001b[1;3mIn 2016, he once again showed his deep ties to Mallorca and opened the Rafa Nadal Academy in his hometown of Manacor.\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mSo the final answer is: Manacor, Mallorca, Spain.\u001b[0m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m Yes.\n",
"Follow up: Who is the reigning men's U.S. Open champion?\u001B[0m\n",
"Intermediate answer: \u001B[36;1m\u001B[1;3m2016 · SUI · Stan Wawrinka ; 2017 · ESP · Rafael Nadal ; 2018 · SRB · Novak Djokovic ; 2019 · ESP · Rafael Nadal.\u001B[0m\n",
"\u001B[32;1m\u001B[1;3mSo the reigning men's U.S. Open champion is Rafael Nadal.\n",
"Follow up: What is Rafael Nadal's hometown?\u001B[0m\n",
"Intermediate answer: \u001B[36;1m\u001B[1;3mIn 2016, he once again showed his deep ties to Mallorca and opened the Rafa Nadal Academy in his hometown of Manacor.\u001B[0m\n",
"\u001B[32;1m\u001B[1;3mSo the final answer is: Manacor, Mallorca, Spain.\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

View File

@ -12,7 +12,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 2,
"id": "e6860c2d",
"metadata": {
"pycharm": {
@ -28,7 +28,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 3,
"id": "dadbcfcd",
"metadata": {},
"outputs": [],
@ -238,6 +238,92 @@
"source": [
"agent.run(\"What is the weather in Pomfret?\")"
]
},
{
"cell_type": "markdown",
"id": "eabad3af",
"metadata": {},
"source": [
"## SearxNG Meta Search Engine\n",
"\n",
"Here we will be using a self hosted SearxNG meta search engine."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "b196c704",
"metadata": {},
"outputs": [],
"source": [
"tools = load_tools([\"searx-search\"], searx_host=\"http://localhost:8888\", llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "9023eeaa",
"metadata": {},
"outputs": [],
"source": [
"agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "3aad92c1",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I should look up the current weather\n",
"Action: SearX Search\n",
"Action Input: \"weather in Pomfret\"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mMainly cloudy with snow showers around in the morning. High around 40F. Winds NNW at 5 to 10 mph. Chance of snow 40%. Snow accumulations less than one inch.\n",
"\n",
"10 Day Weather - Pomfret, MD As of 1:37 pm EST Today 49°/ 41° 52% Mon 27 | Day 49° 52% SE 14 mph Cloudy with occasional rain showers. High 49F. Winds SE at 10 to 20 mph. Chance of rain 50%....\n",
"\n",
"10 Day Weather - Pomfret, VT As of 3:51 am EST Special Weather Statement Today 39°/ 32° 37% Wed 01 | Day 39° 37% NE 4 mph Cloudy with snow showers developing for the afternoon. High 39F....\n",
"\n",
"Pomfret, CT ; Current Weather. 1:06 AM. 35°F · RealFeel® 32° ; TODAY'S WEATHER FORECAST. 3/3. 44°Hi. RealFeel® 50° ; TONIGHT'S WEATHER FORECAST. 3/3. 32°Lo.\n",
"\n",
"Pomfret, MD Forecast Today Hourly Daily Morning 41° 1% Afternoon 43° 0% Evening 35° 3% Overnight 34° 2% Don't Miss Finally, Heres Why We Get More Colds and Flu When Its Cold Coast-To-Coast...\n",
"\n",
"Pomfret, MD Weather Forecast | AccuWeather Current Weather 5:35 PM 35° F RealFeel® 36° RealFeel Shade™ 36° Air Quality Excellent Wind E 3 mph Wind Gusts 5 mph Cloudy More Details WinterCast...\n",
"\n",
"Pomfret, VT Weather Forecast | AccuWeather Current Weather 11:21 AM 23° F RealFeel® 27° RealFeel Shade™ 25° Air Quality Fair Wind ESE 3 mph Wind Gusts 7 mph Cloudy More Details WinterCast...\n",
"\n",
"Pomfret Center, CT Weather Forecast | AccuWeather Daily Current Weather 6:50 PM 39° F RealFeel® 36° Air Quality Fair Wind NW 6 mph Wind Gusts 16 mph Mostly clear More Details WinterCast...\n",
"\n",
"12:00 pm · Feels Like36° · WindN 5 mph · Humidity43% · UV Index3 of 10 · Cloud Cover65% · Rain Amount0 in ...\n",
"\n",
"Pomfret Center, CT Weather Conditions | Weather Underground star Popular Cities San Francisco, CA 49 °F Clear Manhattan, NY 37 °F Fair Schiller Park, IL (60176) warning39 °F Mostly Cloudy...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"agent.run(\"What is the weather in Pomfret\")"
]
}
],
"metadata": {
@ -256,7 +342,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
"version": "3.9.11"
},
"vscode": {
"interpreter": {

View File

@ -1,6 +1,15 @@
How-To Guides
=============
There are three types of examples in this section:
1. Agent Overview: how-to-guides for generic agent functionality
2. Agent Toolkits: how-to-guides for specific agent toolkits (agents optimized for interacting with a certain resource)
3. Agent Types: how-to-guides for working with the different agent types
Agent Overview
---------------
The first category of how-to guides here cover specific parts of working with agents.
`Load From Hub <./examples/load_from_hub.html>`_: This notebook covers how to load agents from `LangChainHub <https://github.com/hwchase17/langchain-hub>`_.
@ -21,7 +30,48 @@ The first category of how-to guides here cover specific parts of working with ag
`Asynchronous <./examples/async_agent.html>`_: Covering asynchronous functionality.
The next set of examples are all end-to-end agents for specific applications.
.. toctree::
:maxdepth: 1
:glob:
:hidden:
./examples/*
Agent Toolkits
---------------
The next set of examples covers agents with toolkits.
As opposed to the examples above, these examples are not intended to show off an agent `type`,
but rather to show off an agent applied to particular use case.
`SQLDatabase Agent <./agent_toolkits/sql_database.html>`_: This notebook covers how to interact with an arbitrary SQL database using an agent.
`JSON Agent <./agent_toolkits/json.html>`_: This notebook covers how to interact with a JSON dictionary using an agent.
`OpenAPI Agent <./agent_toolkits/openapi.html>`_: This notebook covers how to interact with an arbitrary OpenAPI endpoint using an agent.
`VectorStore Agent <./agent_toolkits/vectorstore.html>`_: This notebook covers how to interact with VectorStores using an agent.
`Python Agent <./agent_toolkits/python.html>`_: This notebook covers how to produce and execute python code using an agent.
`Pandas DataFrame Agent <./agent_toolkits/pandas.html>`_: This notebook covers how to do question answering over a pandas dataframe using an agent. Under the hood this calls the Python agent..
`CSV Agent <./agent_toolkits/csv.html>`_: This notebook covers how to do question answering over a csv file. Under the hood this calls the Pandas DataFrame agent.
.. toctree::
:maxdepth: 1
:glob:
:hidden:
./agent_toolkits/*
Agent Types
---------------
The final set of examples are all end-to-end example of different agent types.
In all examples there is an Agent with a particular set of tools.
- Tools: A tool can be anything that takes in a string and returns a string. This means that you can use both the primitives AND the chains found in `this <../chains.html>`_ documentation. LangChain also provides a list of easily loadable tools. For detailed information on those, please see `this documentation <./tools.html>`_
@ -51,16 +101,13 @@ In all examples there is an Agent with a particular set of tools.
.. toctree::
:maxdepth: 1
:glob:
:hidden:
./examples/*
.. toctree::
:maxdepth: 1
:glob:
:hidden:
./implementations/*
./implementations/*

View File

@ -205,7 +205,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
"version": "3.10.9"
}
},
"nbformat": 4,

View File

@ -63,7 +63,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.9.0 64-bit ('llm-env')",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@ -77,7 +77,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.0"
"version": "3.10.9"
},
"vscode": {
"interpreter": {

View File

@ -8,3 +8,8 @@ For more detailed information on agents, and different types of agents in LangCh
Tools are functions that agents can use to interact with the world.
These tools can be generic utilities (e.g. search), other chains, or even other agents.
For more detailed information on tools, and different types of tools in LangChain, see [this documentation](tools.md).
## ToolKits
Toolkits are groups of tools that are best used together.
They allow you to logically group and initialize a set of tools that share a particular resource (such as a database connection or json object).
They can be used to construct an agent for a specific use-case.

View File

@ -2,8 +2,8 @@ Chains
==========================
Using an LLM in isolation is fine for some simple applications,
but many more complex ones require chaining LLMs - either with eachother or with other experts.
LangChain provides a standard interface for Chains, as well as some common implementations of chains for easy use.
but many more complex ones require chaining LLMs - either with each other or with other experts.
LangChain provides a standard interface for Chains, as well as some common implementations of chains for ease of use.
The following sections of documentation are provided:
@ -26,4 +26,4 @@ The following sections of documentation are provided:
./chains/getting_started.ipynb
./chains/how_to_guides.rst
./chains/key_concepts.rst
Reference<../reference/modules/chains.rst>
Reference<../reference/modules/chains.rst>

View File

@ -39,7 +39,7 @@
"\n",
"\n",
"SparkleSmile Toothpaste\n",
"\u001b[1mConcurrent executed in 1.54 seconds.\u001b[0m\n",
"\u001B[1mConcurrent executed in 1.54 seconds.\u001B[0m\n",
"\n",
"\n",
"BrightSmile Toothpaste Co.\n",
@ -55,7 +55,7 @@
"\n",
"\n",
"BrightSmile Toothpaste.\n",
"\u001b[1mSerial executed in 6.38 seconds.\u001b[0m\n"
"\u001B[1mSerial executed in 6.38 seconds.\u001B[0m\n"
]
}
],

File diff suppressed because it is too large Load Diff

View File

@ -71,17 +71,17 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mdef solution():\n",
"\u001B[1m> Entering new PALChain chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3mdef solution():\n",
" \"\"\"Jan has three times the number of pets as Marcia. Marcia has two more pets than Cindy. If Cindy has four pets, how many total pets do the three have?\"\"\"\n",
" cindy_pets = 4\n",
" marcia_pets = cindy_pets + 2\n",
" jan_pets = marcia_pets * 3\n",
" total_pets = cindy_pets + marcia_pets + jan_pets\n",
" result = total_pets\n",
" return result\u001b[0m\n",
" return result\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -139,8 +139,8 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m# Put objects into a list to record ordering\n",
"\u001B[1m> Entering new PALChain chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m# Put objects into a list to record ordering\n",
"objects = []\n",
"objects += [('booklet', 'blue')] * 2\n",
"objects += [('booklet', 'purple')] * 2\n",
@ -151,9 +151,9 @@
"\n",
"# Count number of purple objects\n",
"num_purple = len([object for object in objects if object[1] == 'purple'])\n",
"answer = num_purple\u001b[0m\n",
"answer = num_purple\u001B[0m\n",
"\n",
"\u001b[1m> Finished PALChain chain.\u001b[0m\n"
"\u001B[1m> Finished PALChain chain.\u001B[0m\n"
]
},
{
@ -212,8 +212,8 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m# Put objects into a list to record ordering\n",
"\u001B[1m> Entering new PALChain chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m# Put objects into a list to record ordering\n",
"objects = []\n",
"objects += [('booklet', 'blue')] * 2\n",
"objects += [('booklet', 'purple')] * 2\n",
@ -224,9 +224,9 @@
"\n",
"# Count number of purple objects\n",
"num_purple = len([object for object in objects if object[1] == 'purple'])\n",
"answer = num_purple\u001b[0m\n",
"answer = num_purple\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
}
],

View File

@ -379,9 +379,17 @@
")\n",
"\n",
"SELECT * FROM 'Track' LIMIT 2;\n",
"TrackId Name AlbumId MediaTypeId GenreId Composer Milliseconds Bytes UnitPrice\n",
"1 For Those About To Rock (We Salute You) 1 1 1 Angus Young, Malcolm Young, Brian Johnson 343719 11170334 0.99\n",
"2 Balls to the Wall 2 2 1 None 342562 5510424 0.99\n"
"TrackId\tName\tAlbumId\tMediaTypeId\tGenreId\tComposer\tMilliseconds\tBytes\tUnitPrice\n",
"1\tFor Those About To Rock (We Salute You)\t1\t1\t1\tAngus Young, Malcolm Young, Brian Johnson\t343719\t11170334\t0.99\n",
"2\tBalls to the Wall\t2\t2\t1\tNone\t342562\t5510424\t0.99\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/jon/projects/langchain/langchain/sql_database.py:121: SAWarning: Dialect sqlite+pysqlite does *not* support Decimal objects natively, and SQLAlchemy must convert from floating point - rounding errors and other issues may occur. Please consider storing Decimal numbers as strings or integers on this platform for lossless storage.\n",
" sample_rows = connection.execute(command)\n"
]
}
],
@ -434,6 +442,131 @@
"db_chain.run(\"What are some example tracks by Bach?\")"
]
},
{
"cell_type": "markdown",
"id": "ef94e948",
"metadata": {},
"source": [
"### Custom Table Info\n",
"In some cases, it can be useful to provide custom table information instead of using the automatically generated table definitions and the first `sample_rows_in_table_info` sample rows. For example, if you know that the first few rows of a table are uninformative, it could help to manually provide example rows that are more diverse or provide more information to the model. It is also possible to limit the columns that will be visible to the model if there are unnecessary columns. \n",
"\n",
"This information can be provided as a dictionary with table names as the keys and table information as the values. For example, let's provide a custom definition and sample rows for the Track table with only a few columns:"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "2ad33ab1",
"metadata": {},
"outputs": [],
"source": [
"custom_table_info = {\n",
" \"Track\": \"\"\"CREATE TABLE Track (\n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\t\"Name\" NVARCHAR(200) NOT NULL,\n",
"\t\"Composer\" NVARCHAR(220),\n",
"\tPRIMARY KEY (\"TrackId\")\n",
")\n",
"\n",
"SELECT * FROM 'Track' LIMIT 3;\n",
"TrackId\tName\tComposer\n",
"1\tFor Those About To Rock (We Salute You)\tAngus Young, Malcolm Young, Brian Johnson\n",
"2\tBalls to the Wall\tNone\n",
"3\tMy favorite song ever\tThe coolest composer of all time\"\"\"\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "db144352",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"CREATE TABLE \"Playlist\" (\n",
"\t\"PlaylistId\" INTEGER NOT NULL, \n",
"\t\"Name\" NVARCHAR(120), \n",
"\tPRIMARY KEY (\"PlaylistId\")\n",
")\n",
"\n",
"SELECT * FROM 'Playlist' LIMIT 2;\n",
"PlaylistId\tName\n",
"1\tMusic\n",
"2\tMovies\n",
"\n",
"CREATE TABLE Track (\n",
"\t\"TrackId\" INTEGER NOT NULL, \n",
"\t\"Name\" NVARCHAR(200) NOT NULL,\n",
"\t\"Composer\" NVARCHAR(220),\n",
"\tPRIMARY KEY (\"TrackId\")\n",
")\n",
"\n",
"SELECT * FROM 'Track' LIMIT 3;\n",
"TrackId\tName\tComposer\n",
"1\tFor Those About To Rock (We Salute You)\tAngus Young, Malcolm Young, Brian Johnson\n",
"2\tBalls to the Wall\tNone\n",
"3\tMy favorite song ever\tThe coolest composer of all time\n"
]
}
],
"source": [
"db = SQLDatabase.from_uri(\n",
" \"sqlite:///../../../../notebooks/Chinook.db\",\n",
" include_tables=['Track', 'Playlist'],\n",
" sample_rows_in_table_info=2,\n",
" custom_table_info=custom_table_info)\n",
"\n",
"print(db.table_info)"
]
},
{
"cell_type": "markdown",
"id": "5fc6f507",
"metadata": {},
"source": [
"Note how our custom table definition and sample rows for `Track` overrides the `sample_rows_in_table_info` parameter. Tables that are not overriden by `custom_table_info`, in this example `Playlist`, will have their table info gathered automatically as usual."
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "dfbda4e6",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
"What are some example tracks by Bach? \n",
"SQLQuery:\u001b[32;1m\u001b[1;3m SELECT Name, Composer FROM Track WHERE Composer LIKE '%Bach%' LIMIT 5;\u001b[0m\n",
"SQLResult: \u001b[33;1m\u001b[1;3m[('American Woman', 'B. Cummings/G. Peterson/M.J. Kale/R. Bachman'), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Johann Sebastian Bach'), ('Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria', 'Johann Sebastian Bach'), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', 'Johann Sebastian Bach'), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata', 'Johann Sebastian Bach')]\u001b[0m\n",
"Answer:\u001b[32;1m\u001b[1;3m Some example tracks by Bach are 'American Woman', 'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria', 'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', and 'Toccata and Fugue in D Minor, BWV 565: I. Toccata'.\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' Some example tracks by Bach are \\'American Woman\\', \\'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\\', \\'Aria Mit 30 Veränderungen, BWV 988 \"Goldberg Variations\": Aria\\', \\'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\\', and \\'Toccata and Fugue in D Minor, BWV 565: I. Toccata\\'.'"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)\n",
"db_chain.run(\"What are some example tracks by Bach?\")"
]
},
{
"cell_type": "markdown",
"id": "c12ae15a",
@ -542,7 +675,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
"version": "3.10.9"
}
},
"nbformat": 4,

View File

@ -34,10 +34,10 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"whats 2 raised to .12\u001b[32;1m\u001b[1;3m\n",
"Answer: 1.0791812460476249\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Entering new LLMMathChain chain...\u001B[0m\n",
"whats 2 raised to .12\u001B[32;1m\u001B[1;3m\n",
"Answer: 1.0791812460476249\u001B[0m\n",
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

View File

@ -42,13 +42,13 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mQuestion: What NFL team won the Super Bowl in the year Justin Beiber was born?\n",
"\u001B[32;1m\u001B[1;3mQuestion: What NFL team won the Super Bowl in the year Justin Beiber was born?\n",
"\n",
"Answer: Let's think step by step.\u001b[0m\n",
"Answer: Let's think step by step.\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n"
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n"
]
},
{
@ -95,11 +95,11 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mWrite a sad poem about ducks.\u001b[0m\n",
"\u001B[32;1m\u001B[1;3mWrite a sad poem about ducks.\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n"
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n"
]
},
{

View File

@ -136,13 +136,13 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mQuestion: whats 2 + 2\n",
"\u001B[32;1m\u001B[1;3mQuestion: whats 2 + 2\n",
"\n",
"Answer: Let's think step by step.\u001b[0m\n",
"Answer: Let's think step by step.\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -319,13 +319,13 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mQuestion: whats 2 + 2\n",
"\u001B[32;1m\u001B[1;3mQuestion: whats 2 + 2\n",
"\n",
"Answer: Let's think step by step.\u001b[0m\n",
"Answer: Let's think step by step.\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

View File

@ -9,13 +9,13 @@
"In this tutorial, we will learn about creating simple chains in LangChain. We will learn how to create a chain, add components to it, and run it.\n",
"\n",
"In this tutorial, we will cover:\n",
"- Using the simple LLM chain\n",
"- Using a simple LLM chain\n",
"- Creating sequential chains\n",
"- Creating a custom chain\n",
"\n",
"## Why do we need chains?\n",
"\n",
"Chains allow us to combine multiple components together to create a single, coherent application. For example, we can create a chain that takes user input, format it with a PromptTemplate, and then passes the formatted response to an LLM. We can build more complex chains by combining multiple chains together, or by combining chains with other components.\n"
"Chains allow us to combine multiple components together to create a single, coherent application. For example, we can create a chain that takes user input, formats it with a PromptTemplate, and then passes the formatted response to an LLM. We can build more complex chains by combining multiple chains together, or by combining chains with other components.\n"
]
},
{
@ -88,7 +88,7 @@
"source": [
"## Combine chains with the `SequentialChain`\n",
"\n",
"The next step after calling a language model is make a series of calls to a language model. We can do this using sequential chains, which are chains that execute their links in a predefined order. Specifically, we will use the `SimpleSequentialChain`. This is the simplest form of sequential chains, where each step has a singular input/output, and the output of one step is the input to the next.\n",
"The next step after calling a language model is to make a series of calls to a language model. We can do this using sequential chains, which are chains that execute their links in a predefined order. Specifically, we will use the `SimpleSequentialChain`. This is the simplest type of a sequential chain, where each step has a single input/output, and the output of one step is the input to the next.\n",
"\n",
"In this tutorial, our sequential chain will:\n",
"1. First, create a company name for a product. We will reuse the `LLMChain` we'd previously initialized to create this company name.\n",
@ -156,7 +156,7 @@
"source": [
"## Create a custom chain with the `Chain` class\n",
"\n",
"LangChain provides many chains out of the box, but sometimes you may want to create a custom chains for your specific use case. For this example, we will create a custom chain that concatenates the outputs of 2 `LLMChain`s.\n",
"LangChain provides many chains out of the box, but sometimes you may want to create a custom chain for your specific use case. For this example, we will create a custom chain that concatenates the outputs of 2 `LLMChain`s.\n",
"\n",
"In order to create a custom chain:\n",
"1. Start by subclassing the `Chain` class,\n",

File diff suppressed because one or more lines are too long

View File

@ -0,0 +1,145 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "f70e6118",
"metadata": {},
"source": [
"# Images\n",
"\n",
"This covers how to load images such as JPGs PNGs into a document format that we can use downstream."
]
},
{
"cell_type": "markdown",
"id": "09d64998",
"metadata": {},
"source": [
"## Using Unstructured"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "0cc0cd42",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders.image import UnstructuredImageLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "082d557c",
"metadata": {},
"outputs": [],
"source": [
"loader = UnstructuredImageLoader(\"layout-parser-paper-fast.jpg\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "df11c953",
"metadata": {},
"outputs": [],
"source": [
"data = loader.load()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "4284d44c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Document(page_content=\"LayoutParser: A Unified Toolkit for Deep\\nLearning Based Document Image Analysis\\n\\n\\nZxjiang Shen' (F3}, Ruochen Zhang”, Melissa Dell*, Benjamin Charles Germain\\nLeet, Jacob Carlson, and Weining LiF\\n\\n\\nsugehen\\n\\nshangthrows, et\\n\\n“Abstract. Recent advanocs in document image analysis (DIA) have been\\npimarliy driven bythe application of neural networks dell roar\\n{uteomer could be aly deployed in production and extended fo farther\\n[nvetigtion. However, various factory ke lcely organize codebanee\\nsnd sophisticated modal cnigurations compat the ey ree of\\nerin! innovation by wide sence, Though there have been sng\\nHors to improve reuablty and simplify deep lees (DL) mode\\naon, sone of them ae optimized for challenge inthe demain of DIA,\\nThis roprscte a major gap in the extng fol, sw DIA i eal to\\nscademic research acon wie range of dpi in the social ssencee\\n[rary for streamlining the sage of DL in DIA research and appicn\\ntons The core LayoutFaraer brary comes with a sch of simple and\\nIntative interfaee or applying and eutomiing DI. odel fr Inyo de\\npltfom for sharing both protrined modes an fal document dist\\n{ation pipeline We demonutate that LayootPareer shea fr both\\nlightweight and lrgeseledgtieation pipelines in eal-word uae ces\\nThe leary pblely smal at Btspe://layost-pareergsthab So\\n\\n\\n\\nKeywords: Document Image Analysis» Deep Learning Layout Analysis\\nCharacter Renguition - Open Serres dary « Tol\\n\\n\\nIntroduction\\n\\n\\nDeep Learning(DL)-based approaches are the state-of-the-art for a wide range of\\ndoctiment image analysis (DIA) tea including document image clasiffeation [I]\\n\", lookup_str='', metadata={'source': 'layout-parser-paper-fast.jpg'}, lookup_index=0)"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data[0]"
]
},
{
"cell_type": "markdown",
"id": "09957371",
"metadata": {},
"source": [
"### Retain Elements\n",
"\n",
"Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "0fab833b",
"metadata": {},
"outputs": [],
"source": [
"loader = UnstructuredImageLoader(\"layout-parser-paper-fast.jpg\", mode=\"elements\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "c3e8ff1b",
"metadata": {},
"outputs": [],
"source": [
"data = loader.load()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "43c23d2d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Document(page_content='LayoutParser: A Unified Toolkit for Deep\\nLearning Based Document Image Analysis\\n', lookup_str='', metadata={'source': 'layout-parser-paper-fast.jpg', 'filename': 'layout-parser-paper-fast.jpg', 'page_number': 1, 'category': 'Title'}, lookup_index=0)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data[0]"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@ -59,6 +59,8 @@ There are a lot of different document loaders that LangChain supports. Below are
`CoNLL-U <./examples/CoNLL-U.html>`_: A walkthrough of how to load data from a ConLL-U file.
`iFixit <./examples/ifixit.html>`_: A walkthrough of how to search and load data like guides, technical Q&A's, and device wikis from iFixit.com
.. toctree::
:maxdepth: 1
:glob:

View File

@ -178,16 +178,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new GraphQAChain chain...\u001b[0m\n",
"\u001B[1m> Entering new GraphQAChain chain...\u001B[0m\n",
"Entities Extracted:\n",
"\u001b[32;1m\u001b[1;3m Intel\u001b[0m\n",
"\u001B[32;1m\u001B[1;3m Intel\u001B[0m\n",
"Full Context:\n",
"\u001b[32;1m\u001b[1;3mIntel is going to build $20 billion semiconductor \"mega site\"\n",
"\u001B[32;1m\u001B[1;3mIntel is going to build $20 billion semiconductor \"mega site\"\n",
"Intel is building state-of-the-art factories\n",
"Intel is creating 10,000 new good-paying jobs\n",
"Intel is helping build Silicon Valley\u001b[0m\n",
"Intel is helping build Silicon Valley\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

View File

@ -43,7 +43,7 @@
"metadata": {},
"source": [
"## Generic Recursive Text Splitting\n",
"This text splitter is the recommended one for generic text. It is parameterized by a list of characters. It tries to split on them in order until the chunks are small enough. The default list is `[\"\\n\\n\", \"\\n\", \" \", \"\"]`. This has the affect of trying to keep all paragraphs (and then sentences, and then words) together as long as possible, as those would generically seem to be the strongest semantically related pieces of text.\n",
"This text splitter is the recommended one for generic text. It is parameterized by a list of characters. It tries to split on them in order until the chunks are small enough. The default list is `[\"\\n\\n\", \"\\n\", \" \", \"\"]`. This has the effect of trying to keep all paragraphs (and then sentences, and then words) together as long as possible, as those would generically seem to be the strongest semantically related pieces of text.\n",
"\n",
"\n",
"1. How the text is split: by list of characters\n",

View File

@ -11,7 +11,7 @@
"source": [
"# VectorStores\n",
"\n",
"This notebook showcases basic functionality related to VectorStores. A key part of working with vectorstores is creating the vector to put in them, which is usually created via embeddings. Therefor, it is recommended that you familiarize yourself with the [embedding notebook](embeddings.ipynb) before diving into this.\n",
"This notebook showcases basic functionality related to VectorStores. A key part of working with vectorstores is creating the vector to put in them, which is usually created via embeddings. Therefore, it is recommended that you familiarize yourself with the [embedding notebook](embeddings.ipynb) before diving into this.\n",
"\n",
"This covers generic high level functionality related to all vector stores. For guides on specific vectorstores, please see the how-to guides [here](../how_to_guides.rst)"
]

View File

@ -1,7 +1,6 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "f6574496-b360-4ffa-9523-7fd34a590164",
"metadata": {},
@ -10,14 +9,14 @@
"\n",
"LangChain provides async support for LLMs by leveraging the [asyncio](https://docs.python.org/3/library/asyncio.html) library.\n",
"\n",
"Async support is particularly useful for calling multiple LLMs concurrently, as these calls are network-bound. Currently, only `OpenAI` and `PromptLayerOpenAI` is supported, but async support for other LLMs is on the roadmap.\n",
"Async support is particularly useful for calling multiple LLMs concurrently, as these calls are network-bound. Currently, only `OpenAI` `OpenAIChat`, and `PromptLayerOpenAI` are supported, but async support for other LLMs is on the roadmap.\n",
"\n",
"You can use the `agenerate` method to call an OpenAI LLM asynchronously."
]
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 1,
"id": "5e49e96c-0f88-466d-b3d3-ea0966bdf19e",
"metadata": {
"tags": []
@ -29,64 +28,66 @@
"text": [
"\n",
"\n",
"I'm doing well. How about you?\n",
"As an AI language model, I don't have feelings like humans, but I'm functioning properly. How may I assist you?\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"I'm an AI language model, so I don't have emotions, but I'm functioning properly. How may I assist you today?\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"As an AI language model, I do not have emotions like humans, but I'm functioning normally. How can I assist you today?\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"\n",
"I am doing quite well. How about you?\n",
"I am an AI language model, so I do not have feelings, but I am here to assist you. How may I help you today?\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"As an AI language model, I do not have feelings or emotions but I'm always ready to assist you. How may I assist you today?\n",
"\n",
"\n",
"I'm doing great, thank you! How about you?\n",
"As an AI language model, I don't have feelings, but I'm functioning normally. How may I assist you today?\n",
"\n",
"\n",
"I'm doing well, thanks for asking. How about you?\n",
"As an AI language model, I don't have feelings, but I'm functioning properly. Thank you. How may I assist you today?\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"As an AI language model, I don't have emotions, so I don't have a specific feeling or emotion. How can I assist you today?\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"\u001b[1mConcurrent executed in 1.93 seconds.\u001b[0m\n",
"As an AI language model, I do not have feelings or emotions. However, I am functioning as intended and ready to assist you with any queries you may have. How can I be of assistance today?\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"As an AI language model, I do not have feelings, but I am functioning well. Thank you for asking. How can I assist you today?\n",
"\u001b[1mConcurrent executed in 0.92 seconds.\u001b[0m\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"As an AI language model, I don't have feelings, but I'm functioning well. How can I assist you today?\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"As an AI language model, I don't have feelings, but I'm functioning well. Thank you for asking. How may I assist you today?\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"I'm an AI language model, so I don't have feelings, but I'm functioning well. How can I assist you today?\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"As an AI language model, I don't have feelings, but I'm functioning well. Thank you for asking. How may I assist you today?\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"As an AI language model, I don't have feelings, but I am functioning well. How can I assist you today?\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"As an AI language model, I don't have feelings but I'm functioning well. How can I assist you today?\n",
"\n",
"\n",
"I'm doing well, thank you. How about you?\n",
"As an AI language model, I do not have personal emotions. However, I am functioning well and ready to assist you with any queries or tasks you have. How may I assist you today?\n",
"\n",
"\n",
"I'm doing great, thank you. How about you?\n",
"\u001b[1mSerial executed in 10.54 seconds.\u001b[0m\n"
"As an AI language model, I do not have feelings or emotions, but I'm functioning well. How can I assist you today?\n",
"\n",
"\n",
"I am an AI language model and do not have feelings. But I am functioning properly and ready to assist you with any task. How may I help you today?\n",
"\n",
"\n",
"As an AI language model, I do not have emotions, but I am functioning well. How can I assist you today?\n",
"\u001b[1mSerial executed in 5.00 seconds.\u001b[0m\n"
]
}
],
@ -94,10 +95,10 @@
"import time\n",
"import asyncio\n",
"\n",
"from langchain.llms import OpenAI\n",
"from langchain.llms import OpenAIChat\n",
"\n",
"def generate_serially():\n",
" llm = OpenAI(temperature=0.9)\n",
" llm = OpenAIChat(temperature=0.9)\n",
" for _ in range(10):\n",
" resp = llm.generate([\"Hello, how are you?\"])\n",
" print(resp.generations[0][0].text)\n",
@ -109,7 +110,7 @@
"\n",
"\n",
"async def generate_concurrently():\n",
" llm = OpenAI(temperature=0.9)\n",
" llm = OpenAIChat(temperature=0.9)\n",
" tasks = [async_generate(llm) for _ in range(10)]\n",
" await asyncio.gather(*tasks)\n",
"\n",
@ -125,6 +126,14 @@
"elapsed = time.perf_counter() - s\n",
"print('\\033[1m' + f\"Serial executed in {elapsed:0.2f} seconds.\" + '\\033[0m')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e1d3a966-3a27-44e8-9441-ed72f01b86f4",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {

View File

@ -80,14 +80,14 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: Python REPL\n",
"Action Input: print(2 + 2)\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m4\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mFinal Answer: 4\u001b[0m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3mAction: Python REPL\n",
"Action Input: print(2 + 2)\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3m4\n",
"\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3mFinal Answer: 4\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

View File

@ -7,7 +7,7 @@
"source": [
"# LLM Serialization\n",
"\n",
"This notebook walks how to write and read an LLM Configuration to and from disk. This is useful if you want to save the configuration for a given LLM (eg the provider, the temperature, etc)."
"This notebook walks through how to write and read an LLM Configuration to and from disk. This is useful if you want to save the configuration for a given LLM (e.g., the provider, the temperature, etc)."
]
},
{

View File

@ -31,13 +31,13 @@ The examples here are all "how-to" guides for how to integrate with various LLM
`Forefront AI <./integrations/forefrontai_example.html>`_: Covers how to utilize the Forefront AI wrapper.
`PromptLayer OpenAI <./integrations/promptlayer_openai.html>`_: Covers how to use `PromptLayer <https://promptlayer.com>`_ with Langchain.
`PromptLayer OpenAI <./integrations/promptlayer_openai.html>`_: Covers how to use `PromptLayer <https://promptlayer.com>`_ with LangChain.
`Anthropic <./integrations/anthropic_example.html>`_: Covers how to use Anthropic models with Langchain.
`Anthropic <./integrations/anthropic_example.html>`_: Covers how to use Anthropic models with LangChain.
`DeepInfra <./integrations/deepinfra_example.html>`_: Covers how to utilize the DeepInfra wrapper.
`Self-Hosted Models (via Runhouse) <./integrations/self_hosted_examples.html>`_: Covers how to run models on existing or on-demand remote compute with Langchain.
`Self-Hosted Models (via Runhouse) <./integrations/self_hosted_examples.html>`_: Covers how to run models on existing or on-demand remote compute with LangChain.
.. toctree::

View File

@ -76,19 +76,11 @@
"\n",
"llm_chain.run(question)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4797d719",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.9.12 ('palm')",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@ -102,7 +94,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.12"
"version": "3.9.1"
},
"vscode": {
"interpreter": {

View File

@ -0,0 +1,245 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "e49f1e0d",
"metadata": {},
"source": [
"# OpenAIChat\n",
"\n",
"OpenAI also has a [chat model](https://platform.openai.com/docs/guides/chat) you can use. The interface is very similar to the normal OpenAI model."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "522686de",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAIChat\n",
"from langchain import PromptTemplate, LLMChain"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "62e0dbc3",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAIChat(temperature=0)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "fbb043e6",
"metadata": {},
"outputs": [],
"source": [
"template = \"\"\"Question: {question}\n",
"\n",
"Answer: Let's think step by step.\"\"\"\n",
"\n",
"prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "3f945b76",
"metadata": {},
"outputs": [],
"source": [
"llm_chain = LLMChain(prompt=prompt, llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "25260808",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'\\n\\nJustin Bieber was born on March 1, 1994. \\n\\nThe Super Bowl is played in February of each year. \\n\\nTherefore, the Super Bowl that was played in the year Justin Bieber was born was Super Bowl XXVIII, which was played on January 30, 1994. \\n\\nThe Dallas Cowboys won Super Bowl XXVIII by defeating the Buffalo Bills with a score of 30-13.'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
"\n",
"llm_chain.run(question)"
]
},
{
"cell_type": "markdown",
"id": "75a05b79",
"metadata": {},
"source": [
"## Prefix Messages\n",
"\n",
"OpenAI Chat also supports the idea of [prefix messages](https://platform.openai.com/docs/guides/chat/chat-vs-completions), eg messages that would appear before the user input. These can be used as system messages to give more context/purpose the LLM."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "c27a1501",
"metadata": {},
"outputs": [],
"source": [
"prefix_messages = [{\"role\": \"system\", \"content\": \"You are a helpful assistant that is very good at problem solving who thinks step by step.\"}]"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "e46a914e",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAIChat(temperature=0, prefix_messages=prefix_messages)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "d683d9f2",
"metadata": {},
"outputs": [],
"source": [
"llm_chain = LLMChain(prompt=prompt, llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "6f5b8e78",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Step 1: Justin Bieber was born on March 1, 1994.\\nStep 2: The Super Bowl is played in February of each year.\\nStep 3: Therefore, the Super Bowl that was played in the year Justin Bieber was born was Super Bowl XXVIII, which was played on January 30, 1994.\\nStep 4: The team that won Super Bowl XXVIII was the Dallas Cowboys.'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
"\n",
"llm_chain.run(question)"
]
},
{
"cell_type": "markdown",
"id": "f6d5dda8",
"metadata": {},
"source": [
"## Async"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "1973b9bb",
"metadata": {},
"outputs": [],
"source": [
"result = await llm_chain.arun(question)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "5815178f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Step 1: Justin Bieber was born on March 1, 1994.\\nStep 2: The Super Bowl is played in February of each year.\\nStep 3: Therefore, the Super Bowl that was played in the year Justin Bieber was born was Super Bowl XXVIII, which was played on January 30, 1994.\\nStep 4: The team that won Super Bowl XXVIII was the Dallas Cowboys.'"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"result"
]
},
{
"cell_type": "markdown",
"id": "eb779f3f",
"metadata": {},
"source": [
"## Streaming"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "509181be",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"Justin Bieber was born on March 1, 1994. The NFL team that won the Super Bowl in the same year was the Dallas Cowboys. They defeated the Buffalo Bills 30-13 in Super Bowl XXVIII on January 30, 1994."
]
}
],
"source": [
"\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
"llm = OpenAIChat(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
"resp = llm(question)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c095285d",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@ -2,9 +2,9 @@
## LLMs
Wrappers around Large Language Models (in particular, the "generate" ability of large language models) are at the core of LangChain functionality.
The core method that these classes expose is a `generate` method, which takes in a list of strings and returns an LLMResult (which contains outputs for all input strings).
Read more about LLMResult. This interface operates over a list of strings because often the lists of strings can be batched to the LLM provider,
providing speed and efficiency gains.
The core method that these classes expose is a `generate` method, which takes in a list of strings and returns an LLMResult (which contains outputs for all input strings). Read more about [LLMResult](#llmresult).
This interface operates over a list of strings because often the lists of strings can be batched to the LLM provider, providing speed and efficiency gains.
For convenience, this class also exposes a simpler, more user friendly interface (via `__call__`).
The interface for this takes in a single string, and returns a single string.

View File

@ -7,12 +7,12 @@
"source": [
"# Streaming with LLMs\n",
"\n",
"LangChain provides streaming support for LLMs. Currently, we only support streaming for the `OpenAI` LLM implementation, but streaming support for other LLM implementations is on the roadmap. To utilize streaming, use a [`CallbackHandler`](https://github.com/hwchase17/langchain/blob/master/langchain/callbacks/base.py) that implements `on_llm_new_token`. In this example, we are using [`StreamingStdOutCallbackHandler`]()."
"LangChain provides streaming support for LLMs. Currently, we only support streaming for the `OpenAI` and `OpenAIChat` LLM implementation, but streaming support for other LLM implementations is on the roadmap. To utilize streaming, use a [`CallbackHandler`](https://github.com/hwchase17/langchain/blob/master/langchain/callbacks/base.py) that implements `on_llm_new_token`. In this example, we are using [`StreamingStdOutCallbackHandler`]()."
]
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 2,
"id": "4ac0ff54-540a-4f2b-8d9a-b590fec7fe07",
"metadata": {
"tags": []
@ -27,43 +27,43 @@
"Verse 1\n",
"I'm sippin' on sparkling water,\n",
"It's so refreshing and light,\n",
"It's the perfect way to quench my thirst,\n",
"It's the perfect way to quench my thirst\n",
"On a hot summer night.\n",
"\n",
"Chorus\n",
"Sparkling water, sparkling water,\n",
"It's the best way to stay hydrated,\n",
"It's so refreshing and light,\n",
"It's the perfect way to stay alive.\n",
"It's so crisp and so clean,\n",
"It's the perfect way to stay refreshed.\n",
"\n",
"Verse 2\n",
"I'm sippin' on sparkling water,\n",
"It's so bubbly and bright,\n",
"It's the perfect way to cool me down,\n",
"It's the perfect way to cool me down\n",
"On a hot summer night.\n",
"\n",
"Chorus\n",
"Sparkling water, sparkling water,\n",
"It's the best way to stay hydrated,\n",
"It's so refreshing and light,\n",
"It's the perfect way to stay alive.\n",
"It's so crisp and so clean,\n",
"It's the perfect way to stay refreshed.\n",
"\n",
"Verse 3\n",
"I'm sippin' on sparkling water,\n",
"It's so crisp and clean,\n",
"It's the perfect way to keep me going,\n",
"On a hot summer day.\n",
"It's so light and so clear,\n",
"It's the perfect way to keep me cool\n",
"On a hot summer night.\n",
"\n",
"Chorus\n",
"Sparkling water, sparkling water,\n",
"It's the best way to stay hydrated,\n",
"It's so refreshing and light,\n",
"It's the perfect way to stay alive."
"It's so crisp and so clean,\n",
"It's the perfect way to stay refreshed."
]
}
],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.llms import OpenAI, OpenAIChat\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
"\n",
@ -84,7 +84,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 3,
"id": "a35373f1-9ee6-4753-a343-5aee749b8527",
"metadata": {
"tags": []
@ -103,10 +103,10 @@
{
"data": {
"text/plain": [
"LLMResult(generations=[[Generation(text='\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', generation_info={'finish_reason': 'stop', 'logprobs': None})]], llm_output={'token_usage': {}})"
"LLMResult(generations=[[Generation(text='\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', generation_info={'finish_reason': None, 'logprobs': None})]], llm_output={'token_usage': {}})"
]
},
"execution_count": 8,
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
@ -114,6 +114,85 @@
"source": [
"llm.generate([\"Tell me a joke.\"])"
]
},
{
"cell_type": "markdown",
"id": "a93a4d61-0476-49db-8321-7de92bd74059",
"metadata": {},
"source": [
"Here's an example with `OpenAIChat`:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "22665f16-e05b-473c-a4bd-ad75744ea024",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"Verse 1:\n",
"Bubbles rising to the top\n",
"A refreshing drink that never stops\n",
"Clear and crisp, it's pure delight\n",
"A taste that's sure to excite\n",
"\n",
"Chorus:\n",
"Sparkling water, oh so fine\n",
"A drink that's always on my mind\n",
"With every sip, I feel alive\n",
"Sparkling water, you're my vibe\n",
"\n",
"Verse 2:\n",
"No sugar, no calories, just pure bliss\n",
"A drink that's hard to resist\n",
"It's the perfect way to quench my thirst\n",
"A drink that always comes first\n",
"\n",
"Chorus:\n",
"Sparkling water, oh so fine\n",
"A drink that's always on my mind\n",
"With every sip, I feel alive\n",
"Sparkling water, you're my vibe\n",
"\n",
"Bridge:\n",
"From the mountains to the sea\n",
"Sparkling water, you're the key\n",
"To a healthy life, a happy soul\n",
"A drink that makes me feel whole\n",
"\n",
"Chorus:\n",
"Sparkling water, oh so fine\n",
"A drink that's always on my mind\n",
"With every sip, I feel alive\n",
"Sparkling water, you're my vibe\n",
"\n",
"Outro:\n",
"Sparkling water, you're the one\n",
"A drink that's always so much fun\n",
"I'll never let you go, my friend\n",
"Sparkling water, until the end."
]
}
],
"source": [
"llm = OpenAIChat(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
"resp = llm(\"Write me a song about sparkling water.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "eadae4ba-9f21-4ec8-845d-dd43b0edc2dc",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {

View File

@ -24,9 +24,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -36,9 +36,9 @@
"\n",
"\n",
"Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"```\n",
"$ pwd\n",
@ -93,9 +93,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -110,9 +110,9 @@
"/\n",
"```\n",
"Human: ls ~\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"```\n",
"$ ls ~\n",
@ -138,9 +138,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -161,9 +161,9 @@
"Desktop Documents Downloads Music Pictures Public Templates Videos\n",
"```\n",
"Human: cd ~\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
" \n",
"```\n",
"$ cd ~\n",
@ -190,9 +190,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -214,9 +214,9 @@
"/home/user\n",
"```\n",
"Human: {Please make a file jokes.txt inside and put some jokes inside}\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -245,9 +245,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -272,9 +272,9 @@
"$ echo \"Why did the scarecrow win the Nobel Prize? Because he was outstanding in his field!\" >> jokes.txt\n",
"```\n",
"Human: echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py && python3 run.py\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -304,9 +304,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -332,9 +332,9 @@
"Result: 33\n",
"```\n",
"Human: echo -e \"print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])\" > run.py && python3 run.py\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -362,9 +362,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -391,9 +391,9 @@
"Human: echo -e \"echo 'Hello from Docker\" > entrypoint.sh && echo -e \"FROM ubuntu:20.04\n",
"COPY entrypoint.sh entrypoint.sh\n",
"ENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]\">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -426,9 +426,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -459,9 +459,9 @@
"Hello from Docker\n",
"```\n",
"Human: nvidia-smi\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -502,9 +502,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -548,9 +548,9 @@
"|=============================================================================|\n",
"\n",
"Human: ping bbc.com\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -584,9 +584,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -630,9 +630,9 @@
"round-trip min/avg/max/stddev = 14.945/14.945/14.945/0.000 ms\n",
"```\n",
"Human: curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -659,9 +659,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -691,9 +691,9 @@
"1.8.1\n",
"```\n",
"Human: lynx https://www.deepmind.com/careers\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -726,9 +726,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -757,9 +757,9 @@
"Explore our current openings and apply today. We look forward to hearing from you.\n",
"```\n",
"Human: curl https://chat.openai.com/chat\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
" \n",
"\n",
"```\n",
@ -799,9 +799,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -843,9 +843,9 @@
"</html>\n",
"```\n",
"Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"What is artificial intelligence?\"}' https://chat.openai.com/chat\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -875,9 +875,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -916,9 +916,9 @@
"}\n",
"```\n",
"Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\"}' https://chat.openai.com/chat\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
" \n",
"\n",
"```\n",

View File

@ -76,12 +76,12 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"Thought: Do I need to use a tool? No\n",
"AI: Hi Bob, nice to meet you! How can I help you today?\u001b[0m\n",
"AI: Hi Bob, nice to meet you! How can I help you today?\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -111,12 +111,12 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"Thought: Do I need to use a tool? No\n",
"AI: Your name is Bob!\u001b[0m\n",
"AI: Your name is Bob!\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -146,12 +146,12 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"Thought: Do I need to use a tool? No\n",
"AI: If you like Thai food, some great dinner options this week could include Thai green curry, Pad Thai, or a Thai-style stir-fry. You could also try making a Thai-style soup or salad. Enjoy!\u001b[0m\n",
"AI: If you like Thai food, some great dinner options this week could include Thai green curry, Pad Thai, or a Thai-style stir-fry. You could also try making a Thai-style soup or salad. Enjoy!\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -181,16 +181,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"Thought: Do I need to use a tool? Yes\n",
"Action: Current Search\n",
"Action Input: Who won the World Cup in 1978\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mThe Cup was won by the host nation, Argentina, who defeated the Netherlands 31 in the final, after extra time. The final was held at River Plate's home stadium ... Amid Argentina's celebrations, there was sympathy for the Netherlands, runners-up for the second tournament running, following a 3-1 final defeat at the Estadio ... The match was won by the Argentine squad in extra time by a score of 31. Mario Kempes, who finished as the tournament's top scorer, was named the man of the ... May 21, 2022 ... Argentina won the World Cup for the first time in their history, beating Netherlands 3-1 in the final. This edition of the World Cup was full of ... The adidas Golden Ball is presented to the best player at each FIFA World Cup finals. Those who finish as runners-up in the vote receive the adidas Silver ... Holders West Germany failed to beat Holland and Italy and were eliminated when Berti Vogts' own goal gave Austria a 3-2 victory. Holland thrashed the Austrians ... Jun 14, 2018 ... On a clear afternoon on 1 June 1978 at the revamped El Monumental stadium in Buenos Aires' Belgrano barrio, several hundred children in white ... Dec 15, 2022 ... The tournament couldn't have gone better for the ruling junta. Argentina went on to win the championship, defeating the Netherlands, 3-1, in the ... Nov 9, 2022 ... Host: Argentina Teams: 16. Format: Group stage, second round, third-place playoff, final. Matches: 38. Goals: 102. Winner: Argentina Feb 19, 2009 ... Argentina sealed their first World Cup win on home soil when they defeated the Netherlands in an exciting final that went to extra-time. For the ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
"AI: The last letter in your name is 'b'. Argentina won the World Cup in 1978.\u001b[0m\n",
"Action Input: Who won the World Cup in 1978\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3mThe Cup was won by the host nation, Argentina, who defeated the Netherlands 31 in the final, after extra time. The final was held at River Plate's home stadium ... Amid Argentina's celebrations, there was sympathy for the Netherlands, runners-up for the second tournament running, following a 3-1 final defeat at the Estadio ... The match was won by the Argentine squad in extra time by a score of 31. Mario Kempes, who finished as the tournament's top scorer, was named the man of the ... May 21, 2022 ... Argentina won the World Cup for the first time in their history, beating Netherlands 3-1 in the final. This edition of the World Cup was full of ... The adidas Golden Ball is presented to the best player at each FIFA World Cup finals. Those who finish as runners-up in the vote receive the adidas Silver ... Holders West Germany failed to beat Holland and Italy and were eliminated when Berti Vogts' own goal gave Austria a 3-2 victory. Holland thrashed the Austrians ... Jun 14, 2018 ... On a clear afternoon on 1 June 1978 at the revamped El Monumental stadium in Buenos Aires' Belgrano barrio, several hundred children in white ... Dec 15, 2022 ... The tournament couldn't have gone better for the ruling junta. Argentina went on to win the championship, defeating the Netherlands, 3-1, in the ... Nov 9, 2022 ... Host: Argentina Teams: 16. Format: Group stage, second round, third-place playoff, final. Matches: 38. Goals: 102. Winner: Argentina Feb 19, 2009 ... Argentina sealed their first World Cup win on home soil when they defeated the Netherlands in an exciting final that went to extra-time. For the ...\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m Do I need to use a tool? No\n",
"AI: The last letter in your name is 'b'. Argentina won the World Cup in 1978.\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -220,16 +220,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"Thought: Do I need to use a tool? Yes\n",
"Action: Current Search\n",
"Action Input: Current temperature in Pomfret\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mA mixture of rain and snow showers. High 39F. Winds NNW at 5 to 10 mph. Chance of precip 50%. Snow accumulations less than one inch. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Pomfret Center Weather Forecasts. ... Pomfret Center, CT Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be COOLER than today. It is 46 degrees fahrenheit, or 8 degrees celsius and feels like 46 degrees fahrenheit. The barometric pressure is 29.78 - measured by inch of mercury units - ... Pomfret Weather Forecasts. ... Pomfret, MD Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be MUCH COOLER than today. Additional Headlines. En Español · Share |. Current conditions at ... Pomfret CT. Tonight ... Past Weather Information · Interactive Forecast Map. Pomfret MD detailed current weather report for 20675 in Charles county, Maryland. ... Pomfret, MD weather condition is Mostly Cloudy and 43°F. Mostly Cloudy. Hazardous Weather Conditions. Hazardous Weather Outlook · En Español · Share |. Current conditions at ... South Pomfret VT. Tonight. Pomfret Center, CT Weather. Current Report for Thu Jan 5 2023. As of 2:00 PM EST. 5-Day Forecast | Road Conditions. 45°F 7°c. Feels Like 44°F. Pomfret Center CT. Today. Today: Areas of fog before 9am. Otherwise, cloudy, with a ... Otherwise, cloudy, with a temperature falling to around 33 by 5pm.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
"AI: The current temperature in Pomfret is 45°F (7°C) and it feels like 44°F.\u001b[0m\n",
"Action Input: Current temperature in Pomfret\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3mA mixture of rain and snow showers. High 39F. Winds NNW at 5 to 10 mph. Chance of precip 50%. Snow accumulations less than one inch. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Pomfret Center Weather Forecasts. ... Pomfret Center, CT Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be COOLER than today. It is 46 degrees fahrenheit, or 8 degrees celsius and feels like 46 degrees fahrenheit. The barometric pressure is 29.78 - measured by inch of mercury units - ... Pomfret Weather Forecasts. ... Pomfret, MD Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be MUCH COOLER than today. Additional Headlines. En Español · Share |. Current conditions at ... Pomfret CT. Tonight ... Past Weather Information · Interactive Forecast Map. Pomfret MD detailed current weather report for 20675 in Charles county, Maryland. ... Pomfret, MD weather condition is Mostly Cloudy and 43°F. Mostly Cloudy. Hazardous Weather Conditions. Hazardous Weather Outlook · En Español · Share |. Current conditions at ... South Pomfret VT. Tonight. Pomfret Center, CT Weather. Current Report for Thu Jan 5 2023. As of 2:00 PM EST. 5-Day Forecast | Road Conditions. 45°F 7°c. Feels Like 44°F. Pomfret Center CT. Today. Today: Areas of fog before 9am. Otherwise, cloudy, with a ... Otherwise, cloudy, with a temperature falling to around 33 by 5pm.\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m Do I need to use a tool? No\n",
"AI: The current temperature in Pomfret is 45°F (7°C) and it feels like 44°F.\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

View File

@ -51,16 +51,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi there!\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -90,18 +90,18 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi there!\n",
"AI: Hi there! It's nice to meet you. How can I help you today?\n",
"Human: I'm doing well! Just having a conversation with an AI.\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -131,9 +131,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
@ -142,9 +142,9 @@
"Human: I'm doing well! Just having a conversation with an AI.\n",
"AI: That's great! It's always nice to have a conversation with someone new. What would you like to talk about?\n",
"Human: Tell me about yourself.\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -195,16 +195,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi, what's up?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -239,17 +239,17 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"The human greets the AI and the AI responds, saying it is doing well and is currently helping a customer with a technical issue.\n",
"Human: Tell me more about it!\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -279,18 +279,18 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"\n",
"The human greets the AI and the AI responds, saying it is doing well and is currently helping a customer with a technical issue. The customer is having trouble with their computer not connecting to the internet, and the AI is helping them troubleshoot the issue by resetting the router and checking the network settings. They are still looking into other possible causes.\n",
"Human: Very cool -- what is the scope of the project?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -342,16 +342,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi, what's up?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -387,17 +387,17 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"Human: Hi, what's up?\n",
"AI: Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?\n",
"Human: What's their issues?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -427,9 +427,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"Human: Hi, what's up?\n",
@ -437,9 +437,9 @@
"Human: What's their issues?\n",
"AI: The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected.\n",
"Human: Is it going well?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -469,9 +469,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"Human: What's their issues?\n",
@ -479,9 +479,9 @@
"Human: Is it going well?\n",
"AI: Yes, it's going well so far. We've already identified the problem and are now working on a solution.\n",
"Human: What's the solution?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -534,16 +534,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi, what's up?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -579,17 +579,17 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"Human: Hi, what's up?\n",
"AI: Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?\n",
"Human: Just working on writing some documentation!\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -619,9 +619,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
@ -629,9 +629,9 @@
"Human: Just working on writing some documentation!\n",
"AI: That sounds like a lot of work. What kind of documentation are you writing?\n",
"Human: For LangChain! Have you heard of it?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -662,18 +662,18 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"The human asked the AI what it was up to, and the AI responded that it was helping a customer with a technical issue. The human then mentioned they were writing documentation for LangChain, a blockchain-based language learning platform, and the AI revealed they had heard of it and asked the human to tell them more about the documentation they were writing.\n",
"\n",
"Human: Haha nope, although a lot of people confuse it for that\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -755,9 +755,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
@ -766,9 +766,9 @@
"\n",
"Conversation:\n",
"Human: Hi, what's up?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -798,9 +798,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
@ -809,9 +809,9 @@
"\n",
"Conversation:\n",
"Human: My name is James and I'm helping Will. He's an engineer.\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -841,9 +841,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
@ -852,9 +852,9 @@
"\n",
"Conversation:\n",
"Human: What do you know about Will?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

View File

@ -1,6 +1,6 @@
# Create a custom example selector
In this tutorial, we'll create a custom example selector that selects examples every alternate example given a list of examples.
In this tutorial, we'll create a custom example selector that selects every alternate example from a given list of examples.
An `ExampleSelector` must implement two methods:
@ -65,4 +65,4 @@ example_selector.examples
# Select examples
example_selector.select_examples({"foo": "foo"})
# -> array([{'foo': '1'}, {'foo': '4'}], dtype=object)
```
```

View File

@ -1,4 +1,5 @@
{
"_type": "prompt",
"input_variables": ["input", "output"],
"template": "Input: {input}\nOutput: {output}"
}

View File

@ -3,6 +3,7 @@
"input_variables": ["adjective"],
"prefix": "Write antonyms for the following words.",
"example_prompt": {
"_type": "prompt",
"input_variables": ["input", "output"],
"template": "Input: {input}\nOutput: {output}"
},

View File

@ -4,6 +4,7 @@ input_variables:
prefix:
Write antonyms for the following words.
example_prompt:
_type: prompt
input_variables:
["input", "output"]
template:

View File

@ -3,6 +3,7 @@
"input_variables": ["adjective"],
"prefix": "Write antonyms for the following words.",
"example_prompt": {
"_type": "prompt",
"input_variables": ["input", "output"],
"template": "Input: {input}\nOutput: {output}"
},

View File

@ -4,6 +4,7 @@ input_variables:
prefix:
Write antonyms for the following words.
example_prompt:
_type: prompt
input_variables:
["input", "output"]
template:

View File

@ -0,0 +1,184 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "9355a547",
"metadata": {},
"source": [
"# Partial Prompt Templates\n",
"\n",
"A prompt template is a class with a `.format` method which takes in a key-value map and returns a string (a prompt) to pass to the language model. Like other methods, it can make sense to \"partial\" a prompt template - eg pass in a subset of the required values, as to create a new prompt template which expects only the remaining subset of values.\n",
"\n",
"LangChain supports this in two ways: we allow for partially formatted prompts (1) with string values, (2) with functions that return string values. These two different ways support different use cases. In the documentation below we go over the motivations for both use cases as well as how to do it in LangChain.\n",
"\n",
"## Partial With Strings\n",
"\n",
"One common use case for wanting to partial a prompt template is if you get some of the variables before others. For example, suppose you have a prompt template that requires two variables, `foo` and `baz`. If you get the `foo` value early on in the chain, but the `baz` value later, it can be annoying to wait until you have both variables in the same place to pass them to the prompt template. Instead, you can partial the prompt template with the `foo` value, and then pass the partialed prompt template along and just use that. Below is an example of doing this:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "643af5da",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import PromptTemplate"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "4080d8d7",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"foobaz\n"
]
}
],
"source": [
"prompt = PromptTemplate(template=\"{foo}{bar}\", input_variables=[\"foo\", \"bar\"])\n",
"partial_prompt = prompt.partial(foo=\"foo\");\n",
"print(partial_prompt.format(bar=\"baz\"))"
]
},
{
"cell_type": "markdown",
"id": "9986766e",
"metadata": {},
"source": [
"You can also just initialize the prompt with the partialed variables."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "e2ce95b3",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"foobaz\n"
]
}
],
"source": [
"prompt = PromptTemplate(template=\"{foo}{bar}\", input_variables=[\"bar\"], partial_variables={\"foo\": \"foo\"})\n",
"print(prompt.format(bar=\"baz\"))"
]
},
{
"cell_type": "markdown",
"id": "a9c66f83",
"metadata": {},
"source": [
"## Partial With Functions\n",
"\n",
"The other common use is to partial with a function. The use case for this is when you have a variable you know that you always want to fetch in a common way. A prime example of this is with date or time. Imagine you have a prompt which you always want to have the current date. You can't hard code it in the prompt, and passing it along with the other input variables is a bit annoying. In this case, it's very handy to be able to partial the prompt with a function that always returns the current date."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "d0712d8a",
"metadata": {},
"outputs": [],
"source": [
"from datetime import datetime\n",
"\n",
"def _get_datetime():\n",
" now = datetime.now()\n",
" return now.strftime(\"%m/%d/%Y, %H:%M:%S\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "4cbcb666",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tell me a funny joke about the day 02/27/2023, 22:15:16\n"
]
}
],
"source": [
"prompt = PromptTemplate(\n",
" template=\"Tell me a {adjective} joke about the day {date}\", \n",
" input_variables=[\"adjective\", \"date\"]\n",
");\n",
"partial_prompt = prompt.partial(date=_get_datetime)\n",
"print(partial_prompt.format(adjective=\"funny\"))"
]
},
{
"cell_type": "markdown",
"id": "ffed6811",
"metadata": {},
"source": [
"You can also just initialize the prompt with the partialed variables, which often makes more sense in this workflow."
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "96285b25",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tell me a funny joke about the day 02/27/2023, 22:15:16\n"
]
}
],
"source": [
"prompt = PromptTemplate(\n",
" template=\"Tell me a {adjective} joke about the day {date}\", \n",
" input_variables=[\"adjective\"],\n",
" partial_variables={\"date\": _get_datetime}\n",
");\n",
"print(prompt.format(adjective=\"funny\"))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4bff16f7",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

View File

@ -58,6 +58,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"_type: prompt\r\n",
"input_variables:\r\n",
" [\"adjective\", \"content\"]\r\n",
"template: \r\n",
@ -108,6 +109,7 @@
"output_type": "stream",
"text": [
"{\r\n",
" \"_type\": \"prompt\",\r\n",
" \"input_variables\": [\"adjective\", \"content\"],\r\n",
" \"template\": \"Tell me a {adjective} joke about {content}.\"\r\n",
"}\r\n"
@ -156,6 +158,7 @@
"output_type": "stream",
"text": [
"{\r\n",
" \"_type\": \"prompt\",\r\n",
" \"input_variables\": [\"adjective\", \"content\"],\r\n",
" \"template_path\": \"simple_template.txt\"\r\n",
"}\r\n"
@ -279,6 +282,7 @@
"prefix: \r\n",
" Write antonyms for the following words.\r\n",
"example_prompt:\r\n",
" _type: prompt\r\n",
" input_variables:\r\n",
" [\"input\", \"output\"]\r\n",
" template:\r\n",
@ -346,6 +350,7 @@
"prefix: \r\n",
" Write antonyms for the following words.\r\n",
"example_prompt:\r\n",
" _type: prompt\r\n",
" input_variables:\r\n",
" [\"input\", \"output\"]\r\n",
" template:\r\n",
@ -413,6 +418,7 @@
" \"input_variables\": [\"adjective\"],\r\n",
" \"prefix\": \"Write antonyms for the following words.\",\r\n",
" \"example_prompt\": {\r\n",
" \"_type\": \"prompt\",\r\n",
" \"input_variables\": [\"input\", \"output\"],\r\n",
" \"template\": \"Input: {input}\\nOutput: {output}\"\r\n",
" },\r\n",
@ -478,6 +484,7 @@
" \"input_variables\": [\"adjective\"],\r\n",
" \"prefix\": \"Write antonyms for the following words.\",\r\n",
" \"example_prompt\": {\r\n",
" \"_type\": \"prompt\",\r\n",
" \"input_variables\": [\"input\", \"output\"],\r\n",
" \"template\": \"Input: {input}\\nOutput: {output}\"\r\n",
" },\r\n",
@ -542,6 +549,7 @@
"output_type": "stream",
"text": [
"{\r\n",
" \"_type\": \"prompt\",\r\n",
" \"input_variables\": [\"input\", \"output\"],\r\n",
" \"template\": \"Input: {input}\\nOutput: {output}\" \r\n",
"}\r\n"
@ -622,7 +630,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.11.2"
},
"vscode": {
"interpreter": {

View File

@ -1,4 +1,5 @@
{
"_type": "prompt",
"input_variables": ["adjective", "content"],
"template": "Tell me a {adjective} joke about {content}."
}

View File

@ -1,3 +1,4 @@
_type: prompt
input_variables:
["adjective", "content"]
template:

View File

@ -1,4 +1,5 @@
{
"_type": "prompt",
"input_variables": ["adjective", "content"],
"template_path": "simple_template.txt"
}

View File

@ -8,7 +8,7 @@ In this tutorial, we will learn about:
## What is a prompt template?
A prompt template refers to a reproducible way to generate a prompt. It contains a text string ("the template"), that can can take in a set of parameters from the end user and generate a prompt.
A prompt template refers to a reproducible way to generate a prompt. It contains a text string ("the template"), that can take in a set of parameters from the end user and generate a prompt.
The prompt template may contain:
- instructions to the language model,

View File

@ -17,6 +17,8 @@ The user guide here shows more advanced workflows and how to use the library in
`Few Shot Prompt Examples <./examples/few_shot_examples.html>`_: Examples of Few Shot Prompt Templates.
`Partial Prompt Template <./examples/partial.html>`_: How to partial Prompt Templates.
.. toctree::

View File

@ -62,7 +62,7 @@ To learn more about how to provide few shot examples, see [Few Shot Examples](ex
If there are multiple examples that are relevant to a prompt, it is important to select the most relevant examples. Generally, the quality of the response from the LLM can be significantly improved by selecting the most relevant examples. This is because the language model will be able to better understand the context of the prompt, and also potentially learn failure modes to avoid.
To help the user with selecting the most relevant examples, we provide example selectors that select the most relevant based on different criteria, such as length, semantic similarity, etc. The example selector takes in a list of examples and returns a list of selected examples, formatted as a string. The user can also provide their own example selector. To learn more about example selectors, see [Example Selection](example_selection.md).
To help the user with selecting the most relevant examples, we provide example selectors that select the most relevant based on different criteria, such as length, semantic similarity, etc. The example selector takes in a list of examples and returns a list of selected examples, formatted as a string. The user can also provide their own example selector. To learn more about example selectors, see [Example Selectors](examples/example_selectors.ipynb).
<!-- TODO(shreya): Add correct link here. -->

View File

@ -15,6 +15,6 @@ The following resources exist:
- [Summarization Notebook](../modules/indexes/chain_examples/summarize.ipynb): A notebook walking through how to accomplish this task.
Additional related resources include:
- [Utilities for working with Documents](../modules/utils/how_to_guides.rst): Guides on how to use several of the utilities which will prove helpful for this task, including Text Splitters (for splitting up long documents).
- [Utilities for working with Documents](../reference/utils.rst): Guides on how to use several of the utilities which will prove helpful for this task, including Text Splitters (for splitting up long documents).
- [CombineDocuments Chains](../modules/indexes/combine_docs.md): A conceptual overview of specific types of chains by which you can accomplish this task.
- [Data Augmented Generation](./combine_docs.md): An overview of data augmented generation, which is the general concept of combining external data with LLMs (of which this is a subset).

View File

@ -1,5 +1,14 @@
"""Interface for agents."""
from langchain.agents.agent import Agent, AgentExecutor
from langchain.agents.agent_toolkits import (
create_csv_agent,
create_json_agent,
create_openapi_agent,
create_pandas_dataframe_agent,
create_sql_agent,
create_vectorstore_agent,
create_vectorstore_router_agent,
)
from langchain.agents.conversational.base import ConversationalAgent
from langchain.agents.initialize import initialize_agent
from langchain.agents.load_tools import get_all_tool_names, load_tools
@ -24,4 +33,11 @@ __all__ = [
"get_all_tool_names",
"ConversationalAgent",
"load_agent",
"create_sql_agent",
"create_json_agent",
"create_openapi_agent",
"create_vectorstore_router_agent",
"create_vectorstore_agent",
"create_pandas_dataframe_agent",
"create_csv_agent",
]

View File

@ -47,7 +47,7 @@ class Agent(BaseModel):
@property
def _stop(self) -> List[str]:
return [f"\n{self.observation_prefix}"]
return [f"\n{self.observation_prefix}", f"\n\t{self.observation_prefix}"]
def _construct_scratchpad(
self, intermediate_steps: List[Tuple[AgentAction, str]]
@ -426,7 +426,7 @@ class AgentExecutor(Chain, BaseModel):
)
else:
observation = InvalidTool().run(
output.tool_input,
output.tool,
verbose=self.verbose,
color=None,
llm_prefix="",
@ -473,7 +473,7 @@ class AgentExecutor(Chain, BaseModel):
)
else:
observation = await InvalidTool().arun(
output.tool_input,
output.tool,
verbose=self.verbose,
color=None,
llm_prefix="",

View File

@ -0,0 +1,37 @@
"""Agent toolkits."""
from langchain.agents.agent_toolkits.csv.base import create_csv_agent
from langchain.agents.agent_toolkits.json.base import create_json_agent
from langchain.agents.agent_toolkits.json.toolkit import JsonToolkit
from langchain.agents.agent_toolkits.openapi.base import create_openapi_agent
from langchain.agents.agent_toolkits.openapi.toolkit import OpenAPIToolkit
from langchain.agents.agent_toolkits.pandas.base import create_pandas_dataframe_agent
from langchain.agents.agent_toolkits.python.base import create_python_agent
from langchain.agents.agent_toolkits.sql.base import create_sql_agent
from langchain.agents.agent_toolkits.sql.toolkit import SQLDatabaseToolkit
from langchain.agents.agent_toolkits.vectorstore.base import (
create_vectorstore_agent,
create_vectorstore_router_agent,
)
from langchain.agents.agent_toolkits.vectorstore.toolkit import (
VectorStoreInfo,
VectorStoreRouterToolkit,
VectorStoreToolkit,
)
__all__ = [
"create_json_agent",
"create_sql_agent",
"create_openapi_agent",
"create_python_agent",
"create_vectorstore_agent",
"JsonToolkit",
"SQLDatabaseToolkit",
"OpenAPIToolkit",
"VectorStoreToolkit",
"create_vectorstore_router_agent",
"VectorStoreInfo",
"VectorStoreRouterToolkit",
"create_pandas_dataframe_agent",
"create_csv_agent",
]

View File

@ -0,0 +1,15 @@
"""Toolkits for agents."""
from abc import abstractmethod
from typing import List
from pydantic import BaseModel
from langchain.tools import BaseTool
class BaseToolkit(BaseModel):
"""Class responsible for defining a collection of related tools."""
@abstractmethod
def get_tools(self) -> List[BaseTool]:
"""Get the tools in the toolkit."""

View File

@ -0,0 +1 @@
"""CSV toolkit."""

View File

@ -0,0 +1,17 @@
"""Agent for working with csvs."""
from typing import Any, Optional
from langchain.agents.agent import AgentExecutor
from langchain.agents.agent_toolkits.pandas.base import create_pandas_dataframe_agent
from langchain.llms.base import BaseLLM
def create_csv_agent(
llm: BaseLLM, path: str, pandas_kwargs: Optional[dict] = None, **kwargs: Any
) -> AgentExecutor:
"""Create csv agent by loading to a dataframe and using pandas agent."""
import pandas as pd
_kwargs = pandas_kwargs or {}
df = pd.read_csv(path, **_kwargs)
return create_pandas_dataframe_agent(llm, df, **kwargs)

View File

@ -0,0 +1 @@
"""Json agent."""

View File

@ -0,0 +1,43 @@
"""Json agent."""
from typing import Any, List, Optional
from langchain.agents.agent import AgentExecutor
from langchain.agents.agent_toolkits.json.prompt import JSON_PREFIX, JSON_SUFFIX
from langchain.agents.agent_toolkits.json.toolkit import JsonToolkit
from langchain.agents.mrkl.base import ZeroShotAgent
from langchain.agents.mrkl.prompt import FORMAT_INSTRUCTIONS
from langchain.callbacks.base import BaseCallbackManager
from langchain.chains.llm import LLMChain
from langchain.llms.base import BaseLLM
def create_json_agent(
llm: BaseLLM,
toolkit: JsonToolkit,
callback_manager: Optional[BaseCallbackManager] = None,
prefix: str = JSON_PREFIX,
suffix: str = JSON_SUFFIX,
format_instructions: str = FORMAT_INSTRUCTIONS,
input_variables: Optional[List[str]] = None,
verbose: bool = False,
**kwargs: Any,
) -> AgentExecutor:
"""Construct a json agent from an LLM and tools."""
tools = toolkit.get_tools()
prompt = ZeroShotAgent.create_prompt(
tools,
prefix=prefix,
suffix=suffix,
format_instructions=format_instructions,
input_variables=input_variables,
)
llm_chain = LLMChain(
llm=llm,
prompt=prompt,
callback_manager=callback_manager,
)
tool_names = [tool.name for tool in tools]
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
return AgentExecutor.from_agent_and_tools(
agent=agent, tools=toolkit.get_tools(), verbose=verbose
)

View File

@ -0,0 +1,25 @@
# flake8: noqa
JSON_PREFIX = """You are an agent designed to interact with JSON.
Your goal is to return a final answer by interacting with the JSON.
You have access to the following tools which help you learn more about the JSON you are interacting with.
Only use the below tools. Only use the information returned by the below tools to construct your final answer.
Do not make up any information that is not contained in the JSON.
Your input to the tools should be in the form of `data["key"][0]` where `data` is the JSON blob you are interacting with, and the syntax used is Python.
You should only use keys that you know for a fact exist. You must validate that a key exists by seeing it previously when calling `json_spec_list_keys`.
If you have not seen a key in one of those responses, you cannot use it.
You should only add one key at a time to the path. You cannot add multiple keys at once.
If you encounter a "KeyError", go back to the previous key, look at the available keys, and try again.
If the question does not seem to be related to the JSON, just return "I don't know" as the answer.
Always begin your interaction with the `json_spec_list_keys` tool with input "data" to see what keys exist in the JSON.
Note that sometimes the value at a given path is large. In this case, you will get an error "Value is a large dictionary, should explore its keys directly".
In this case, you should ALWAYS follow up by using the `json_spec_list_keys` tool to see what keys exist at that path.
Do not simply refer the user to the JSON or a section of the JSON, as this is not a valid answer. Keep digging until you find the answer and explicitly return it.
"""
JSON_SUFFIX = """Begin!"
Question: {input}
Thought: I should look at the keys that exist in data to see what I have access to
{agent_scratchpad}"""

View File

@ -0,0 +1,21 @@
"""Toolkit for interacting with a JSON spec."""
from __future__ import annotations
from typing import List
from langchain.agents.agent_toolkits.base import BaseToolkit
from langchain.tools import BaseTool
from langchain.tools.json.tool import JsonGetValueTool, JsonListKeysTool, JsonSpec
class JsonToolkit(BaseToolkit):
"""Toolkit for interacting with a JSON spec."""
spec: JsonSpec
def get_tools(self) -> List[BaseTool]:
"""Get the tools in the toolkit."""
return [
JsonListKeysTool(spec=self.spec),
JsonGetValueTool(spec=self.spec),
]

View File

@ -0,0 +1 @@
"""OpenAPI spec agent."""

View File

@ -0,0 +1,46 @@
"""OpenAPI spec agent."""
from typing import Any, List, Optional
from langchain.agents.agent import AgentExecutor
from langchain.agents.agent_toolkits.openapi.prompt import (
OPENAPI_PREFIX,
OPENAPI_SUFFIX,
)
from langchain.agents.agent_toolkits.openapi.toolkit import OpenAPIToolkit
from langchain.agents.mrkl.base import ZeroShotAgent
from langchain.agents.mrkl.prompt import FORMAT_INSTRUCTIONS
from langchain.callbacks.base import BaseCallbackManager
from langchain.chains.llm import LLMChain
from langchain.llms.base import BaseLLM
def create_openapi_agent(
llm: BaseLLM,
toolkit: OpenAPIToolkit,
callback_manager: Optional[BaseCallbackManager] = None,
prefix: str = OPENAPI_PREFIX,
suffix: str = OPENAPI_SUFFIX,
format_instructions: str = FORMAT_INSTRUCTIONS,
input_variables: Optional[List[str]] = None,
verbose: bool = False,
**kwargs: Any,
) -> AgentExecutor:
"""Construct a json agent from an LLM and tools."""
tools = toolkit.get_tools()
prompt = ZeroShotAgent.create_prompt(
tools,
prefix=prefix,
suffix=suffix,
format_instructions=format_instructions,
input_variables=input_variables,
)
llm_chain = LLMChain(
llm=llm,
prompt=prompt,
callback_manager=callback_manager,
)
tool_names = [tool.name for tool in tools]
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
return AgentExecutor.from_agent_and_tools(
agent=agent, tools=toolkit.get_tools(), verbose=verbose
)

View File

@ -0,0 +1,29 @@
# flake8: noqa
OPENAPI_PREFIX = """You are an agent designed to answer questions by making web requests to an API given the openapi spec.
If the question does not seem related to the API, return I don't know. Do not make up an answer.
Only use information provided by the tools to construct your response.
First, find the base URL needed to make the request.
Second, find the relevant paths needed to answer the question. Take note that, sometimes, you might need to make more than one request to more than one path to answer the question.
Third, find the required parameters needed to make the request. For GET requests, these are usually URL parameters and for POST requests, these are request body parameters.
Fourth, make the requests needed to answer the question. Ensure that you are sending the correct parameters to the request by checking which parameters are required. For parameters with a fixed set of values, please use the spec to look at which values are allowed.
Use the exact parameter names as listed in the spec, do not make up any names or abbreviate the names of parameters.
If you get a not found error, ensure that you are using a path that actually exists in the spec.
"""
OPENAPI_SUFFIX = """Begin!"
Question: {input}
Thought: I should explore the spec to find the base url for the API.
{agent_scratchpad}"""
DESCRIPTION = """Can be used to answer questions about the openapi spec for the API. Always use this tool before trying to make a request.
Example inputs to this tool:
'What are the required query parameters for a GET request to the /bar endpoint?`
'What are the required parameters in the request body for a POST request to the /foo endpoint?'
Always give this tool a specific question."""

View File

@ -0,0 +1,67 @@
"""Requests toolkit."""
from __future__ import annotations
from typing import Any, List
from langchain.agents.agent import AgentExecutor
from langchain.agents.agent_toolkits.base import BaseToolkit
from langchain.agents.agent_toolkits.json.base import create_json_agent
from langchain.agents.agent_toolkits.json.toolkit import JsonToolkit
from langchain.agents.agent_toolkits.openapi.prompt import DESCRIPTION
from langchain.agents.tools import Tool
from langchain.llms.base import BaseLLM
from langchain.requests import RequestsWrapper
from langchain.tools import BaseTool
from langchain.tools.json.tool import JsonSpec
from langchain.tools.requests.tool import (
RequestsDeleteTool,
RequestsGetTool,
RequestsPatchTool,
RequestsPostTool,
RequestsPutTool,
)
class RequestsToolkit(BaseToolkit):
"""Toolkit for making requests."""
requests_wrapper: RequestsWrapper
def get_tools(self) -> List[BaseTool]:
"""Return a list of tools."""
return [
RequestsGetTool(requests_wrapper=self.requests_wrapper),
RequestsPostTool(requests_wrapper=self.requests_wrapper),
RequestsPatchTool(requests_wrapper=self.requests_wrapper),
RequestsPutTool(requests_wrapper=self.requests_wrapper),
RequestsDeleteTool(requests_wrapper=self.requests_wrapper),
]
class OpenAPIToolkit(BaseToolkit):
"""Toolkit for interacting with a OpenAPI api."""
json_agent: AgentExecutor
requests_wrapper: RequestsWrapper
def get_tools(self) -> List[BaseTool]:
"""Get the tools in the toolkit."""
json_agent_tool = Tool(
name="json_explorer",
func=self.json_agent.run,
description=DESCRIPTION,
)
request_toolkit = RequestsToolkit(requests_wrapper=self.requests_wrapper)
return [*request_toolkit.get_tools(), json_agent_tool]
@classmethod
def from_llm(
cls,
llm: BaseLLM,
json_spec: JsonSpec,
requests_wrapper: RequestsWrapper,
**kwargs: Any,
) -> OpenAPIToolkit:
"""Create json agent from llm, then initialize."""
json_agent = create_json_agent(llm, JsonToolkit(spec=json_spec), **kwargs)
return cls(json_agent=json_agent, requests_wrapper=requests_wrapper)

View File

@ -0,0 +1 @@
"""Pandas toolkit."""

View File

@ -0,0 +1,42 @@
"""Agent for working with pandas objects."""
from typing import Any, List, Optional
from langchain.agents.agent import AgentExecutor
from langchain.agents.agent_toolkits.pandas.prompt import PREFIX, SUFFIX
from langchain.agents.mrkl.base import ZeroShotAgent
from langchain.callbacks.base import BaseCallbackManager
from langchain.chains.llm import LLMChain
from langchain.llms.base import BaseLLM
from langchain.tools.python.tool import PythonAstREPLTool
def create_pandas_dataframe_agent(
llm: BaseLLM,
df: Any,
callback_manager: Optional[BaseCallbackManager] = None,
prefix: str = PREFIX,
suffix: str = SUFFIX,
input_variables: Optional[List[str]] = None,
verbose: bool = False,
**kwargs: Any,
) -> AgentExecutor:
"""Construct a pandas agent from an LLM and dataframe."""
import pandas as pd
if not isinstance(df, pd.DataFrame):
raise ValueError(f"Expected pandas object, got {type(df)}")
if input_variables is None:
input_variables = ["df", "input", "agent_scratchpad"]
tools = [PythonAstREPLTool(locals={"df": df})]
prompt = ZeroShotAgent.create_prompt(
tools, prefix=prefix, suffix=suffix, input_variables=input_variables
)
partial_prompt = prompt.partial(df=str(df.head()))
llm_chain = LLMChain(
llm=llm,
prompt=partial_prompt,
callback_manager=callback_manager,
)
tool_names = [tool.name for tool in tools]
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=verbose)

View File

@ -0,0 +1,13 @@
# flake8: noqa
PREFIX = """
You are working with a pandas dataframe in Python. The name of the dataframe is `df`.
You should use the tools below to answer the question posed of you:"""
SUFFIX = """
This is the result of `print(df.head())`:
{df}
Begin!
Question: {input}
{agent_scratchpad}"""

View File

@ -0,0 +1,32 @@
"""Python agent."""
from typing import Any, Optional
from langchain.agents.agent import AgentExecutor
from langchain.agents.agent_toolkits.python.prompt import PREFIX
from langchain.agents.mrkl.base import ZeroShotAgent
from langchain.callbacks.base import BaseCallbackManager
from langchain.chains.llm import LLMChain
from langchain.llms.base import BaseLLM
from langchain.tools.python.tool import PythonREPLTool
def create_python_agent(
llm: BaseLLM,
tool: PythonREPLTool,
callback_manager: Optional[BaseCallbackManager] = None,
verbose: bool = False,
prefix: str = PREFIX,
**kwargs: Any,
) -> AgentExecutor:
"""Construct a python agent from an LLM and tool."""
tools = [tool]
prompt = ZeroShotAgent.create_prompt(tools, prefix=prefix)
llm_chain = LLMChain(
llm=llm,
prompt=prompt,
callback_manager=callback_manager,
)
tool_names = [tool.name for tool in tools]
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=verbose)

View File

@ -0,0 +1,9 @@
# flake8: noqa
PREFIX = """You are an agent designed to write and execute python code to answer questions.
You have access to a python REPL, which you can use to execute python code.
If you get an error, debug your code and try again.
Only use the output of your code to answer the question.
You might know the answer without running any code, but you should still run the code to get the answer.
If it does not seem like you can write code to answer the question, just return "I don't know" as the answer.
"""

View File

@ -0,0 +1 @@
"""SQL agent."""

View File

@ -0,0 +1,45 @@
"""SQL agent."""
from typing import Any, List, Optional
from langchain.agents.agent import AgentExecutor
from langchain.agents.agent_toolkits.sql.prompt import SQL_PREFIX, SQL_SUFFIX
from langchain.agents.agent_toolkits.sql.toolkit import SQLDatabaseToolkit
from langchain.agents.mrkl.base import ZeroShotAgent
from langchain.agents.mrkl.prompt import FORMAT_INSTRUCTIONS
from langchain.callbacks.base import BaseCallbackManager
from langchain.chains.llm import LLMChain
from langchain.llms.base import BaseLLM
def create_sql_agent(
llm: BaseLLM,
toolkit: SQLDatabaseToolkit,
callback_manager: Optional[BaseCallbackManager] = None,
prefix: str = SQL_PREFIX,
suffix: str = SQL_SUFFIX,
format_instructions: str = FORMAT_INSTRUCTIONS,
input_variables: Optional[List[str]] = None,
top_k: int = 10,
verbose: bool = False,
**kwargs: Any,
) -> AgentExecutor:
"""Construct a sql agent from an LLM and tools."""
tools = toolkit.get_tools()
prefix = prefix.format(dialect=toolkit.dialect, top_k=top_k)
prompt = ZeroShotAgent.create_prompt(
tools,
prefix=prefix,
suffix=suffix,
format_instructions=format_instructions,
input_variables=input_variables,
)
llm_chain = LLMChain(
llm=llm,
prompt=prompt,
callback_manager=callback_manager,
)
tool_names = [tool.name for tool in tools]
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
return AgentExecutor.from_agent_and_tools(
agent=agent, tools=toolkit.get_tools(), verbose=verbose
)

View File

@ -0,0 +1,21 @@
# flake8: noqa
SQL_PREFIX = """You are an agent designed to interact with a SQL database.
Given an input question, create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer.
Unless the user specifies a specific number of examples they wish to obtain, always limit your query to at most {top_k} results.
You can order the results by a relevant column to return the most interesting examples in the database.
Never query for all the columns from a specific table, only ask for a the few relevant columns given the question.
You have access to tools for interacting with the database.
Only use the below tools. Only use the information returned by the below tools to construct your final answer.
You MUST double check your query before executing it. If you get an error while executing a query, rewrite the query and try again.
DO NOT make any DML statements (INSERT, UPDATE, DELETE, DROP etc.) to the database.
If the question does not seem related to the database, just return "I don't know" as the answer.
"""
SQL_SUFFIX = """Begin!
Question: {input}
Thought: I should look at the tables in the database to see what I can query.
{agent_scratchpad}"""

View File

@ -0,0 +1,39 @@
"""Toolkit for interacting with a SQL database."""
from typing import List
from pydantic import Field
from langchain.agents.agent_toolkits.base import BaseToolkit
from langchain.sql_database import SQLDatabase
from langchain.tools import BaseTool
from langchain.tools.sql_database.tool import (
InfoSQLDatabaseTool,
ListSQLDatabaseTool,
QueryCheckerTool,
QuerySQLDataBaseTool,
)
class SQLDatabaseToolkit(BaseToolkit):
"""Toolkit for interacting with SQL databases."""
db: SQLDatabase = Field(exclude=True)
@property
def dialect(self) -> str:
"""Return string representation of dialect to use."""
return self.db.dialect
class Config:
"""Configuration for this pydantic object."""
arbitrary_types_allowed = True
def get_tools(self) -> List[BaseTool]:
"""Get the tools in the toolkit."""
return [
QuerySQLDataBaseTool(db=self.db),
InfoSQLDatabaseTool(db=self.db),
ListSQLDatabaseTool(db=self.db),
QueryCheckerTool(db=self.db),
]

View File

@ -0,0 +1 @@
"""Agent toolkit for interacting with vector stores."""

View File

@ -0,0 +1,55 @@
"""VectorStore agent."""
from typing import Any, Optional
from langchain.agents.agent import AgentExecutor
from langchain.agents.agent_toolkits.vectorstore.prompt import PREFIX, ROUTER_PREFIX
from langchain.agents.agent_toolkits.vectorstore.toolkit import (
VectorStoreRouterToolkit,
VectorStoreToolkit,
)
from langchain.agents.mrkl.base import ZeroShotAgent
from langchain.callbacks.base import BaseCallbackManager
from langchain.chains.llm import LLMChain
from langchain.llms.base import BaseLLM
def create_vectorstore_agent(
llm: BaseLLM,
toolkit: VectorStoreToolkit,
callback_manager: Optional[BaseCallbackManager] = None,
prefix: str = PREFIX,
verbose: bool = False,
**kwargs: Any,
) -> AgentExecutor:
"""Construct a vectorstore agent from an LLM and tools."""
tools = toolkit.get_tools()
prompt = ZeroShotAgent.create_prompt(tools, prefix=prefix)
llm_chain = LLMChain(
llm=llm,
prompt=prompt,
callback_manager=callback_manager,
)
tool_names = [tool.name for tool in tools]
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=verbose)
def create_vectorstore_router_agent(
llm: BaseLLM,
toolkit: VectorStoreRouterToolkit,
callback_manager: Optional[BaseCallbackManager] = None,
prefix: str = ROUTER_PREFIX,
verbose: bool = False,
**kwargs: Any,
) -> AgentExecutor:
"""Construct a vectorstore router agent from an LLM and tools."""
tools = toolkit.get_tools()
prompt = ZeroShotAgent.create_prompt(tools, prefix=prefix)
llm_chain = LLMChain(
llm=llm,
prompt=prompt,
callback_manager=callback_manager,
)
tool_names = [tool.name for tool in tools]
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=verbose)

View File

@ -0,0 +1,13 @@
# flake8: noqa
PREFIX = """You are an agent designed to answer questions about sets of documents.
You have access to tools for interacting with the documents, and the inputs to the tools are questions.
Sometimes, you will be asked to provide sources for your questions, in which case you should use the appropriate tool to do so.
If the question does not seem relevant to any of the tools provided, just return "I don't know" as the answer.
"""
ROUTER_PREFIX = """You are an agent designed to answer questions.
You have access to tools for interacting with different sources, and the inputs to the tools are questions.
Your main task is to decide which of the tools is relevant for answering question at hand.
For complex questions, you can break the question down into sub questions and use tools to answers the sub questions.
"""

View File

@ -0,0 +1,89 @@
"""Toolkit for interacting with a vector store."""
from typing import List
from pydantic import BaseModel, Field
from langchain.agents.agent_toolkits.base import BaseToolkit
from langchain.llms.base import BaseLLM
from langchain.llms.openai import OpenAI
from langchain.tools import BaseTool
from langchain.tools.vectorstore.tool import (
VectorStoreQATool,
VectorStoreQAWithSourcesTool,
)
from langchain.vectorstores.base import VectorStore
class VectorStoreInfo(BaseModel):
"""Information about a vectorstore."""
vectorstore: VectorStore = Field(exclude=True)
name: str
description: str
class Config:
"""Configuration for this pydantic object."""
arbitrary_types_allowed = True
class VectorStoreToolkit(BaseToolkit):
"""Toolkit for interacting with a vector store."""
vectorstore_info: VectorStoreInfo = Field(exclude=True)
llm: BaseLLM = Field(default_factory=lambda: OpenAI(temperature=0))
class Config:
"""Configuration for this pydantic object."""
arbitrary_types_allowed = True
def get_tools(self) -> List[BaseTool]:
"""Get the tools in the toolkit."""
description = VectorStoreQATool.get_description(
self.vectorstore_info.name, self.vectorstore_info.description
)
qa_tool = VectorStoreQATool(
name=self.vectorstore_info.name,
description=description,
vectorstore=self.vectorstore_info.vectorstore,
llm=self.llm,
)
description = VectorStoreQAWithSourcesTool.get_description(
self.vectorstore_info.name, self.vectorstore_info.description
)
qa_with_sources_tool = VectorStoreQAWithSourcesTool(
name=f"{self.vectorstore_info.name}_with_sources",
description=description,
vectorstore=self.vectorstore_info.vectorstore,
llm=self.llm,
)
return [qa_tool, qa_with_sources_tool]
class VectorStoreRouterToolkit(BaseToolkit):
"""Toolkit for routing between vectorstores."""
vectorstores: List[VectorStoreInfo] = Field(exclude=True)
llm: BaseLLM = Field(default_factory=lambda: OpenAI(temperature=0))
class Config:
"""Configuration for this pydantic object."""
arbitrary_types_allowed = True
def get_tools(self) -> List[BaseTool]:
"""Get the tools in the toolkit."""
tools: List[BaseTool] = []
for vectorstore_info in self.vectorstores:
description = VectorStoreQATool.get_description(
vectorstore_info.name, vectorstore_info.description
)
qa_tool = VectorStoreQATool(
name=vectorstore_info.name,
description=description,
vectorstore=vectorstore_info.vectorstore,
llm=self.llm,
)
tools.append(qa_tool)
return tools

View File

@ -17,12 +17,12 @@ def initialize_agent(
agent_kwargs: Optional[dict] = None,
**kwargs: Any,
) -> AgentExecutor:
"""Load agent given tools and LLM.
"""Load an agent executor given tools and LLM.
Args:
tools: List of tools this agent has access to.
llm: Language model to use as the agent.
agent: The agent to use. Valid options are:
agent: A string that specified the agent type to use. Valid options are:
`zero-shot-react-description`
`react-docstore`
`self-ask-with-search`
@ -32,10 +32,11 @@ def initialize_agent(
callback_manager: CallbackManager to use. Global callback manager is used if
not provided. Defaults to None.
agent_path: Path to serialized agent to use.
**kwargs: Additional key word arguments to pass to the agent.
agent_kwargs: Additional key word arguments to pass to the underlying agent
**kwargs: Additional key word arguments passed to the agent executor
Returns:
An agent.
An agent executor
"""
if agent is None and agent_path is None:
agent = "zero-shot-react-description"

View File

@ -9,11 +9,12 @@ from langchain.chains.api.base import APIChain
from langchain.chains.llm_math.base import LLMMathChain
from langchain.chains.pal.base import PALChain
from langchain.llms.base import BaseLLM
from langchain.python import PythonREPL
from langchain.tools.python.tool import PythonREPLTool
from langchain.requests import RequestsWrapper
from langchain.tools.base import BaseTool
from langchain.tools.bing_search.tool import BingSearchRun
from langchain.tools.google_search.tool import GoogleSearchResults, GoogleSearchRun
from langchain.tools.requests.tool import RequestsGetTool
from langchain.tools.wolfram_alpha.tool import WolframAlphaQueryRun
from langchain.utilities.bash import BashProcess
from langchain.utilities.bing_search import BingSearchAPIWrapper
@ -25,19 +26,11 @@ from langchain.utilities.wolfram_alpha import WolframAlphaAPIWrapper
def _get_python_repl() -> BaseTool:
return Tool(
name="Python REPL",
description="A Python shell. Use this to execute python commands. Input should be a valid python command. If you expect output it should be printed out.",
func=PythonREPL().run,
)
return PythonREPLTool()
def _get_requests() -> BaseTool:
return Tool(
name="Requests",
description="A portal to the internet. Use this when you need to get specific content from a site. Input should be a specific url, and the output will be all the text on that page.",
func=RequestsWrapper().run,
)
return RequestsGetTool(requests_wrapper=RequestsWrapper())
def _get_terminal() -> BaseTool:

View File

@ -11,6 +11,7 @@ from langchain.chains.llm_bash.base import LLMBashChain
from langchain.chains.llm_checker.base import LLMCheckerChain
from langchain.chains.llm_math.base import LLMMathChain
from langchain.chains.llm_requests import LLMRequestsChain
from langchain.chains.llm_summarization_checker.base import LLMSummarizationCheckerChain
from langchain.chains.loading import load_chain
from langchain.chains.mapreduce import MapReduceChain
from langchain.chains.moderation import OpenAIModerationChain
@ -30,6 +31,7 @@ __all__ = [
"LLMChain",
"LLMBashChain",
"LLMCheckerChain",
"LLMSummarizationCheckerChain",
"LLMMathChain",
"PALChain",
"QAWithSourcesChain",

View File

@ -69,7 +69,7 @@ class APIChain(Chain, BaseModel):
self.callback_manager.on_text(
api_url, color="green", end="\n", verbose=self.verbose
)
api_response = self.requests_wrapper.run(api_url)
api_response = self.requests_wrapper.get(api_url)
self.callback_manager.on_text(
api_response, color="yellow", end="\n", verbose=self.verbose
)

View File

@ -67,7 +67,7 @@ class LLMRequestsChain(Chain, BaseModel):
# Other keys are assumed to be needed for LLM prediction
other_keys = {k: v for k, v in inputs.items() if k != self.input_key}
url = inputs[self.input_key]
res = self.requests_wrapper.run(url)
res = self.requests_wrapper.get(url)
# extract the text from the html
soup = BeautifulSoup(res, "html.parser")
other_keys[self.requests_key] = soup.get_text()[: self.text_length]

View File

@ -0,0 +1,7 @@
"""Summarization checker chain for verifying accuracy of text generation.
Chain that tries to verify the accuracy of text generation by splitting it into a
list of facts, then checking if those facts are true or not, and rewriting
the text to make it more truth-ful. It will repeat this loop until it hits `max_tries`
or gets to a "true" output.
"""

View File

@ -0,0 +1,133 @@
"""Chain for summarization with self-verification."""
from pathlib import Path
from typing import Dict, List
from pydantic import BaseModel, Extra
from langchain.chains.base import Chain
from langchain.chains.llm import LLMChain
from langchain.chains.sequential import SequentialChain
from langchain.llms.base import BaseLLM
from langchain.prompts.prompt import PromptTemplate
PROMPTS_DIR = Path(__file__).parent / "prompts"
CREATE_ASSERTIONS_PROMPT = PromptTemplate.from_file(
PROMPTS_DIR / "create_facts.txt", ["summary"]
)
CHECK_ASSERTIONS_PROMPT = PromptTemplate.from_file(
PROMPTS_DIR / "check_facts.txt", ["assertions"]
)
REVISED_SUMMARY_PROMPT = PromptTemplate.from_file(
PROMPTS_DIR / "revise_summary.txt", ["checked_assertions", "summary"]
)
ARE_ALL_TRUE_PROMPT = PromptTemplate.from_file(
PROMPTS_DIR / "are_all_true_prompt.txt", ["checked_assertions"]
)
class LLMSummarizationCheckerChain(Chain, BaseModel):
"""Chain for question-answering with self-verification.
Example:
.. code-block:: python
from langchain import OpenAI, LLMSummarizationCheckerChain
llm = OpenAI(temperature=0.0)
checker_chain = LLMSummarizationCheckerChain(llm=llm)
"""
llm: BaseLLM
"""LLM wrapper to use."""
create_assertions_prompt: PromptTemplate = CREATE_ASSERTIONS_PROMPT
check_assertions_prompt: PromptTemplate = CHECK_ASSERTIONS_PROMPT
revised_summary_prompt: PromptTemplate = REVISED_SUMMARY_PROMPT
are_all_true_prompt: PromptTemplate = ARE_ALL_TRUE_PROMPT
input_key: str = "query" #: :meta private:
output_key: str = "result" #: :meta private:
max_checks: int = 2
"""Maximum number of times to check the assertions. Default to double-checking."""
class Config:
"""Configuration for this pydantic object."""
extra = Extra.forbid
arbitrary_types_allowed = True
@property
def input_keys(self) -> List[str]:
"""Return the singular input key.
:meta private:
"""
return [self.input_key]
@property
def output_keys(self) -> List[str]:
"""Return the singular output key.
:meta private:
"""
return [self.output_key]
def _call(self, inputs: Dict[str, str]) -> Dict[str, str]:
all_true = False
count = 0
output = None
original_input = inputs[self.input_key]
chain_input = original_input
while not all_true and count < self.max_checks:
chain = SequentialChain(
chains=[
LLMChain(
llm=self.llm,
prompt=self.create_assertions_prompt,
output_key="assertions",
verbose=self.verbose,
),
LLMChain(
llm=self.llm,
prompt=self.check_assertions_prompt,
output_key="checked_assertions",
verbose=self.verbose,
),
LLMChain(
llm=self.llm,
prompt=self.revised_summary_prompt,
output_key="revised_summary",
verbose=self.verbose,
),
LLMChain(
llm=self.llm,
output_key="all_true",
prompt=self.are_all_true_prompt,
verbose=self.verbose,
),
],
input_variables=["summary"],
output_variables=["all_true", "revised_summary"],
verbose=True,
)
output = chain({"summary": chain_input})
count += 1
if output["all_true"].strip() == "True":
break
if self.verbose:
print(output["revised_summary"])
chain_input = output["revised_summary"]
if not output:
raise ValueError("No output from chain")
return {self.output_key: output["revised_summary"].strip()}
@property
def _chain_type(self) -> str:
return "llm_summarization_checker_chain"

View File

@ -0,0 +1,38 @@
Below are some assertions that have been fact checked and are labeled as true or false.
If all of the assertions are true, return "True". If any of the assertions are false, return "False".
Here are some examples:
===
Checked Assertions: """
- The sky is red: False
- Water is made of lava: False
- The sun is a star: True
"""
Result: False
===
Checked Assertions: """
- The sky is blue: True
- Water is wet: True
- The sun is a star: True
"""
Result: True
===
Checked Assertions: """
- The sky is blue - True
- Water is made of lava- False
- The sun is a star - True
"""
Result: False
===
Checked Assertions:"""
{checked_assertions}
"""
Result:

View File

@ -0,0 +1,10 @@
You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.
Here is a bullet point list of facts:
"""
{assertions}
"""
For each fact, determine whether it is true or false about the subject. If you are unable to determine whether the fact is true or false, output "Undetermined".
If the fact is false, explain why.

Some files were not shown because too many files have changed in this diff Show More