Commit Graph

375 Commits

Author SHA1 Message Date
Sam
931e68692e
Adds a chain around sympy for symbolic math (#6834)
- Description: Adds a new chain that acts as a wrapper around Sympy to
give LLMs the ability to do some symbolic math.
- Dependencies: SymPy

---------

Co-authored-by: sreiswig <sreiswig@github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-12 15:17:32 -04:00
Alec Flett
6cdd4b5edc
only add handlers if they are new (#7504)
When using callbacks, there are times when callbacks can be added
redundantly: for instance sometimes you might need to create an llm with
specific callbacks, but then also create and agent that uses a chain
that has those callbacks already set. This means that "callbacks" might
get passed down again to the llm at predict() time, resulting in
duplicate calls to the `on_llm_start` callback.

For the sake of simplicity, I made it so that langchain never adds an
exact handler/callbacks object in `add_handler`, thus avoiding the
duplicate handler issue.

Tagging @hwchase17 for callback review

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-12 03:48:29 -04:00
Junlin Zhou
5f17c57174
Update chat agents' output parser to extract action by regex (#7511)
Currently `ChatOutputParser` extracts actions by splitting the text on
"```", and then load the second part as a json string.

But sometimes the LLM will wrap the action in markdown code block like:

````markdown
```json
{
  "action": "foo",
  "action_input": "bar"
}
```
````

Splitting text on "```" will cause `OutputParserException` in such case.

This PR changes the behaviour to extract the `$JSON_BLOB` by regex, so
that it can handle both ` ``` ``` ` and ` ```json ``` `

@hinthornw

---------

Co-authored-by: Junlin Zhou <jlzhou@zjuici.com>
2023-07-12 03:12:02 -04:00
Bagatur
ebcb144342
unit test sqlalachemy (#7582) 2023-07-12 03:03:16 -04:00
Daniel Chalef
c7f7788d0b
Add ZepMemory; improve ZepChatMessageHistory handling of metadata; Fix bugs (#7444)
Hey @hwchase17 - 

This PR adds a `ZepMemory` class, improves handling of Zep's message
metadata, and makes it easier for folks building custom chains to
persist metadata alongside their chat history.

We've had plenty confused users unfamiliar with ChatMessageHistory
classes and how to wrap the `ZepChatMessageHistory` in a
`ConversationBufferMemory`. So we've created the `ZepMemory` class as a
light wrapper for `ZepChatMessageHistory`.

Details:
- add ZepMemory, modify notebook to demo use of ZepMemory
- Modify summary to be SystemMessage
- add metadata argument to add_message; add Zep metadata to
Message.additional_kwargs
- support passing in metadata
2023-07-10 01:53:49 -04:00
William FH
612a74eb7e
Make Ref Example Threadsafe (#7383)
Have noticed transient ref example misalignment. I believe this is
caused by the logic of assigning an example within the thread executor
rather than before.
2023-07-07 21:50:42 -07:00
William FH
4789c99bc2
Add String Distance and Embedding Evaluators (#7123)
Add a string evaluator and pairwise string evaluator implementation for:
- Embedding distance
- String distance

Update docs
2023-07-07 21:44:31 -07:00
William FH
c5edbea34a
Load Run Evaluator (#7101)
Current problems:
1. Evaluating LLMs or Chat models isn't smooth. Even specifying
'generations' as the output inserts a redundant list into the eval
template
2. Configuring input / prediction / reference keys in the
`get_qa_evaluator` function is confusing. Unless you are using a chain
with the default keys, you have to specify all the variables and need to
reason about whether the key corresponds to the traced run's inputs,
outputs or the examples inputs or outputs.


Proposal:
- Configure the run evaluator according to a model. Use the model type
and input/output keys to assert compatibility where possible. Only need
to specify a reference_key for certain evaluators (which is less
confusing than specifying input keys)


When does this work:
- If you have your langchain model available (assumed always for
run_on_dataset flow)
- If you are evaluating an LLM, Chat model, or chain
- If the LLM or chat models are traced by langchain (wouldn't work if
you add an incompatible schema via the REST API)

When would this fail:
- Currently if you directly create an example from an LLM run, the
outputs are generations with all the extra metadata present. A simple
`example_key` and dumping all to the template could make the evaluations
unreliable
- Doesn't help if you're not using the low level API
- If you want to instantiate the evaluator without instantiating your
chain or LLM (maybe common for monitoring, for instance) -> could also
load from run or run type though

What's ugly:
- Personally think it's better to load evaluators one by one since
passing a config down is pretty confusing.
- Lots of testing needs to be added
- Inconsistent in that it makes a separate run and example input mapper
instead of the original `RunEvaluatorInputMapper`, which maps a run and
example to a single input.

Example usage running the for an LLM, Chat Model, and Agent.

```
# Test running for the string evaluators
evaluator_names = ["qa", "criteria"]

model = ChatOpenAI()
configured_evaluators = load_run_evaluators_for_model(evaluator_names, model=model, reference_key="answer")
run_on_dataset(ds_name, model, run_evaluators=configured_evaluators)
```


<details>
  <summary>Full code with dataset upload</summary>
```
## Create dataset
from langchain.evaluation.run_evaluators.loading import load_run_evaluators_for_model
from langchain.evaluation import load_dataset
import pandas as pd

lcds = load_dataset("llm-math")
df = pd.DataFrame(lcds)

from uuid import uuid4
from langsmith import Client
client = Client()
ds_name = "llm-math - " + str(uuid4())[0:8]
ds = client.upload_dataframe(df, name=ds_name, input_keys=["question"], output_keys=["answer"])



## Define the models we'll test over
from langchain.llms import OpenAI
from langchain.chat_models import ChatOpenAI
from langchain.agents import initialize_agent, AgentType

from langchain.tools import tool

llm = OpenAI(temperature=0)
chat_model = ChatOpenAI(temperature=0)

@tool
    def sum(a: float, b: float) -> float:
        """Add two numbers"""
        return a + b
    
def construct_agent():
    return initialize_agent(
        llm=chat_model,
        tools=[sum],
        agent=AgentType.OPENAI_MULTI_FUNCTIONS,
    )

agent = construct_agent()

# Test running for the string evaluators
evaluator_names = ["qa", "criteria"]

models = [llm, chat_model, agent]
run_evaluators = []
for model in models:
    run_evaluators.append(load_run_evaluators_for_model(evaluator_names, model=model, reference_key="answer"))
    

# Run on LLM, Chat Model, and Agent
from langchain.client.runner_utils import run_on_dataset

to_test = [llm, chat_model, construct_agent]

for model, configured_evaluators in zip(to_test, run_evaluators):
    run_on_dataset(ds_name, model, run_evaluators=configured_evaluators, verbose=True)
```
</details>

---------

Co-authored-by: Nuno Campos <nuno@boringbits.io>
2023-07-07 19:57:59 -07:00
Bagatur
4d427b2397
Base language model docstrings (#7104) 2023-07-07 16:09:10 -04:00
William FH
4e180dc54e
Unset Cache in Tests (#7362)
This is impacting other unit tests that use callbacks since the cache is
still set (just empty)
2023-07-07 11:05:09 -07:00
Bagatur
927c8eb91a
Refac package version check (#7312) 2023-07-07 01:21:53 -04:00
Jason B. Koh
d642609a23
Fix: Recognize List at from_function (#7178)
- Description: pydantic's `ModelField.type_` only exposes the native
data type but not complex type hints like `List`. Thus, generating a
Tool with `from_function` through function signature produces incorrect
argument schemas (e.g., `str` instead of `List[str]`)
  - Issue: N/A
  - Dependencies: N/A
  - Tag maintainer: @hinthornw
  - Twitter handle: `mapped`

All the unittest (with an additional one in this PR) passed, though I
didn't try integration tests...
2023-07-06 17:22:09 -04:00
William FH
e736d60516
Load Evaluator (#6942)
Create a `load_evaluators()` function so you don't have to import all
the individual evaluator classes
2023-07-06 13:58:58 -07:00
William FH
576880abc5
Re-use Trajectory Evaluator (#7248)
Use the trajectory eval chain in the run evaluation implementation and
update the prepare inputs method to apply to both asynca nd sync
2023-07-06 07:00:24 -07:00
William FH
ec66d5188c
Add Better Errors for Comparison Chain (#7033)
+ change to ABC - this lets us add things like the evaluation name for
loading
2023-07-06 06:37:04 -07:00
Sasmitha Manathunga
0c7a5cb206
Fix inconsistent behavior of CharacterTextSplitter when changing keep_separator (#7263)
- Description:
- When `keep_separator` is `True` the `_split_text_with_regex()` method
in `text_splitter` uses regex to split, but when `keep_separator` is
`False` it uses `str.split()`. This causes problems when the separator
is a special regex character like `.` or `*`. This PR fixes that by
using `re.split()` in both cases.
- Issue: #7262 
- Tag maintainer: @baskaryan
2023-07-06 09:30:03 -04:00
Mike Nitsenko
d669b9ece9
Document loader for Cube Semantic Layer (#6882)
### Description

This pull request introduces the "Cube Semantic Layer" document loader,
which demonstrates the retrieval of Cube's data model metadata in a
format suitable for passing to LLMs as embeddings. This enhancement aims
to provide contextual information and improve the understanding of data.

Twitter handle:
@the_cube_dev

---------

Co-authored-by: rlm <pexpresss31@gmail.com>
2023-07-05 15:18:12 -07:00
Mike Salvatore
265f05b10e
Enable InMemoryDocstore to be constructed without providing a dict (#6976)
- Description: Allow `InMemoryDocstore` to be created without passing a
dict to the constructor; the constructor can create a dict at runtime if
one isn't provided.
- Tag maintainer: @dev2049
2023-07-05 16:56:31 -04:00
Santiago Delgado
fa55c5a16b
Fixed Office365 tool __init__.py files, tests, and get_tools() function (#7046)
## Description
Added Office365 tool modules to `__init__.py` files
## Issue
As described in Issue
https://github.com/hwchase17/langchain/issues/6936, the Office365
toolkit can't be loaded easily because it is not included in the
`__init__.py` files.
## Reviewer
@dev2049
2023-07-05 15:46:21 -04:00
Mohammad Mohtashim
7d92e9407b
Jinja2 validation changed to issue warnings rather than issuing exceptions. (#7161)
- Description: If their are missing or extra variables when validating
Jinja 2 template then a warning is issued rather than raising an
exception. This allows for better flexibility for the developer as
described in #7044. Also changed the relevant test so pytest is checking
for raised warnings rather than exceptions.
  - Issue: #7044 
  - Tag maintainer: @hwchase17, @baskaryan

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-07-05 14:04:29 -04:00
Nuno Campos
81e5b1ad36
Add serialized object to retriever start callback (#7074)
<!-- Thank you for contributing to LangChain!

Replace this comment with:
  - Description: a description of the change, 
  - Issue: the issue # it fixes (if applicable),
  - Dependencies: any dependencies required for this change,
- Tag maintainer: for a quicker response, tag the relevant maintainer
(see below),
- Twitter handle: we announce bigger features on Twitter. If your PR
gets announced and you'd like a mention, we'll gladly shout you out!

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
  2. an example notebook showing its use.

Maintainer responsibilities:
  - General / Misc / if you don't know who to tag: @dev2049
  - DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
  - Models / Prompts: @hwchase17, @dev2049
  - Memory: @hwchase17
  - Agents / Tools / Toolkits: @vowelparrot
  - Tracing / Callbacks: @agola11
  - Async: @agola11

If no one reviews your PR within a few days, feel free to @-mention the
same people again.

See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
 -->
2023-07-05 18:04:43 +01:00
Harrison Chase
0ad984fa27
Docs combine document chain (#6994)
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-04 12:51:04 -06:00
Nuno Campos
c8f8b1b327
Add events to tracer runs (#7090)
<!-- Thank you for contributing to LangChain!

Replace this comment with:
  - Description: a description of the change, 
  - Issue: the issue # it fixes (if applicable),
  - Dependencies: any dependencies required for this change,
- Tag maintainer: for a quicker response, tag the relevant maintainer
(see below),
- Twitter handle: we announce bigger features on Twitter. If your PR
gets announced and you'd like a mention, we'll gladly shout you out!

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
  2. an example notebook showing its use.

Maintainer responsibilities:
  - General / Misc / if you don't know who to tag: @dev2049
  - DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
  - Models / Prompts: @hwchase17, @dev2049
  - Memory: @hwchase17
  - Agents / Tools / Toolkits: @vowelparrot
  - Tracing / Callbacks: @agola11
  - Async: @agola11

If no one reviews your PR within a few days, feel free to @-mention the
same people again.

See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
 -->
2023-07-03 12:43:43 -07:00
Sergey Kozlov
6d15854cda
Add JSON Lines support to JSONLoader (#6913)
**Description**:

The JSON Lines format is used by some services such as OpenAI and
HuggingFace. It's also a convenient alternative to CSV.

This PR adds JSON Lines support to `JSONLoader` and also updates related
tests.

**Tag maintainer**: @rlancemartin, @eyurtsev.

PS I was not able to build docs locally so didn't update related
section.
2023-07-02 12:32:41 -07:00
Bagatur
7acd524210
Rm retriever kwargs (#7013)
Doesn't actually limit the Retriever interface but hopefully in practice
it does
2023-07-02 08:22:24 -06:00
Harrison Chase
3bfe7cf467
Harrison/split schema dir (#7025)
should be no functional changes

also keep __init__ exposing a lot for backwards compat

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-01 13:39:19 -04:00
Zander Chase
b0859c9b18
Add New Retriever Interface with Callbacks (#5962)
Handle the new retriever events in a way that (I think) is entirely
backwards compatible? Needs more testing for some of the chain changes
and all.

This creates an entire new run type, however. We could also just treat
this as an event within a chain run presumably (same with memory)

Adds a subclass initializer that upgrades old retriever implementations
to the new schema, along with tests to ensure they work.

First commit doesn't upgrade any of our retriever implementations (to
show that we can pass the tests along with additional ones testing the
upgrade logic).

Second commit upgrades the known universe of retrievers in langchain.

- [X] Add callback handling methods for retriever start/end/error (open
to renaming to 'retrieval' if you want that)
- [X] Update BaseRetriever schema to support callbacks
- [X] Tests for upgrading old "v1" retrievers for backwards
compatibility
- [X] Update existing retriever implementations to implement the new
interface
- [X] Update calls within chains to .{a]get_relevant_documents to pass
the child callback manager
- [X] Update the notebooks/docs to reflect the new interface
- [X] Test notebooks thoroughly


Not handled:
- Memory pass throughs: retrieval memory doesn't have a parent callback
manager passed through the method

---------

Co-authored-by: Nuno Campos <nuno@boringbits.io>
Co-authored-by: William Fu-Hinthorn <13333726+hinthornw@users.noreply.github.com>
2023-06-30 14:44:03 -07:00
Bagatur
e3b7effc8f
Beef up import test (#6979) 2023-06-30 09:26:05 -07:00
William FH
8c73037dff
Simplify eval arg names (#6944)
It'll be easier to switch between these if the names of predictions are
consistent
2023-06-30 07:47:53 -07:00
Tahjyei Thompson
7d8830f707
Add OpenAIMultiFunctionsAgent to import list in agents directory (#6824)
- Added OpenAIMultiFunctionsAgent to the import list of the Agents
directory

---------

Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-06-29 18:34:26 -07:00
Zander Chase
429f4dbe4d
Add Input Mapper in run_on_dataset (#6894)
If you create a dataset from runs and run the same chain or llm on it
later, it usually works great.

If you have an agent dataset and want to run a different agent on it, or
have more complex schema, it's hard for us to automatically map these
values every time. This PR lets you pass in an input_mapper function
that converts the example inputs to whatever format your model expects
2023-06-29 16:53:49 -07:00
corranmac
20c6ade2fc
Grobid parser for Scientific Articles from PDF (#6729)
### Scientific Article PDF Parsing via Grobid

`Description:`
This change adds the GrobidParser class, which uses the Grobid library
to parse scientific articles into a universal XML format containing the
article title, references, sections, section text etc. The GrobidParser
uses a local Grobid server to return PDFs document as XML and parses the
XML to optionally produce documents of individual sentences or of whole
paragraphs. Metadata includes the text, paragraph number, pdf relative
bboxes, pages (text may overlap over two pages), section title
(Introduction, Methodology etc), section_number (i.e 1.1, 2.3), the
title of the paper and finally the file path.
      
Grobid parsing is useful beyond standard pdf parsing as it accurately
outputs sections and paragraphs within them. This allows for
post-fitering of results for specific sections i.e. limiting results to
the methodology section or results. While sections are split via
headings, ideally they could be classified specifically into
introduction, methodology, results, discussion, conclusion. I'm
currently experimenting with chatgpt-3.5 for this function, which could
later be implemented as a textsplitter.

`Dependencies:`
For use, the grobid repo must be cloned and Java must be installed, for
colab this is:

```
!apt-get install -y openjdk-11-jdk -q
!update-alternatives --set java /usr/lib/jvm/java-11-openjdk-amd64/bin/java
!git clone https://github.com/kermitt2/grobid.git
os.environ["JAVA_HOME"] = "/usr/lib/jvm/java-11-openjdk-amd64"
os.chdir('grobid')
!./gradlew clean install
```

Once installed the server is ran on localhost:8070 via
```
get_ipython().system_raw('nohup ./gradlew run > grobid.log 2>&1 &')
```

@rlancemartin, @eyurtsev

Twitter Handle: @Corranmac

Grobid Demo Notebook is
[here](https://colab.research.google.com/drive/1X-St_mQRmmm8YWtct_tcJNtoktbdGBmd?usp=sharing).

---------

Co-authored-by: rlm <pexpresss31@gmail.com>
2023-06-29 14:29:29 -07:00
Ayan Bandyopadhyay
f92ccf70fd
Update to the latest Psychic python library version (#6804)
Update the Psychic document loader to use the latest `psychicapi` python
library version: `0.8.0`
2023-06-27 22:26:38 -07:00
Matthew Plachter
d6664af0ee
add async to zapier nla tools (#6791)
Replace this comment with:
  - Description: Add Async functionality to Zapier NLA Tools
  - Issue:  n/a 
  - Dependencies: n/a
  - Tag maintainer: 

Maintainer responsibilities:
  - Agents / Tools / Toolkits: @vowelparrot
  - Async: @agola11

If no one reviews your PR within a few days, feel free to @-mention the
same people again.

See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
2023-06-27 16:53:35 -07:00
Robert Lewis
74848aafea
Zapier - Add better error messaging for 401 responses (#6840)
Description: When a 401 response is given back by Zapier, hint to the
end user why that may have occurred

- If an API Key was initialized with the wrapper, ask them to check
their API Key value
- if an access token was initialized with the wrapper, ask them to check
their access token or verify that it doesn't need to be refreshed.

Tag maintainer: @dev2049
2023-06-27 16:35:42 -07:00
Cristóbal Carnero Liñán
e494b0a09f
feat (documents): add a source code loader based on AST manipulation (#6486)
#### Summary

A new approach to loading source code is implemented:

Each top-level function and class in the code is loaded into separate
documents. Then, an additional document is created with the top-level
code, but without the already loaded functions and classes.

This could improve the accuracy of QA chains over source code.

For instance, having this script:

```
class MyClass:
    def __init__(self, name):
        self.name = name

    def greet(self):
        print(f"Hello, {self.name}!")

def main():
    name = input("Enter your name: ")
    obj = MyClass(name)
    obj.greet()

if __name__ == '__main__':
    main()
```

The loader will create three documents with this content:

First document:
```
class MyClass:
    def __init__(self, name):
        self.name = name

    def greet(self):
        print(f"Hello, {self.name}!")
```

Second document:
```
def main():
    name = input("Enter your name: ")
    obj = MyClass(name)
    obj.greet()
```

Third document:
```
# Code for: class MyClass:

# Code for: def main():

if __name__ == '__main__':
    main()
```

A threshold parameter is added to control whether small scripts are
split in this way or not.

At this moment, only Python and JavaScript are supported. The
appropriate parser is determined by examining the file extension.

#### Tests

This PR adds:

- Unit tests
- Integration tests

#### Dependencies

Only one dependency was added as optional (needed for the JavaScript
parser).

#### Documentation

A notebook is added showing how the loader can be used.

#### Who can review?

@eyurtsev @hwchase17

---------

Co-authored-by: rlm <pexpresss31@gmail.com>
2023-06-27 15:58:47 -07:00
Robert Lewis
da462d9dd4
Zapier update oauth support (#6780)
Description: Update documentation to

1) point to updated documentation links at Zapier.com (we've revamped
our help docs and paths), and
2) To provide clarity how to use the wrapper with an access token for
OAuth support

Demo:

Initializing the Zapier Wrapper with an OAuth Access Token

`ZapierNLAWrapper(zapier_nla_oauth_access_token="<redacted>")`

Using LangChain to resolve the current weather in Vancouver BC
leveraging Zapier NLA to lookup weather by coords.

```
> Entering new  chain...
 I need to use a tool to get the current weather.
Action: The Weather: Get Current Weather
Action Input: Get the current weather for Vancouver BC
Observation: {"coord__lon": -123.1207, "coord__lat": 49.2827, "weather": [{"id": 802, "main": "Clouds", "description": "scattered clouds", "icon": "03d", "icon_url": "http://openweathermap.org/img/wn/03d@2x.png"}], "weather[]icon_url": ["http://openweathermap.org/img/wn/03d@2x.png"], "weather[]icon": ["03d"], "weather[]id": [802], "weather[]description": ["scattered clouds"], "weather[]main": ["Clouds"], "base": "stations", "main__temp": 71.69, "main__feels_like": 71.56, "main__temp_min": 67.64, "main__temp_max": 76.39, "main__pressure": 1015, "main__humidity": 64, "visibility": 10000, "wind__speed": 3, "wind__deg": 155, "wind__gust": 11.01, "clouds__all": 41, "dt": 1687806607, "sys__type": 2, "sys__id": 2011597, "sys__country": "CA", "sys__sunrise": 1687781297, "sys__sunset": 1687839730, "timezone": -25200, "id": 6173331, "name": "Vancouver", "cod": 200, "summary": "scattered clouds", "_zap_search_was_found_status": true}
Thought: I now know the current weather in Vancouver BC.
Final Answer: The current weather in Vancouver BC is scattered clouds with a temperature of 71.69 and wind speed of 3
```
2023-06-27 11:46:32 -07:00
Zander Chase
ad028bbb80
Permit Constitutional Principles (#6807)
In the criteria evaluator.
2023-06-27 00:23:54 -07:00
Zander Chase
6ca383ecf6
Update to RunOnDataset helper functions to accept evaluator callbacks (#6629)
Also improve docstrings and update the tracing datasets notebook to
focus on "debug, evaluate, monitor"
2023-06-26 23:58:13 -07:00
Zander Chase
d7dbf4aefe
Clean up agent trajectory interface (#6799)
- Enable reference
- Enable not specifying tools at the start
- Add methods with keywords
2023-06-26 22:54:04 -07:00
Zander Chase
cc60fed3be
Add a Pairwise Comparison Chain (#6703)
Notebook shows preference scoring between two chains and reports wilson
score interval + p value

I think I'll add the option to insert ground truth labels but doesn't
have to be in this PR
2023-06-26 20:47:41 -07:00
Zander Chase
c460b04c64
Update String Evaluator (#6615)
- Add protocol for `evaluate_strings` 
- Move the criteria evaluator out so it's not restricted to being
applied on traced runs
2023-06-26 14:16:14 -07:00
Zander Chase
6d30acffcb
Fix breaking tags (#6765)
Fix tags change that broke old way of initializing agent

Closes #6756
2023-06-26 09:28:11 -07:00
Pau Ramon Revilla
87802c86d9
Added a MHTML document loader (#6311)
MHTML is a very interesting format since it's used both for emails but
also for archived webpages. Some scraping projects want to store pages
in disk to process them later, mhtml is perfect for that use case.

This is heavily inspired from the beautifulsoup html loader, but
extracting the html part from the mhtml file.

---------

Co-authored-by: rlm <pexpresss31@gmail.com>
2023-06-25 13:12:08 -07:00
Ankush Gola
e1b801be36
split up batch llm calls into separate runs (#5804) 2023-06-24 21:03:31 -07:00
UmerHA
068142fce2
Add caching to BaseChatModel (issue #1644) (#5089)
#  Add caching to BaseChatModel
Fixes #1644

(Sidenote: While testing, I noticed we have multiple implementations of
Fake LLMs, used for testing. I consolidated them.)

## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
Models
- @hwchase17
- @agola11

Twitter: [@UmerHAdil](https://twitter.com/@UmerHAdil) | Discord:
RicChilligerDude#7589

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-24 11:45:09 -07:00
Alejandra De Luna
980c865174
fix: remove callbacks arg from Tool and StructuredTool inferred schema (#6483)
Fixes #5456 

This PR removes the `callbacks` argument from a tool's schema when
creating a `Tool` or `StructuredTool` with the `from_function` method
and `infer_schema` is set to `True`. The `callbacks` argument is now
removed in the `create_schema_from_function` and `_get_filtered_args`
methods. As suggested by @vowelparrot, this fix provides a
straightforward solution that minimally affects the existing
implementation.

A test was added to verify that this change enables the expected use of
`Tool` and `StructuredTool` when using a `CallbackManager` and inferring
the tool's schema.

  - @hwchase17
2023-06-23 01:48:27 -07:00
Zander Chase
b4fe7f3a09
Session to project (#6249)
Sessions are being renamed to projects in the tracer
2023-06-23 01:11:01 -07:00
Tim Conkling
c28990d871
StreamlitCallbackHandler (#6315)
A new implementation of `StreamlitCallbackHandler`. It formats Agent
thoughts into Streamlit expanders.

You can see the handler in action here:
https://langchain-mrkl.streamlit.app/

Per a discussion with Harrison, we'll be adding a
`StreamlitCallbackHandler` implementation to an upcoming
[Streamlit](https://github.com/streamlit/streamlit) release as well, and
will be updating it as we add new LLM- and LangChain-specific features
to Streamlit.

The idea with this PR is that the LangChain `StreamlitCallbackHandler`
will "auto-update" in a way that keeps it forward- (and backward-)
compatible with Streamlit. If the user has an older Streamlit version
installed, the LangChain `StreamlitCallbackHandler` will be used; if
they have a newer Streamlit version that has an updated
`StreamlitCallbackHandler`, that implementation will be used instead.

(I'm opening this as a draft to get the conversation going and make sure
we're on the same page. We're really excited to land this into
LangChain!)

#### Who can review?

@agola11, @hwchase17
2023-06-22 13:14:28 -07:00
Lance Martin
30f7288082
MD header text splitter returns Documents (#6571)
Return `Documents` from MD header text splitter to simplify UX.

Updates the test as well as example notebooks.
2023-06-22 09:25:38 -07:00