Commit Graph

1684 Commits

Author SHA1 Message Date
Davis Chase
3b609642ae
Self-query with generic query constructor (#3607)
Alternate implementation of #3452 that relies on a generic query
constructor chain and language and then has vector store-specific
translation layer. Still refactoring and updating examples but general
structure is there and seems to work s well as #3452 on exampels

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-27 08:36:00 -07:00
plutopulp
6d6fd1b9e1
Add PipelineAI LLM integration (#3644)
Add PipelineAI LLM integration
2023-04-27 08:22:26 -07:00
Harrison Chase
a35bbbfa9e
Harrison/lancedb (#3634)
Co-authored-by: Minh Le <minhle@canva.com>
2023-04-27 08:14:36 -07:00
Nuno Campos
52b5290810
Update README.md (#3643) 2023-04-27 08:14:09 -07:00
Eugene Yurtsev
5d02010763
Introduce Blob and Blob Loader interface (#3603)
This PR introduces a Blob data type and a Blob loader interface.

This is the first of a sequence of PRs that follows this proposal: 

https://github.com/hwchase17/langchain/pull/2833

The primary goals of these abstraction are:

* Decouple content loading from content parsing code.
* Help duplicated content loading code from document loaders.
* Make lazy loading a default for langchain.
2023-04-27 09:45:25 -04:00
Matt Robinson
8e10ac422e
enhancement: add elements mode to UnstructuredURLLoader (#3456)
### Summary

Updates the `UnstructuredURLLoader` to include a "elements" mode that
retains additional metadata from `unstructured`. This makes
`UnstructuredURLLoader` consistent with other unstructured loaders,
which also support "elements" mode. Patched mode into the existing
`UnstructuredURLLoader` class instead of inheriting from
`UnstructuredBaseLoader` because it significantly simplified the
implementation.

### Testing

This should still work and show the url in the source for the metadata

```python
from langchain.document_loaders import UnstructuredURLLoader

urls = ["https://www.understandingwar.org/sites/default/files/Russian%20Offensive%20Campaign%20Assessment%2C%20April%2011%2C%202023.pdf"]

loader = UnstructuredURLLoader(urls=urls, headers={"Accept": "application/json"}, strategy="fast")
docs = loader.load()
print(docs[0].page_content[:1000])
docs[0].metadata
``` 

This should now work and show additional metadata from `unstructured`.

This should still work and show the url in the source for the metadata

```python
from langchain.document_loaders import UnstructuredURLLoader

urls = ["https://www.understandingwar.org/sites/default/files/Russian%20Offensive%20Campaign%20Assessment%2C%20April%2011%2C%202023.pdf"]

loader = UnstructuredURLLoader(urls=urls, headers={"Accept": "application/json"}, strategy="fast", mode="elements")
docs = loader.load()
print(docs[0].page_content[:1000])
docs[0].metadata
```
2023-04-26 22:09:45 -07:00
Eduard van Valkenburg
a3e3f26090
Some more PowerBI pydantic and import fixes (#3461) 2023-04-26 22:09:12 -07:00
Harrison Chase
ab749fa1bb
Harrison/opensearch logic (#3631)
Co-authored-by: engineer-matsuo <95115586+engineer-matsuo@users.noreply.github.com>
2023-04-26 22:08:03 -07:00
ccw630
cf384dcb7f
Supports async in SequentialChain/SimpleSequentialChain (#3503) 2023-04-26 22:07:20 -07:00
Ehsan M. Kermani
4a246e2fd6
Allow clearing cache and fix gptcache (#3493)
This PR

* Adds `clear` method for `BaseCache` and implements it for various
caches
* Adds the default `init_func=None` and fixes gptcache integtest
* Since right now integtest is not running in CI, I've verified the
changes by running `docs/modules/models/llms/examples/llm_caching.ipynb`
(until proper e2e integtest is done in CI)
2023-04-26 22:03:50 -07:00
Howard Su
83e871f1ff
Fix Invalid Request using AzureOpenAI (#3522)
This fixes the error when calling AzureOpenAI of gpt-35-turbo model.

The error is:
InvalidRequestError: logprobs, best_of and echo parameters are not
available on gpt-35-turbo model. Please remove the parameter and try
again. For more details, see
https://go.microsoft.com/fwlink/?linkid=2227346.
2023-04-26 22:00:09 -07:00
Luoyger
f5aa767ef1
add --no-sandbox for chrome in url_selenium (#3589)
without --no-sandbox param, load documents from url by selenium in
chrome occured error below:

```Traceback (most recent call last):
  File "/data//playgroud/try_langchain.py", line 343, in <module>
    langchain_doc_loader()
  File "/data//playgroud/try_langchain.py", line 67, in langchain_doc_loader
    documents = loader.load()
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/langchain/document_loaders/url_selenium.py", line 102, in load
    driver = self._get_driver()
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/langchain/document_loaders/url_selenium.py", line 76, in _get_driver
    return Chrome(options=chrome_options)
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/selenium/webdriver/chrome/webdriver.py", line 80, in __init__
    super().__init__(
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/selenium/webdriver/chromium/webdriver.py", line 104, in __init__
    super().__init__(
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/selenium/webdriver/remote/webdriver.py", line 286, in __init__
    self.start_session(capabilities, browser_profile)
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/selenium/webdriver/remote/webdriver.py", line 378, in start_session
    response = self.execute(Command.NEW_SESSION, parameters)
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/selenium/webdriver/remote/webdriver.py", line 440, in execute
    self.error_handler.check_response(response)
  File "/install/anaconda3-env/envs/python3.10/lib/python3.10/site-packages/selenium/webdriver/remote/errorhandler.py", line 245, in check_response
    raise exception_class(message, screen, stacktrace)
selenium.common.exceptions.WebDriverException: Message: unknown error: Chrome failed to start: exited abnormally.
  (unknown error: DevToolsActivePort file doesn't exist)
  (The process started from chrome location /usr/bin/google-chrome is no longer running, so ChromeDriver is assuming that Chrome has crashed.)
Stacktrace:
#0 0x55cf8da1bfe3 <unknown>
#1 0x55cf8d75ad36 <unknown>
#2 0x55cf8d783b20 <unknown>
#3 0x55cf8d77fa9b <unknown>
#4 0x55cf8d7c1af7 <unknown>
#5 0x55cf8d7c111f <unknown>
#6 0x55cf8d7b8693 <unknown>
#7 0x55cf8d78b03a <unknown>
#8 0x55cf8d78c17e <unknown>
#9 0x55cf8d9dddbd <unknown>
#10 0x55cf8d9e1c6c <unknown>
#11 0x55cf8d9eb4b0 <unknown>
#12 0x55cf8d9e2d63 <unknown>
#13 0x55cf8d9b5c35 <unknown>
#14 0x55cf8da06138 <unknown>
#15 0x55cf8da062c7 <unknown>
#16 0x55cf8da14093 <unknown>
#17 0x7f3da31a72de start_thread
```

add option `chrome_options.add_argument("--no-sandbox")` for chrome.
2023-04-26 21:48:43 -07:00
Shukri
fac4f36a87
Update models used for embeddings in the weaviate example (#3594)
Use text-embedding-ada-002 because it [outperforms all other
models](https://openai.com/blog/new-and-improved-embedding-model).
2023-04-26 21:48:08 -07:00
cs0lar
440c98e24b
Fix/issue 2695 (#3608)
## Background
fixes #2695  

## Changes
The `add_text` method uses the internal embedding function if one was
passes to the `Weaviate` constructor.
NOTE: the latest merge on the `Weaviate` class made the specification of
a `weaviate_api_key` mandatory which might not be desirable for all
users and connection methods (for example weaviate also support Embedded
Weaviate which I am happy to add support to here if people think it's
desirable). I wrapped the fetching of the api key into a try catch in
order to allow the `weaviate_api_key` to be unspecified. Do let me know
if this is unsatisfactory.

## Test Plan
added test for `add_texts` method.
2023-04-26 21:45:03 -07:00
brian-tecton-ai
615812581e
Add Tecton example to the "Connecting to a Feature Store" example notebook (#3626)
This PR adds a similar example to the Feast example, using the [Tecton
Feature Platform](https://www.tecton.ai/) and features from the [Tecton
Fundamentals
Tutorial](https://docs.tecton.ai/docs/tutorials/tecton-fundamentals).
2023-04-26 21:38:50 -07:00
mbchang
3b7d27d39e
new example: multiagent dialogue with decentralized speaker selection (#3629)
This notebook showcases how to implement a multi-agent simulation
without a fixed schedule for who speaks when. Instead the agents decide
for themselves who speaks. We can implement this by having each agent
bid to speak. Whichever agent's bid is the highest gets to speak.

We will show how to do this in the example below that showcases a
fictitious presidential debate.
2023-04-26 21:37:36 -07:00
leo-gan
36c59e0c25
Arxiv document loader (#3627)
It makes sense to use `arxiv` as another source of the documents for
downloading.
- Added the `arxiv` document_loader, based on the
`utilities/arxiv.py:ArxivAPIWrapper`
- added tests
- added an example notebook
- sorted `__all__` in `__init__.py` (otherwise it is hard to find a
class in the very long list)
2023-04-26 21:04:56 -07:00
Tim Asp
539142f8d5
Add way to get serpapi results async (#3604)
Sometimes it's nice to get the raw results from serpapi, and we're
missing the async version of this function.
2023-04-26 16:37:03 -07:00
Zander Chase
443a893ffd
Align names of search tools (#3620)
Tools for Bing, DDG and Google weren't consistent even though the
underlying implementations were.
All three services now have the same tools and implementations to easily
switch and experiment when building chains.
2023-04-26 16:21:34 -07:00
Maciej Bryński
aa345a4bb7
Add get_text_separator parameter to BSHTMLLoader (#3551)
By default get_text doesn't separate content of different HTML tag.
Adding option for specifying separator helps with document splitting.
2023-04-26 16:10:16 -07:00
Bhupendra Aole
568c4f0d81
Close dataframe column names are being treated as one by the LLM (#3611)
We are sending sample dataframe to LLM with df.head().
If the column names are close by, LLM treats two columns names as one,
returning incorrect results.


![image](https://user-images.githubusercontent.com/4707543/234678692-97851fa0-9e12-44db-92ec-9ad9f3545ae2.png)

In the above case the LLM uses **Org Week** as the column name instead
of **Week** if asked about a specific week.

Returning head() as a markdown separates out the columns names and thus
using correct column name.


![image](https://user-images.githubusercontent.com/4707543/234678945-c6d7b218-143e-4e70-9e17-77dc64841a49.png)
2023-04-26 16:05:53 -07:00
James O'Dwyer
860fa59cd3
add metal to ecosystem (#3613) 2023-04-26 15:57:48 -07:00
Zander Chase
ee670c448e
Persistent Bash Shell (#3580)
Clean up linting and make more idiomatic by using an output parser

---------

Co-authored-by: FergusFettes <fergusfettes@gmail.com>
2023-04-26 15:20:28 -07:00
Ilyes Bouchada
c5451f4298
Update docker-compose.yaml (#3582)
The following error gets returned when trying to launch
langchain-server:

ERROR: The Compose file
'/opt/homebrew/lib/python3.11/site-packages/langchain/docker-compose.yaml'
is invalid because:
services.langchain-db.expose is invalid: should be of the format
'PORT[/PROTOCOL]'

Solution:
Change line 28 from - 5432:5432 to - 5432
2023-04-26 15:11:59 -07:00
Kátia Nakamura
e1a4fc55e6
Add docs for Fly.io deployment (#3584)
A minimal example of how to deploy LangChain to Fly.io using Flask.
2023-04-26 14:41:08 -07:00
Chirag Bhatia
08478deec5
Fixed typo for HuggingFaceHub (#3612)
The current text has a typo. This PR contains the corrected spelling for
HuggingFaceHub
2023-04-26 14:33:31 -07:00
Charlie Holtz
246710def9
Fix Replicate llm response to handle iterator / multiple outputs (#3614)
One of our users noticed a bug when calling streaming models. This is
because those models return an iterator. So, I've updated the Replicate
`_call` code to join together the output. The other advantage of this
fix is that if you requested multiple outputs you would get them all –
previously I was just returning output[0].

I also adjusted the demo docs to use dolly, because we're featuring that
model right now and it's always hot, so people won't have to wait for
the model to boot up.

The error that this fixes:
```
> llm = Replicate(model=“replicate/flan-t5-xl:eec2f71c986dfa3b7a5d842d22e1130550f015720966bec48beaae059b19ef4c”)
>  llm(“hello”)
> Traceback (most recent call last):
  File "/Users/charlieholtz/workspace/dev/python/main.py", line 15, in <module>
    print(llm(prompt))
  File "/opt/homebrew/lib/python3.10/site-packages/langchain/llms/base.py", line 246, in __call__
    return self.generate([prompt], stop=stop).generations[0][0].text
  File "/opt/homebrew/lib/python3.10/site-packages/langchain/llms/base.py", line 140, in generate
    raise e
  File "/opt/homebrew/lib/python3.10/site-packages/langchain/llms/base.py", line 137, in generate
    output = self._generate(prompts, stop=stop)
  File "/opt/homebrew/lib/python3.10/site-packages/langchain/llms/base.py", line 324, in _generate
    text = self._call(prompt, stop=stop)
  File "/opt/homebrew/lib/python3.10/site-packages/langchain/llms/replicate.py", line 108, in _call
    return outputs[0]
TypeError: 'generator' object is not subscriptable
```
2023-04-26 14:26:33 -07:00
Harrison Chase
7536912125
bump ver 150 (#3599) 2023-04-26 08:29:09 -07:00
Chirag Bhatia
f174aa7712
Fix broken Cerebrium link in documentation (#3554)
The current hyperlink has a typo. This PR contains the corrected
hyperlink to Cerebrium docs
2023-04-26 08:11:58 -07:00
Harrison Chase
d880775e5d
Harrison/plugnplai (#3573)
Co-authored-by: Eduardo Reis <edu.pontes@gmail.com>
2023-04-26 08:09:34 -07:00
Zander Chase
85dae78548
Confluence beautifulsoup (#3576)
Co-authored-by: Theau Heral <theau.heral@ln.email.gs.com>
2023-04-25 23:40:06 -07:00
Mike Wang
64501329ab
[simple] updated annotation in load_tools.py (#3544)
- added a few missing annotation for complex local variables.
- auto formatted.
- I also went through all other files in agent directory. no seeing any
other missing piece. (there are several prompt strings not annotated,
but I think it’s trivial. Also adding annotation will make it harder to
read in terms of indents.) Anyway, I think this is the last PR in
agent/annotation.
2023-04-25 23:30:49 -07:00
Zander Chase
d6d697a41b
Sentence Transformers Aliasing (#3541)
The sentence transformers was a dup of the HF one. 

This is a breaking change (model_name vs. model) for anyone using
`SentenceTransformerEmbeddings(model="some/nondefault/model")`, but
since it was landed only this week it seems better to do this now rather
than doing a wrapper.
2023-04-25 23:29:20 -07:00
Eric Peter
603ea75bcd
Fix docs error for google drive loader (#3574) 2023-04-25 22:52:59 -07:00
CG80499
cfd34e268e
Add ReAct eval chain (#3161)
- Adds GPT-4 eval chain for arbitrary agents using any set of tools
- Adds notebook

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-25 21:22:25 -07:00
mbchang
4bc209c6f7
example: multi player dnd (#3560)
This notebook shows how the DialogueAgent and DialogueSimulator class
make it easy to extend the [Two-Player Dungeons & Dragons
example](https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html)
to multiple players.

The main difference between simulating two players and multiple players
is in revising the schedule for when each agent speaks

To this end, we augment DialogueSimulator to take in a custom function
that determines the schedule of which agent speaks. In the example
below, each character speaks in round-robin fashion, with the
storyteller interleaved between each player.
2023-04-25 21:20:39 -07:00
James Brotchie
5fdaa95e06
Strip surrounding quotes from requests tool URLs. (#3563)
Often an LLM will output a requests tool input argument surrounded by
single quotes. This triggers an exception in the requests library. Here,
we add a simple clean url function that strips any leading and trailing
single and double quotes before passing the URL to the underlying
requests library.

Co-authored-by: James Brotchie <brotchie@google.com>
2023-04-25 21:20:26 -07:00
Harrison Chase
f4829025fe
add feast nb (#3565) 2023-04-25 17:46:06 -07:00
Harrison Chase
47da5f0e58
Harrison/streamlit handler (#3564)
Co-authored-by: kurupapi <37198601+kurupapi@users.noreply.github.com>
2023-04-25 17:26:30 -07:00
Filip Michalsky
49593a3e41
Notebook example: Context-Aware AI Sales Agent (#3547)
I would like to contribute with a jupyter notebook example
implementation of an AI Sales Agent using `langchain`.

The bot understands the conversation stage (you can define your own
stages fitting your needs)
using two chains:

1. StageAnalyzerChain - takes context and LLM decides what part of sales
conversation is one in
2. SalesConversationChain - generate next message

Schema:

https://images-genai.s3.us-east-1.amazonaws.com/architecture2.png

my original repo: https://github.com/filip-michalsky/SalesGPT

This example creates a sales person named Ted Lasso who is trying to
sell you mattresses.

Happy to update based on your feedback.

Thanks, Filip
https://twitter.com/FilipMichalsky
2023-04-25 16:14:33 -07:00
Harrison Chase
52d95ec47d
anthropic docs: deprecated LLM, add chat model (#3549) 2023-04-25 16:11:14 -07:00
mbchang
628e93a9a0
docs: simplification of two agent d&d simulation (#3550)
Simplifies the [Two Agent
D&D](https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html)
example with a cleaner, simpler interface that is extensible for
multiple agents.

`DialogueAgent`:
- `send()`: applies the chatmodel to the message history and returns the
message string
- `receive(name, message)`: adds the `message` spoken by `name` to
message history

The `DialogueSimulator` class takes a list of agents. At each step, it
performs the following:
1. Select the next speaker
2. Calls the next speaker to send a message 
3. Broadcasts the message to all other agents
4. Update the step counter.
The selection of the next speaker can be implemented as any function,
but in this case we simply loop through the agents.
2023-04-25 16:10:32 -07:00
apurvsibal
af7906f100
Update Alchemy Key URL (#3559)
Update Alchemy Key URL in Blockchain Document Loader. I want to say
thank you for the incredible work the LangChain library creators have
done.

I am amazed at how seamlessly the Loader integrates with Ethereum
Mainnet, Ethereum Testnet, Polygon Mainnet, and Polygon Testnet, and I
am excited to see how this technology can be extended in the future.

@hwchase17 - Please let me know if I can improve or if I have missed any
community guidelines in making the edit? Thank you again for your hard
work and dedication to the open source community.
2023-04-25 16:08:42 -07:00
Tiago De Gaspari
4d53cefbe9
Fix agents' notebooks outputs (#3517)
Fix agents' notebooks to make the answer reflect what is being asked by
the user.
2023-04-25 16:06:47 -07:00
engkheng
5680fb6894
Fix typo in Prompts Templates Getting Started page (#3514)
`from_templates` -> `from_template`
2023-04-25 16:05:13 -07:00
Vincent
9e36d7b82c
adding add_documents and aadd_documents to class RedisVectorStoreRetriever (#3419)
Ran into this issue In vectorstores/redis.py when trying to use the
AutoGPT agent with redis vector store. The error I received was

`
langchain/experimental/autonomous_agents/autogpt/agent.py", line 134, in
run
    self.memory.add_documents([Document(page_content=memory_to_add)])
AttributeError: 'RedisVectorStoreRetriever' object has no attribute
'add_documents'
`

Added the needed function to the class RedisVectorStoreRetriever which
did not have the functionality like the base VectorStoreRetriever in
vectorstores/base.py that, for example, vectorstores/faiss.py has
2023-04-25 13:53:20 -07:00
Davis Chase
d18b0caf0e
Add Anthropic default request timeout (#3540)
thanks @hitflame!

---------

Co-authored-by: Wenqiang Zhao <hitzhaowenqiang@sina.com>
Co-authored-by: delta@com <delta@com>
2023-04-25 11:40:41 -07:00
Zander Chase
b49ee372f1
Change Chain Docs (#3537)
Co-authored-by: engkheng <60956360+outday29@users.noreply.github.com>
2023-04-25 10:51:09 -07:00
Ikko Eltociear Ashimine
cf71b5d396
fix typo in comet_tracking.ipynb (#3505)
intializing -> initializing
2023-04-25 10:50:58 -07:00
Zander Chase
64bbbf2cc2
Add DDG to load_tools (#3535)
Fix linting

---------

Co-authored-by: Mike Wang <62768671+skcoirz@users.noreply.github.com>
2023-04-25 10:40:37 -07:00