Commit Graph

5520 Commits (60d009f75a3cab23085e53a5413d9125474a840f)
 

Author SHA1 Message Date
hiigao f818ec49b8
Encapsulate alicloud pai-eas access method for chatmodels and llms (#11852)
### Description: 
To provide an eas llm service access methods in this pull request by
impletementing `PaiEasEndpoint` and `PaiEasChatEndpoint` classes in
`langchain.llms` and `langchain.chat_models` modules. Base on this pr,
langchain users can build up a chain to call remote eas llm service and
get the llm inference results.

### About EAS Service
EAS is a Alicloud product on Alibaba Cloud Machine Learning Platform for
AI which is short for AliCloud PAI. EAS provides model inference
deployment services for the users. We build up a llm inference services
on EAS with a general llm docker images. Therefore, end users can
quickly setup their llm remote instances to load majority of the
hugginface llm models, and serve as a backend for most of the llm apps.

### Dependencies
This pr does't involve any new dependencies.

---------

Co-authored-by: 子洪 <gaoyihong.gyh@alibaba-inc.com>
10 months ago
Shinya Maeda 1da6d92369
fix: superfluous List Parser doc (#12014) 10 months ago
John Mai a6b483dcbc
Supported RetryOutputParser & RetryWithErrorOutputParser max_retries (#11903)
Description: Supported RetryOutputParser & RetryWithErrorOutputParser
max_retries
- max_retries: Maximum number of retries to parser.

Issue: None
Dependencies: None
Tag maintainer: @baskaryan 
Twitter handle:
10 months ago
Hugues Chocart 008c7df80d
[LLMonitorCallbackHandler] Refactor + add llmonitor-py dependency (#11948)
We now require uses to have the pip package `llmonitor` installed. It
allows us to have cleaner code and avoid duplicates between our library
and our code in Langchain.
10 months ago
Sian Cao 77fc2f7644
fix: impl missing embeddings method (#10823)
FAISS does not implement embeddings method and use embed_query to
embedding texts which is wrong for some embedding models.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
10 months ago
Holt Skinner 2661dc94f3
feat: Google Vertex AI Search Retriever - Add support for Website Data Stores (#11736)
- Only works for Data stores with Advanced Website Indexing
-
https://cloud.google.com/generative-ai-app-builder/docs/about-advanced-features
- Minor restructuring - Follow up to #10513
- Remove outdated docs (readded in
https://github.com/langchain-ai/langchain/pull/11620)
  - Move legacy class into new py file to clean up the directory
- Shouldn't cause backwards compatibility issues as the import works the
same way for users
10 months ago
Shorthills AI 4b6fdd7bf0
Update modal.py (#11588)
feat: Raise KeyError when 'prompt' key is missing in JSON response

This commit updates the error handling in the code to raise a KeyError
when the 'prompt' key is not found in the JSON response. This change
makes the code more explicit about the nature of the error, helping to
improve clarity and debugging.

@baskaryan, @eyurtsev.
10 months ago
Surav Shrestha 2038c7fd5d
fix typo in multi_language.ipynb (#12009)
exprience -> experience
10 months ago
William FH dfb4baa3f9
Fix Fireworks Callbacks (#12003)
I may be missing something but it seems like we inappropriately overrode
the 'stream()' method, losing callbacks in the process. I don't think
(?) it gave us anything in this case to customize it here?

See new trace:

https://smith.langchain.com/public/fbb82825-3a16-446b-8207-35622358db3b/r

and confirmed it streams.

Also fixes the stopwords issues from #12000
10 months ago
Lance Martin 12f8e87a0e
LLaMA2 SQL cookbook clean (#12007) 10 months ago
Harrison Chase bdecc5bade
Harrison/lcel configuration (#11997) 10 months ago
Lance Martin 26d0858a60
Update LLaMA2 SQL notebook (#11995) 10 months ago
Wang Wei e26559f512
Add ERNIE-Bot-4 model support for ErnieBotChat. (#11969)
- **Description:** According to the document
https://cloud.baidu.com/doc/WENXINWORKSHOP/s/clntwmv7t, add ERNIE-Bot-4
model support for ErnieBotChat.
- **Dependencies:** Before using the ERNIE-Bot-4, you should have the
model's access authority.
10 months ago
Alfrick Opidi 71b0f51003
Update clarifai.mdx (#11964)
Corrected broken link
10 months ago
Alfrick Opidi 5ba7a7d2bc
Update clarifai.ipynb (#11963)
documents=docs not required when making a vector search on an existing
Clarifai application
10 months ago
Bagatur 642d2e4b67
caps not title for cookbooks descriptions (#11993) 10 months ago
Bagatur fd7ab539c8
add cookbook readme (#11992) 10 months ago
Eugene Yurtsev f4bec9686d
Add more security notes (#11990)
Add more security notes
10 months ago
Eugene Yurtsev 3d81c76160
Add security notes to agent toolkits (#11989)
Add more security notes to agent toolkits.
10 months ago
Leonid Ganeline b81a4c1d94
docstrings added (#11988)
Added docstrings. Some docsctrings formatting.
10 months ago
Bagatur 35c7c1f050
bump 317 (#11986) 10 months ago
Bagatur 122af2effe
fix chroma from_texts bug (#11984) 10 months ago
Erick Friis c149954cc5
Hub Runnable (#11946)
Adds `langchain.runnables.hub.HubRunnable` for pulling configurable
objects from the hub
10 months ago
Owen 9e24626e87
chore: remove duplicated export variables (#11962)
- **Description:** remove duplicated `__all__` variables
10 months ago
Nuno Campos 6bd9c1d2b3
Make prompt validation opt-in (#11973)
By default replace input_variables with the correct value

<!-- Thank you for contributing to LangChain!

Replace this entire 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!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

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. It lives in `docs/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
10 months ago
Nuno Campos 9bc7e1851a
Ensure dict() does not raise not implemented error, which should instead be raised in our custom method save() (#11970)
.dict() is a Pydantic method that cannot raise exceptions, as it is used
eg. in `__eq__`

<!-- Thank you for contributing to LangChain!

Replace this entire 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!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

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. It lives in `docs/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
10 months ago
Nuno Campos 653cf56e0e Lint 10 months ago
Predrag Gruevski debcf053eb
Fix `invalid escape sequence` warnings by using raw strings for regexes. (#11943)
This code also generates warnings when our users' apps hit it, which is
annoying and doesn't look great. Let's fix it.
10 months ago
Nuno Campos e4ae690244 Sort order 10 months ago
Bagatur 8e1b1db90d
bearly api key docs (#11981) 10 months ago
Nuno Campos b753bf3323 Make prompt validation opt-in
By default replace input_variables with the correct value
10 months ago
Nuno Campos 202acce0c9 Ensure dict() does not raise not implemented error, which should instead be raised in our custom method save() 10 months ago
Predrag Gruevski 392df7b2e3
Type hints on varargs and kwargs that take anything should be `Any`. (#11950)
Type hinting `*args` as `List[Any]` means that each positional argument
should be a list. Type hinting `**kwargs` as `Dict[str, Any]` means that
each keyword argument should be a dict of strings.

This is almost never what we actually wanted, and doesn't seem to be
what we want in any of the cases I'm replacing here.
10 months ago
volodymyr-memsql 7f17ce3742
SingleStoreDBChatMessageHistory: Add jupiter notebook with usage example (#11941)
The Docs folder changed its structure, and the notebook example for
SingleStoreDChatMessageHistory has not been copied to the new place due
to a merge conflict. Adding the example to the correct place.

Co-authored-by: Volodymyr Tkachuk <vtkachuk-ua@singlestore.com>
10 months ago
Eugene Yurtsev 908c7bf33e
Add documentation to tools (#11938)
Add security notes to tools

---------

Co-authored-by: Predrag Gruevski <2348618+obi1kenobi@users.noreply.github.com>
10 months ago
Eugene Yurtsev 43dc669332
Update playwright documentation (#11949)
Add security note to playwright tool
10 months ago
Daniel Chalef 2beb767ae5
zep: Memory Retriever MMR Support & Docs Updates (#11954)
- Update Zep Memory and Retriever docstrings
- Zep Memory Retriever: Add support for native MMR
- Add MMR example to existing ZepRetriever Notebook

@baskaryan
10 months ago
William FH a27fa9bf10
Use traceable context (#11896)
Example

```
from langchain.schema.runnable import RunnableLambda
from langsmith import traceable

chain = RunnableLambda(lambda x: x)

@traceable(run_type = "chain")
def my_traceable(a):
    chain.invoke(a)
my_traceable(5)
```

Would have a nested result.

This would NOT work for interleaving chains and traceables. E.g., things
like thiswould still not work well

```
from langchain.schema.runnable import RunnableLambda
from langsmith import traceable

@traceable()
def other_traceable(a):
    return a

def foo(x):
    return other_traceable(x)
    
chain = RunnableLambda(foo)

@traceable(run_type = "chain")
def my_traceable(a):
    chain.invoke(a)
my_traceable(5)
```
10 months ago
Predrag Gruevski dcd0392423
Upgrade to newer black (23.10) and ruff (first 0.1.x!) versions. (#11944)
Minor lint dependency version upgrade to pick up latest functionality.

Ruff's new v0.1 version comes with lots of nice features, like
fix-safety guarantees and a preview mode for not-yet-stable features:
https://astral.sh/blog/ruff-v0.1.0
10 months ago
Trayan Azarov 1fd21ed21c
Chroma batching (#11203)
- **Description:** Chroma >= 0.4.10 added support for batch sizes
validation of add/upsert. This batch size is dependent on the SQLite
limits of the target system and varies. In this change, for
Chroma>=0.4.10 batch splitting was added as the aforementioned
validation is starting to surface in the Chroma community (users using
LC)
 - **Issue:** N/A
 - **Dependencies:** N/A
 - **Tag maintainer:** @eyurtsev
 - **Twitter handle:** t_azarov
10 months ago
Guy Korland 9373b9c004
Add Graph interface (#11012)
Replace this entire comment with:
  - **Description:** Add a Graph interface
  - **Tag maintainer:** @baskaryan @hwchase17 
  - **Twitter handle:** @g_korland
10 months ago
DanielZzz b647505280
feat: support ChatModels Qianfan `QianfanChatEndpoint` function_call (#11107)
- **Description:** 
* feature for `QianfanChatEndpoint` function_call ability, add
integration_test for it
    * add `model`, `endpoint` supported in calling params
    * add raw response in ChatModel Message
- **Issue:** 
    * #10867 
    * #11105 
    * #10215
- **Dependencies:** no
- **Tag maintainer:** @baskaryan 
- **Twitter handle:** no
10 months ago
M Bharat lal 67300567d3
GCSFileLoader retrieve blob custom metadata and append to document metadata (#11066)
- **Description:** GCSFileLoader retrieve blob's custom metadata and
append to document's metadata
- **Issue:** #9975,
- **Tag maintainer:** @baskaryan please review

Co-authored-by: b0l00ib <bharat.lal@walmart.com>
10 months ago
staoxiao 23c261ba57
Update bge_huggingface.ipynb (#8960)
- Description: Considering the similarity computation method of
[BGE](https://github.com/FlagOpen/FlagEmbedding) model is cosine
similarity, set normalize_embeddings to be True.
- Tag maintainer: @baskaryan

Co-authored-by: Erick Friis <erick@langchain.dev>
10 months ago
billytrend-cohere f4742dce50
Add Cohere retrieval augmented generation to retrievers (#11483)
Add Cohere retrieval augmented generation to retrievers

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
10 months ago
刘 方瑞 0a24ac7388
Revised notebook and add delete to MyScale vector store (#11848)
- **Description:** 
  - Add `.delete` to myscale vector store. 
  - Revised vector store notebooks
- **Tag maintainer:** @baskaryan 
- **Twitter handle:** @myscaledb @mpsk_liu
10 months ago
John Mai 3fb5e4d185
Add Baichuan chat model (#11923)
Description: A large language models developed by Baichuan Intelligent
Technology,https://www.baichuan-ai.com/home
Issue: None
Dependencies: None
Tag maintainer:
Twitter handle:
10 months ago
Eugene Yurtsev 9ecb7240a4
Add security note to recursive url loader (#11934)
Add security note to recursive loader
10 months ago
maks-operlejn-ds 42dcc502c7
Anonymizer small fixes (#11915) 10 months ago
Eugene Yurtsev 90e9ec6962
Sitemap specify default filter url (#11925)
Specify default filter URL in sitemap loader and add a security note

---------

Co-authored-by: Predrag Gruevski <2348618+obi1kenobi@users.noreply.github.com>
10 months ago