Commit Graph

7144 Commits (bcc71d1a5754c49300aedc9d681e21bcea343015)
 

Author SHA1 Message Date
Bagatur bcc71d1a57
openai[patch]: Release 0.0.5 (#16598) 8 months ago
Bagatur 68f7468754
google-vertexai[patch]: Release 0.0.3 (#16597) 8 months ago
Bagatur 61e876aad8
openai[patch]: Explicitly support embedding dimensions (#16596) 8 months ago
Bagatur 5df8ab574e
infra: move indexing documentation test (#16595) 8 months ago
Bagatur f3d61a6e47
langchain[patch]: Release 0.1.4 (#16592) 8 months ago
Bagatur 61b200947f
community[patch]: Release 0.0.16 (#16591) 8 months ago
Bagatur 75ad0bba2d
openai[patch]: Release 0.0.4 (#16590) 8 months ago
Bagatur 1e3ce338ca
core[patch]: Release 0.1.16 (#16589) 8 months ago
Bagatur 6c89507988
docs: add rag citations page (#16549) 8 months ago
Bagatur 31790d15ec
openai[patch]: accept function_call dict in bind_functions (#16483)
Confusing that you can't pass in a dict
8 months ago
Bagatur db80832e4f
docs: output parser nits (#16588) 8 months ago
Bagatur ef42d9d559
core[patch], community[patch], openai[patch]: consolidate openai tool… (#16485)
… converters

One way to convert anything to an OAI function:
convert_to_openai_function
One way to convert anything to an OAI tool: convert_to_openai_tool
Corresponding bind functions on OAI models: bind_functions, bind_tools
8 months ago
Brian Burgin 148347e858
community[minor]: Add LiteLLM Router Integration (#15588)
community:

  - **Description:**
- Add new ChatLiteLLMRouter class that allows a client to use a LiteLLM
Router as a LangChain chat model.
- Note: The existing ChatLiteLLM integration did not cover the LiteLLM
Router class.
    - Add tests and Jupyter notebook.
  - **Issue:** None
  - **Dependencies:** Relies on existing ChatLiteLLM integration
  - **Twitter handle:** @bburgin_0

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
8 months ago
Bob Lin 35e60728b7
docs: Fix broken urls (#16559) 8 months ago
Bob Lin 6023953ea7
docs: Fix github link (#16560) 8 months ago
JongRok BAEK 3b8eba32f9
anthropic[patch]: Fix message type lookup in Anthropic Partners (#16563)
- **Description:** 

The parameters for user and assistant in Anthropic should be 'ai ->
assistant,' but they are reversed to 'assistant -> ai.'
Below is error code.
```python
anthropic.BadRequestError: Error code: 400 - {'type': 'error', 'error': {'type': 'invalid_request_error', 'message': 'messages: Unexpected role "ai". Allowed roles are "user" or "assistant"'}}
```

[anthropic](7177f3a71f/src/anthropic/types/beta/message_param.py (L13))

  - **Issue:** : #16561
  -  **Dependencies:** : None
   - **Twitter handle:** : None
8 months ago
Dmitry Tyumentsev e86e66bad7
community[patch]: YandexGPT models - add sleep_interval (#16566)
Added sleep between requests to prevent errors associated with
simultaneous requests.
8 months ago
Bagatur e510cfaa23
core[patch]: passthrough BaseRetriever.invoke(**kwargs) (#16551)
Fix for #16547
8 months ago
Anders Åhsman 355ef2a4a6
langchain[patch]: Fix doc-string grammar (#16543)
- **Description:** Small grammar fix in docstring for class
`BaseCombineDocumentsChain`.
8 months ago
Aditya 9dd7cbb447
google-genai: added logic for method get_num_tokens() (#16205)
<!-- Thank you for contributing to LangChain!

Please title your PR "partners: google-genai",

Replace this entire comment with:
- **Description:** : added logic for method get_num_tokens() for
ChatGoogleGenerativeAI , GoogleGenerativeAI,
  - **Issue:** : https://github.com/langchain-ai/langchain/issues/16204,
  - **Dependencies:** : None,
  - **Twitter handle:** @Aditya_Rane

---------

Co-authored-by: adityarane@google.com <adityarane@google.com>
Co-authored-by: Leonid Kuligin <lkuligin@yandex.ru>
8 months ago
James Braza 0785432e7b
langchain-google-vertexai: perserving grounding metadata (#16309)
Revival of https://github.com/langchain-ai/langchain/pull/14549 that
closes https://github.com/langchain-ai/langchain/issues/14548.
8 months ago
Erick Friis adc008407e
exa: init pkg (#16553) 8 months ago
Rave Harpaz c4e9c9ca29
community[minor]: Add OCI Generative AI integration (#16548)
<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

Replace this entire comment with:
- **Description:** Adding Oracle Cloud Infrastructure Generative AI
integration. Oracle Cloud Infrastructure (OCI) Generative AI is a fully
managed service that provides a set of state-of-the-art, customizable
large language models (LLMs) that cover a wide range of use cases, and
which is available through a single API. Using the OCI Generative AI
service you can access ready-to-use pretrained models, or create and
host your own fine-tuned custom models based on your own data on
dedicated AI clusters.
https://docs.oracle.com/en-us/iaas/Content/generative-ai/home.htm
  - **Issue:** None,
  - **Dependencies:** OCI Python SDK,
- **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` from the root
of the package you've modified to check this locally.
Passed

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

we provide unit tests. However, we cannot provide integration tests due
to Oracle policies that prohibit public sharing of api keys.
 
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->

---------

Co-authored-by: Arthur Cheng <arthur.cheng@oracle.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
8 months ago
Bagatur b8768bd6e7
docs: allow pdf download of api ref (#16550)
https://docs.readthedocs.io/en/stable/config-file/v2.html#formats
8 months ago
Leonid Ganeline f6a05e964b
docs: `Hugging Face` update (#16490)
- added missed integrations to the platform page
- updated integration examples: added links and fixed formats
8 months ago
Bagatur c173a69908
langchain[patch]: oai tools output parser nit (#16540)
allow positional init args
8 months ago
arnob-sengupta f9976b9630
core[patch]: consolidate conditional in BaseTool (#16530)
- **Description:** Refactor contradictory conditional to single line
  - **Issue:** #16528
8 months ago
Bagatur 5c2538b9f7
anthropic[patch]: allow pop by field name (#16544)
allow `ChatAnthropicMessages(model=...)`
8 months ago
Harel Gal a91181fe6d
community[minor]: add support for Guardrails for Amazon Bedrock (#15099)
Added support for optionally supplying 'Guardrails for Amazon Bedrock'
on both types of model invocations (batch/regular and streaming) and for
all models supported by the Amazon Bedrock service.

@baskaryan  @hwchase17

```python 
llm = Bedrock(model_id="<model_id>", client=bedrock,
                  model_kwargs={},
                  guardrails={"id": " <guardrail_id>",
                              "version": "<guardrail_version>",
                               "trace": True}, callbacks=[BedrockAsyncCallbackHandler()])

class BedrockAsyncCallbackHandler(AsyncCallbackHandler):
    """Async callback handler that can be used to handle callbacks from langchain."""

    async def on_llm_error(
            self,
            error: BaseException,
            **kwargs: Any,
    ) -> Any:
        reason = kwargs.get("reason")
        if reason == "GUARDRAIL_INTERVENED":
           # kwargs contains additional trace information sent by 'Guardrails for Bedrock' service.
            print(f"""Guardrails: {kwargs}""")


# streaming 
llm = Bedrock(model_id="<model_id>", client=bedrock,
                  model_kwargs={},
                  streaming=True,
                  guardrails={"id": "<guardrail_id>",
                              "version": "<guardrail_version>"})
```

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
8 months ago
Martin Kolb 04651f0248
community[minor]: VectorStore integration for SAP HANA Cloud Vector Engine (#16514)
- **Description:**
This PR adds a VectorStore integration for SAP HANA Cloud Vector Engine,
which is an upcoming feature in the SAP HANA Cloud database
(https://blogs.sap.com/2023/11/02/sap-hana-clouds-vector-engine-announcement/).

  - **Issue:** N/A
- **Dependencies:** [SAP HANA Python
Client](https://pypi.org/project/hdbcli/)
  - **Twitter handle:** @sapopensource

Implementation of the integration:
`libs/community/langchain_community/vectorstores/hanavector.py`

Unit tests:
`libs/community/tests/unit_tests/vectorstores/test_hanavector.py`

Integration tests:
`libs/community/tests/integration_tests/vectorstores/test_hanavector.py`

Example notebook:
`docs/docs/integrations/vectorstores/hanavector.ipynb`

Access credentials for execution of the integration tests can be
provided to the maintainers.

---------

Co-authored-by: sascha <sascha.stoll@sap.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
8 months ago
Leonid Kuligin 1113700b09
google-genai[patch]: better error message when location is not supported (#16535)
Replace this entire comment with:
- **Description:** a better error message when location is not supported
8 months ago
Bob Lin 54dd8e52a8
docs: Updated comments about `n_gpu_layers` in the Metal section (#16501)
Ref: https://github.com/langchain-ai/langchain/issues/16502
8 months ago
Eugene Yurtsev fe382fcf20
CI: more qa template changes (#16533)
More qa template changes
8 months ago
Eugene Yurtsev 06f66f25e1
CI: Update q-a template (#16532)
Update template for QA discussions
8 months ago
Eugene Yurtsev b1b351b37e
CI: more updates to feature request template (#16531)
More updates
8 months ago
Eugene Yurtsev 4fad71882e
CI: Fix ideas template (#16529)
Fix ideas template
8 months ago
Anastasiia Manokhina ce595f0203
docs:Updated integration docs structure for chat/google_vertex_ai_palm (#16201)
Description: 

- checked that the doc chat/google_vertex_ai_palm is using new
functions: invoke, stream etc.
- added Gemini example
- fixed wrong output in Sanskrit example

Issue: https://github.com/langchain-ai/langchain/issues/15664
Dependencies: None
Twitter handle: None
8 months ago
Unai Garay Maestre fdbfa6b2c8
Adds progress bar to VertexAIEmbeddings (#14542)
- **Description:** Adds progress bar to VertexAIEmbeddings 
- **Issue:** related issue
https://github.com/langchain-ai/langchain/issues/13637

Signed-off-by: ugm2 <unaigaraymaestre@gmail.com>

---------

Signed-off-by: ugm2 <unaigaraymaestre@gmail.com>
8 months ago
James Braza 643fb3ab50
langchain-google-vertexai[patch]: more verbose mypy config (#16307)
Flushing out the `mypy` config in `langchain-google-vertexai` to show
error codes and other warnings

This PR also bumps `mypy` to above version 1's stable release
8 months ago
Eugene Yurtsev 8d990ba67b
CI: more update to ideas template (#16524)
Update ideas template
8 months ago
Eugene Yurtsev 63da14d620
CI: redirect feature requests to ideas in discussions (#16522)
Redirect feature requests to ideas in discussions
8 months ago
Erick Friis 8d299645f9
docs: rm output (#16519) 8 months ago
Eugene Yurtsev dfd94fb2f0
CI: Update issue template (#16517)
More updates to the ISSUE template
8 months ago
Lance Martin 0b740ebd49
Update SQL agent toolkit docs (#16409) 8 months ago
Francisco Ingham 13cf4594f4
docs: added a few suggestions for sql docs (#16508) 8 months ago
Eugene Yurtsev 6004e9706f
Docs: Add streaming section (#16468)
Adds a streaming section to LangChain documentation, explaining
`stream`/`astream` API and `astream_events` API.
8 months ago
Tipwheal 66aafc0573
Docs: typo in tool use quick start page (#16494)
Minor typo fix
8 months ago
Jeremi Joslin 9e95699277
community[patch]: Fix error message when litellm is not installed (#16316)
The error message was mentioning the wrong package. I updated it to the
correct one.
8 months ago
bachr b3ed98dec0
community[patch]: avoid KeyError when language not in LANGUAGE_SEGMENTERS (#15212)
**Description:**

Handle unsupported languages in same way as when none is provided 
 
**Issue:**

The following line will throw a KeyError if the language is not
supported.
```python
self.Segmenter = LANGUAGE_SEGMENTERS[language]
```
E.g. when using `Language.CPP` we would get `KeyError: <Language.CPP:
'cpp'>`

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
8 months ago
Nuno Campos 3f38e1a457
Remove double line (#16426)
<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
8 months ago