Commit Graph

299 Commits

Author SHA1 Message Date
harry-cohere
beab9adffb
cohere: Improve integration test stability, fix documents bug (#19929)
**Description**: Improves the stability of all Cohere partner package
integration tests. Fixes a bug with document parsing (both dicts and
Documents are handled).
2024-04-02 11:22:30 -07:00
harry-cohere
37fc1c525a
cohere: simplify integration test (#19928)
**Description**: This PR simplifies an integration test within the
Cohere partner package:
 * It no longer relies on exact model answers
 * It no longer relies on a third party tool
2024-04-02 10:57:25 -07:00
billytrend-cohere
de6c0cf248
cohere, docs: update imports and installs to langchain_cohere (#19918)
cohere: update imports and installs to langchain_cohere

---------

Co-authored-by: Harry M <127103098+harry-cohere@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-02 09:47:58 -07:00
Erick Friis
146d1a6347
cohere[patch]: release 0.1.0rc2 (#19924) 2024-04-02 16:24:23 +00:00
harry-cohere
e2b83c87b1
cohere[patch]: Add multihop tool agent (#19919)
**Description**: Adds an agent that uses Cohere with multiple hops and
multiple tools.

This PR is a continuation of
https://github.com/langchain-ai/langchain/pull/19650 - which was
previously approved. Conceptually nothing has changed, but this PR has
extra fixes, documentation and testing.

---------

Co-authored-by: BeatrixCohere <128378696+BeatrixCohere@users.noreply.github.com>
Co-authored-by: Erick Friis <erickfriis@gmail.com>
2024-04-02 09:18:50 -07:00
Massimiliano Pronesti
06dac394a6
cohere[patch]: support request timeout in BaseCohere (#19641)
As in #19346, this PR exposes `request_timeout` in `BaseCohere`, while
`max_retires` is no longer a parameter of the beneath client
(`cohere.Client`) and it is already configured in
`langchain_cohere.llms.Cohere`.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-04-01 14:16:32 -07:00
Erick Friis
0b0a55192f
robocorp[patch]: fix core min version (#19879) 2024-04-01 11:34:14 -07:00
Mikko Korpela
3f06cef60c
robocorp[patch]: Fix nested arguments descriptors and tool names (#19707)
Thank you for contributing to LangChain!

- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
  - Example: "community: add foobar LLM"


- [x] **PR message**:
- **Description:** Fix argument translation from OpenAPI spec to OpenAI
function call (and similar)
- **Issue:** OpenGPTs failures with calling Action Server based actions.
    - **Dependencies:** None
    - **Twitter handle:** mikkorpela


- [x] **Add tests and docs**: 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.~


- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
2024-04-01 11:29:39 -07:00
Erick Friis
4fbdc2a7ee
openai[patch]: remove openai chunk size validation (#19878) 2024-04-01 18:26:06 +00:00
Erick Friis
e3ed6a7c28
ai21[patch]: fix core dep (#19874) 2024-04-01 10:48:16 -07:00
Nuno Campos
aa5797d908
openai[patch]: Partially Revert Update openai chat model to new base class interface (#19871)
Partially Reverts langchain-ai/langchain#19729

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-01 10:31:06 -07:00
Erick Friis
be92cf57ca
openai[patch]: fix azure embedding length check (#19870) 2024-04-01 10:26:15 -07:00
Erick Friis
7376e4dbe9
ai21[patch]: release 0.1.3 (#19867) 2024-04-01 09:56:23 -07:00
Giannis
8cf1d75d08
cohere[patch]: Fix retriever (#19771)
* Replace `source_documents` with `documents`
* Pass `documents` as a named arg vs keyword
* Make `parsed_docs` more robust
* Fix edge case of doc page_content being `None`
2024-03-31 14:47:03 -07:00
Yash Mathur
c42ec58578
together[minor]: Update endpoint to non deprecated version (#19649)
- **Updating Together.ai Endpoint**: "langchain_together: Updated
Deprecated endpoint for partner package"

- Description: The inference API of together is deprecates, do replaced
with completions and made corresponding changes.
- Twitter handle: @dev_yashmathur

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-31 21:21:46 +00:00
Bagatur
2f5606a318
mistralai[patch]: correct integration_test (#19774) 2024-03-29 21:47:35 +00:00
Pierre Véron
ace7b66261
mistralai[patch]: add missing _combine_llm_outputs implementation in ChatMistralAI (#18603)
# Description
Implementing `_combine_llm_outputs` to `ChatMistralAI` to override the
default implementation in `BaseChatModel` returning `{}`. The
implementation is inspired by the one in `ChatOpenAI` from package
`langchain-openai`.
# Issue
None
# Dependencies
None
# Twitter handle
None

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-29 14:43:20 -07:00
Nuno Campos
d4673a3507
openai[patch]: Update openai chat model to new base class interface (#19729) 2024-03-29 14:30:28 -07:00
harry-cohere
23fcc14650
cohere[patch]: support kwargs in with_structured_output (#19736)
**Description:** We'd like to support passing additional kwargs in
`with_structured_output`. I believe this is the accepted approach to
enable additional arguments on API calls.
2024-03-29 14:30:14 -07:00
BeatrixCohere
bd02b83acd
cohere[patch]: Allow overriding of the base URL in Cohere Client (#19766)
This PR adds the ability for a user to override the base API url for the
Cohere client for embeddings and chat llm.
2024-03-29 14:22:30 -07:00
Kaixin Yang
a8104ea8e9
openai[patch]: add checking codes for calling AI model get error (#17909)
**Description:**: adding checking codes for calling AI model get error
in chat_models/base.py and llms/base.py
**Issue**: Sometimes the AI Model calling will get error, we should
raise it.
Otherwise, the next code 'choices.extend(response["choices"])' will
throw a "TypeError: 'NoneType' object is not iterable" error to mask the
true error.
       Because 'response["choices"]' is None.
**Dependencies**: None

---------

Co-authored-by: yangkx <yangkx@asiainfo-int.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-03-29 00:17:32 +00:00
Vincent Chen
833d61adb3
docs: update Together README.md (#18004)
## PR message
**Description:** This PR adds a README file for the Together API in the
`libs/partners` folder of this repository. The README includes:
 - A brief description of the package
 - Installation instructions and class introductions
 - Simple usage examples

**Issue:** #17545 

This PR only contains document changes.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-29 00:02:32 +00:00
aditya thomas
dc9e9a66db
docs: update docstring of the ChatAnthropic and AnthropicLLM classes (#18649)
**Description:** Update docstring of the ChatAnthropic and AnthropicLLM
classes
**Issue:** Not applicable
**Dependencies:** None
2024-03-28 15:33:54 -07:00
HuangZiy
e1f10a697e
openai[patch]: perform judgment processing on chat model streaming delta (#18983)
**PR title:** partners: openai chat model
**PR message:** perform judgment processing on chat model streaming
delta
Closes #18977

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-03-28 14:46:27 -07:00
Erick Friis
e576d6c6b4
cohere[patch]: release 0.1.0rc1 (rc1-2 never released) (#19731) 2024-03-28 19:12:22 +00:00
harry-cohere
ea57050122
cohere: add with_structured_output to ChatCohere (#19730)
**Description:** Adds support for `with_structured_output` to Cohere,
which supports single function calling.

---------

Co-authored-by: BeatrixCohere <128378696+BeatrixCohere@users.noreply.github.com>
2024-03-28 12:09:25 -07:00
BeatrixCohere
d1a2e194c3
cohere[patch]: misc fixs tool use agent and cohere chat (#19705)
Bug fixes in this PR:
* allows for other params such as "message" not just the input param to
the prompt for the cohere tools agent
* fixes to documents kwarg from messages
* fixes to tool_calls API call

---------

Co-authored-by: Harry M <127103098+harry-cohere@users.noreply.github.com>
2024-03-28 10:19:38 -07:00
Erick Friis
5327bc9ec4
elasticsearch[patch]: move to repo (#19620) 2024-03-28 08:54:57 -07:00
aditya thomas
4cd38fe89f
docs: update docstring of the ChatGroq class (#18645)
**Description:** Update docstring of the ChatGroq class
**Issue:** Not applicable
**Dependencies:** None
2024-03-27 23:46:52 -07:00
Jaid
e4d7b1a482
voyageai[patch]: top level reranker import (#19645)
The previous version didn't had  Voyage rerank in the init file


- [ ] **PR title**: langchain_voyageai reranker is not working
 


- [ ] **PR message**: 
    - **Description:** This fix let you run reranker from voyage
    - **Issue:** Was not able to run reranker from voyage
  






 @efriis
2024-03-28 06:37:55 +00:00
Shuqian
332996b4b2
openai[patch]: fix ChatOpenAI model's openai proxy (#19559)
Due to changes in the OpenAI SDK, the previous method of setting the
OpenAI proxy in ChatOpenAI no longer works. This PR fixes this issue,
making the previous way of setting the OpenAI proxy in ChatOpenAI
effective again.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-27 23:16:55 -07:00
Bagatur
b15c7fdde6
anthropic[patch]: fix response metadata type (#19683) 2024-03-27 23:16:26 -07:00
William FH
b7b62e29fb
community[patch], mongodb[patch]: Stop spamming SIMD import warnings (#19531)
If you use an embedding dist function in an eval loop, you get warned
every time. Would prefer to just check once and forget about it.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-28 03:11:02 +00:00
billytrend-cohere
36abb5dd41
cohere[patch]: Fix positional argument (#19678)
cohere: Fix positional argument

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-03-28 02:26:08 +00:00
harry-cohere
3685f8ceac
cohere[patch]: Add cohere tools agent (#19602)
**Description**: Adds a cohere tools agent and related notebook.

---------

Co-authored-by: BeatrixCohere <128378696+BeatrixCohere@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-03-27 18:35:43 -07:00
Erick Friis
929ed65554
cohere[patch]: release 0.1.0rc1 (#19663) 2024-03-27 17:14:56 +00:00
Erick Friis
7630e9529c
Revert "community: added partners/package-name folders" (#19662)
Reverts langchain-ai/langchain#19290
2024-03-27 17:09:30 +00:00
billytrend-cohere
85f57ab4cd
cohere[patch]: Fix cohere rerank (#19624)
Fix cohere rerank inspired by
https://github.com/langchain-ai/langchain/pull/19486
2024-03-27 08:41:53 -07:00
Guangdong Liu
cd79305eb9
openai[patch]: fix AzureChatOpenAI missing parameter problem (#19258)
- **Issue:** close #19255
- PTAL @baskaryan @eyurtsev
2024-03-26 22:31:36 -07:00
fzowl
aea2be5bf3
voyageai[patch]: VoyageAI rerank (#19521)
Adding VoyageAI reranking

---------

Co-authored-by: fodizoltan <zoltan@conway.expert>
Co-authored-by: Yujie Qian <thomasq0809@gmail.com>
2024-03-26 17:07:23 -07:00
Giannis
9ea2a9b0c1
cohere[patch]: Add additional kwargs support for Cohere SDK params (#19533)
* Adds support for `additional_kwargs` in `get_cohere_chat_request`
* This functionality passes in Cohere SDK specific parameters from
`BaseMessage` based classes to the API

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-03-26 18:30:37 +00:00
Leonid Ganeline
0199b73188
docs: added partners/package-name folders (#19290)
Added references to new integration packages from Google, by adding
subfolders to `partners/`.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-26 02:16:59 +00:00
miri-bar
55db737302
ai21[minor]: AI21 Labs Semantic Text Splitter support (#19510)
Description: Added support for AI21 Labs model - Segmentation, as a Text
Splitter
Dependencies: ai21, langchain-text-splitter
Twitter handle: https://github.com/AI21Labs

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-26 01:39:37 +00:00
Erick Friis
441a8012b3
mistralai[patch]: release 0.1.0 (#19540) 2024-03-25 17:29:40 -07:00
Ash Vardanian
d01bad5169
core[patch]: Convert SimSIMD back to NumPy (#19473)
This patch fixes the #18022 issue, converting the SimSIMD internal
zero-copy outputs to NumPy.

I've also noticed, that oftentimes `dtype=np.float32` conversion is used
before passing to SimSIMD. Which numeric types do LangChain users
generally care about? We support `float64`, `float32`, `float16`, and
`int8` for cosine distances and `float16` seems reasonable for
practically any kind of embeddings and any modern piece of hardware, so
we can change that part as well 🤗
2024-03-25 16:36:26 -07:00
Orest Xherija
0b1e09029f
openai[patch]: increase max batch size for Azure OpenAI Embeddings API (#19532)
**Description:** Azure OpenAI has increased its maximum batch size from
16 to 2048 for the Embeddings API per this How-To
[page](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/embeddings?tabs=console#best-practices)

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-03-25 15:50:07 -07:00
Erick Friis
e6952b04d5
cohere[patch]: fix release (#19529) 2024-03-25 13:46:29 -07:00
billytrend-cohere
63343b4987
cohere[patch]: add cohere as a partner package (#19049)
Description: adds support for langchain_cohere

---------

Co-authored-by: Harry M <127103098+harry-cohere@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-03-25 20:23:47 +00:00
Erick Friis
b617085af0
mistralai[patch]: streaming tool calls (#19469) 2024-03-23 19:24:53 +00:00
aditya thomas
16ef88a87d
docs: moving FireworksEmbeddings documentation to docs folder (#19398)
**Description:** Moving FireworksEmbeddings documentation to the
location docs/integration/text_embedding/ from langchain_fireworks/docs/
**Issue:** FireworksEmbeddings documentation was not in the correct
location
**Dependencies:** None

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-22 23:24:22 +00:00