langchain

Commit Graph

Author	SHA1	Message	Date
Guangdong Liu	97d91ec17c	community[patch]: standardize baichuan init args (#20209 ) Related to https://github.com/langchain-ai/langchain/issues/20085 @baskaryan	3 months ago
Shuqian	ad9750403b	community[minor]: add bedrock anthropic callback for token usage counting (#19864 ) Description: add bedrock anthropic callback for token usage counting, consulted openai callback. --------- Co-authored-by: Massimiliano Pronesti <massimiliano.pronesti@gmail.com>	3 months ago
Prince Canuma	1f9f4d8742	community[minor]: Add support for MLX models (chat & llm) (#18152 ) Description: This PR adds support for MLX models both chat (i.e., instruct) and llm (i.e., pretrained) types/ Dependencies: mlx, mlx_lm, transformers Twitter handle: @Prince_Canuma --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
Bagatur	5ae0e687b3	docs: use standard openai params (#20160 ) Part of #20085	3 months ago
Chenhui Zhang	a1f3e9f537	community[minor]: Update ChatZhipuAI to support GLM-4 model (#16695 ) Description: Update `ChatZhipuAI` to support the latest `glm-4` model. Issue: N/A Dependencies: httpx, httpx-sse, PyJWT The previous `ChatZhipuAI` implementation requires the `zhipuai` package, and cannot call the latest GLM model. This is because - The old version `zhipuai==1.` doesn't support the latest model. - `zhipuai==2.` requires `pydantic V2`, which is incompatible with 'langchain-community'. This re-implementation invokes the GLM model by sending HTTP requests to [open.bigmodel.cn](https://open.bigmodel.cn/dev/api) via the `httpx` package, and uses the `httpx-sse` package to handle stream events. --------- Co-authored-by: zR <2448370773@qq.com>	3 months ago
ethynic	e9caa22d47	community[patch]: Update minimax.py (#14384 ) MiniMaxChat class _generate method shoud return a ChatResult object not str Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Jialei	f7c903e24a	community[minor]: add support for Moonshot llm and chat model (#17100 )	3 months ago
Sachin Paryani	25c9f3d1d1	community[patch]: Support Streaming in Azure Machine Learning (#18246 ) - [x] PR title: "community: Support streaming in Azure ML and few naming changes" - [x] PR message: - Description: Added support for streaming for azureml_endpoint. Also, renamed and AzureMLEndpointApiType.realtime to AzureMLEndpointApiType.dedicated. Also, added new classes CustomOpenAIChatContentFormatter and CustomOpenAIContentFormatter and updated the classes LlamaChatContentFormatter and LlamaContentFormatter to now show a deprecated warning message when instantiated. --------- Co-authored-by: Sachin Paryani <saparan@microsoft.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
高璟琦	75173d31db	community[minor]: Add solar model chat model (#18556 ) Add our solar chat models, available model choices: * solar-1-mini-chat * solar-1-mini-translate-enko * solar-1-mini-translate-koen More documents and pricing can be found at https://console.upstage.ai/services/solar. The references to our solar model can be found at * https://arxiv.org/abs/2402.17032 --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Davide Menini	f7042321f1	community[patch]: gather token usage info in BedrockChat during generation (#19127 ) This PR allows to calculate token usage for prompts and completion directly in the generation method of BedrockChat. The token usage details are then returned together with the generations, so that other downstream tasks can access them easily. This allows to define a callback for tokens tracking and cost calculation, similarly to what happens with OpenAI (see [OpenAICallbackHandler](https://api.python.langchain.com/en/latest/_modules/langchain_community/callbacks/openai_info.html#OpenAICallbackHandler). I plan on adding a BedrockCallbackHandler later. Right now keeping track of tokens in the callback is already possible, but it requires passing the llm, as done here: https://how.wtf/how-to-count-amazon-bedrock-anthropic-tokens-with-langchain.html. However, I find the approach of this PR cleaner. Thanks for your reviews. FYI @baskaryan, @hwchase17 --------- Co-authored-by: taamedag <Davide.Menini@swisscom.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
ligang-super	a662468dde	community[patch]: Fix the error of Baidu Qianfan not passing the stop parameter (#18666 ) - [x] PR title: "community: fix baidu qianfan missing stop parameter" - [x] PR message: - **Description: Baidu Qianfan lost the stop parameter when requesting service due to extracting it from kwargs. This bug can cause the agent to receive incorrect results --------- Co-authored-by: ligang33 <ligang33@baidu.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
kaijietti	9c4b6dc979	community[patch]: fix bug in cohere that `async for` a coroutine in ChatCohere (#19381 ) Without `await`, the `stream` returned from the `async_client` is actually a coroutine, which could not be used in `async for`.	3 months ago
Dobiichi-Origami	18e6f9376d	community[Qianfan]: add function_call in additional_kwargs (#19550 ) - Description: add lacked `function_call` field in `additional_kwargs` in previous version - Dependencies: None of new dependency	3 months ago
Anindyadeep	b2a11ce686	community[minor]: Prem AI langchain integration (#19113 ) ### Prem SDK integration in LangChain This PR adds the integration with [PremAI's](https://www.premai.io/) prem-sdk with langchain. User can now access to deployed models (llms/embeddings) and use it with langchain's ecosystem. This PR adds the following: ### This PR adds the following: - [x] Add chat support - [X] Adding embedding support - [X] writing integration tests - [X] writing tests for chat - [X] writing tests for embedding - [X] writing unit tests - [X] writing tests for chat - [X] writing tests for embedding - [X] Adding documentation - [X] writing documentation for chat - [X] writing documentation for embedding - [X] run `make test` - [X] run `make lint`, `make lint_diff` - [X] Final checks (spell check, lint, format and overall testing) --------- Co-authored-by: Anindyadeep Sannigrahi <anindyadeepsannigrahi@Anindyadeeps-MacBook-Pro.local> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
Dmitry Tyumentsev	08b769d539	community[patch]: YandexGPT Use recent yandexcloud sdk version (#19341 ) Fixed inability to work with [yandexcloud SDK](https://pypi.org/project/yandexcloud/) version higher 0.265.0	3 months ago
Mikelarg	dac2e0165a	community[minor]: Added GigaChat Embeddings support + updated previous GigaChat integration (#19516 ) - Description: Added integration with [GigaChat](https://developers.sber.ru/portal/products/gigachat) embeddings. Also added support for extra fields in GigaChat LLM and fixed docs.	3 months ago
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>	3 months ago
Igor Muniz Soares	743f888580	community[minor]: Dappier chat model integration (#19370 ) Description: This PR adds [Dappier](https://dappier.com/) for the chat model. It supports generate, async generate, and batch functionalities. We added unit and integration tests as well as a notebook with more details about our chat model. Dependencies: No extra dependencies are needed.	3 months ago
billytrend-cohere	f6bcd42421	community[patch]: Replace positional argument with text=text for cohere>=5 compatibility (#19407 ) - Description: Replace positional argument with text=text for cohere>=5 compatibility	4 months ago
Taqi Jaffri	044bc22acc	Community: Add mistral oss model support to azureml endpoints, plus configurable timeout (#19123 ) - Description: There was no formatter for mistral models for Azure ML endpoints. Adding that, plus a configurable timeout (it was hard coded before) - Dependencies: none - Twitter handle: @tjaffri @docugami	4 months ago
Pengfei Jiang	514fe80778	community[patch]: add stop parameter support to volcengine maas (#19052 ) - Description: add stop parameter to volcengine maas model - Dependencies: no --------- Co-authored-by: 江鹏飞 <jiangpengfei.jiangpf@bytedance.com>	4 months ago
htaoruan	bcc771e37c	docs: ChatTongyi example error (#19013 )	4 months ago
Rodrigo Nogueira	e64cf1aba4	community: Add model argument for maritalk models and better error handling (#19187 )	4 months ago
wulixuan	0e0030f494	community[patch]: fix yuan2 chat model errors while invoke. (#19015 ) 1. fix yuan2 chat model errors while invoke. 2. update related tests. 3. fix some deprecationWarning.	4 months ago
Shuai Liu	c244e1a50b	community[patch]: Fixed bug in merging `generation_info` during chunk concatenation in Tongyi and ChatTongyi (#19014 ) - Description: In #16218 , during the `GenerationChunk` and `ChatGenerationChunk` concatenation, the `generation_info` merging changed from simple keys & values replacement to using the util method [`merge_dicts`](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/utils/_merge.py): ![image](https://github.com/langchain-ai/langchain/assets/2098020/10f315bf-7fe0-43a7-a0ce-6a3834b99a15) The `merge_dicts` method could not handle merging values of `int` or some other types, and would raise a [`TypeError`](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/utils/_merge.py#L55). This PR fixes this issue in the Tongyi and ChatTongyi Model by adopting the `generation_info` of the last chunk and discarding the `generation_info` of the intermediate chunks, ensuring that `stream` and `astream` function correctly. - Issue: - Related issues or PRs about Tongyi & ChatTongyi: #16605, #17105 - Other models or cases: #18441, #17376 - Dependencies: No new dependencies	4 months ago
case-k	ebc4a64f9e	docs: fix databricks document url (#19096 ) Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	4 months ago
billytrend-cohere	7253b816cc	community: Add support for cohere SDK v5 (keeps v4 backwards compatibility) (#19084 ) - Description: Add support for cohere SDK v5 (keeps v4 backwards compatibility) --------- Co-authored-by: Erick Friis <erick@langchain.dev>	4 months ago
Dobiichi-Origami	471f2ed40a	community[patch]: re-arrange the addtional_kwargs of returned qianfan structure to avoid _merge_dict issue (#18889 ) fix issue: https://github.com/langchain-ai/langchain/issues/18441 PTAL, thanks @baskaryan, @efriis, @eyurtsev, @hwchase17. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	4 months ago
Leonid Ganeline	11195cfa42	community[patch]: speed up import times in the community package (#18928 ) This PR speeds up import times in the community package	4 months ago
Anis ZAKARI	37e89ba5b1	community[patch]: Bedrock add support for mistral models (#18756 ) Description*: My previous [PR](https://github.com/langchain-ai/langchain/pull/18521) was mistakenly closed, so I am reopening this one. Context: AWS released two Mistral models on Bedrock last Friday (March 1, 2024). This PR includes some code adjustments to ensure their compatibility with the Bedrock class. --------- Co-authored-by: Anis ZAKARI <anis.zakari@hymaia.com> Co-authored-by: Erick Friis <erick@langchain.dev>	4 months ago
Yunmo Koo	fee6f983ef	community[minor]: Integration for `Friendli` LLM and `ChatFriendli` ChatModel. (#17913 ) ## Description - Add [Friendli](https://friendli.ai/) integration for `Friendli` LLM and `ChatFriendli` chat model. - Unit tests and integration tests corresponding to this change are added. - Documentations corresponding to this change are added. ## Dependencies - Optional dependency [`friendli-client`](https://pypi.org/project/friendli-client/) package is added only for those who use `Frienldi` or `ChatFriendli` model. ## Twitter handle - https://twitter.com/friendliai	4 months ago
Bagatur	3b1eb1f828	community[patch]: chat hf typing fix (#18693 )	4 months ago
Erick Friis	1beb84b061	community[patch]: move pdf text tests to integration (#18746 )	4 months ago
Guangdong Liu	ced5e7bae7	community[patch]: Fix sparkllm authentication problem. (#18651 ) - Description: fix sparkllm authentication problem.The current timestamp is in RFC1123 format. The time deviation must be controlled within 300s. I changed to re-obtain the url every time I ask a question. https://www.xfyun.cn/doc/spark/general_url_authentication.html#_1-2-%E9%89%B4%E6%9D%83%E5%8F%82%E6%95%B0	4 months ago
Piyush Jain	2b234a4d96	Support for claude v3 models. (#18630 ) Fixes #18513. ## Description This PR attempts to fix the support for Anthropic Claude v3 models in BedrockChat LLM. The changes here has updated the payload to use the `messages` format instead of the formatted text prompt for all models; `messages` API is backwards compatible with all models in Anthropic, so this should not break the experience for any models. ## Notes The PR in the current form does not support the v3 models for the non-chat Bedrock LLM. This means, that with these changes, users won't be able to able to use the v3 models with the Bedrock LLM. I can open a separate PR to tackle this use-case, the intent here was to get this out quickly, so users can start using and test the chat LLM. The Bedrock LLM classes have also grown complex with a lot of conditions to support various providers and models, and is ripe for a refactor to make future changes more palatable. This refactor is likely to take longer, and requires more thorough testing from the community. Credit to PRs [18579](https://github.com/langchain-ai/langchain/pull/18579) and [18548](https://github.com/langchain-ai/langchain/pull/18548) for some of the code here. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	4 months ago
Erick Friis	343438e872	community[patch]: deprecate community fireworks (#18544 )	4 months ago
William De Vena	2087cbae64	community[patch]: Invoke callback prior to yielding token (#18449 ) ## PR title community[patch]: Invoke callback prior to yielding token ## PR message - Description: Invoke callback prior to yielding token in _stream method in chat_models/perplexity. - Issue: https://github.com/langchain-ai/langchain/issues/16913 - Dependencies: None	4 months ago
Ather Fawaz	a5ccf5d33c	community[minor]: Add support for Perplexity chat model(#17024 ) - Description: This PR adds support for [Perplexity AI APIs](https://blog.perplexity.ai/blog/introducing-pplx-api). - Issues: None - Dependencies: None - Twitter handle: [@atherfawaz](https://twitter.com/AtherFawaz) --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Erick Friis <erick@langchain.dev>	4 months ago
Rodrigo Nogueira	3438d2cbcc	community[minor]: add maritalk chat (#17675 ) Description: Adds the MariTalk chat that is based on a LLM specially trained for Portuguese. Twitter handle: @MaritacaAI	4 months ago
Daniel Chico	7d962278f6	community[patch]: type ignore fixes (#18395 ) Related to #17048	4 months ago
Guangdong Liu	760a16ff32	community[patch]: Fix ChatModel for sparkllm Bug. (#18375 ) PR message: *Delete this entire checklist* and replace with - Description: fix sparkllm paramer error - Issue: close #18370 - Dependencies: change `IFLYTEK_SPARK_APP_URL` to `IFLYTEK_SPARK_API_URL` - Twitter handle: No	4 months ago
mackong	2c42f3a955	ollama[patch]: delete suffix slash to avoid redirect (#18260 ) - Description: see [ollama](https://github.com/ollama/ollama/blob/main/server/routes.go#L949)'s route definitions - Issue: N/A - Dependencies: N/A	4 months ago
kYLe	56b955fc31	community[minor]: Add async_client for Anyscale Chat model (#18050 ) Add `async_client` for Anyscale Chat_model	4 months ago
Nicolò Boschi	4c132b4cc6	community: fix openai streaming throws 'AIMessageChunk' object has no attribute 'text' (#18006 ) After upgrading langchain-community to 0.0.22, it's not possible to use openai from the community package with streaming=True ``` File "/home/runner/work/ragstack-ai/ragstack-ai/ragstack-e2e-tests/.tox/langchain/lib/python3.11/site-packages/langchain_community/chat_models/openai.py", line 434, in _generate return generate_from_stream(stream_iter) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/runner/work/ragstack-ai/ragstack-ai/ragstack-e2e-tests/.tox/langchain/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 65, in generate_from_stream for chunk in stream: File "/home/runner/work/ragstack-ai/ragstack-ai/ragstack-e2e-tests/.tox/langchain/lib/python3.11/site-packages/langchain_community/chat_models/openai.py", line 418, in _stream run_manager.on_llm_new_token(chunk.text, chunk=cg_chunk) ^^^^^^^^^^ AttributeError: 'AIMessageChunk' object has no attribute 'text' ``` Fix regression of https://github.com/langchain-ai/langchain/pull/17907 Twitter handle: @nicoloboschi	4 months ago
mackong	9678797625	community[patch]: callback before yield for _stream/_astream (#17907 ) - Description: callback on_llm_new_token before yield chunk for _stream/_astream for some chat models, make all chat models in a consistent behaviour. - Issue: N/A - Dependencies: N/A	4 months ago
Chad Juliano	50ba3c68bb	community[minor]: add Kinetica LLM wrapper (#17879 ) Description: Initial pull request for Kinetica LLM wrapper Issue: N/A Dependencies: No new dependencies for unit tests. Integration tests require gpudb, typeguard, and faker Twitter handle: @chad_juliano Note: There is another pull request for Kinetica vectorstore. Ultimately we would like to make a partner package but we are starting with a community contribution.	4 months ago
Xudong Sun	c524bf31f5	docs: add helpful comments to sparkllm.py (#17774 ) Adding helpful comments to sparkllm.py, help users to use ChatSparkLLM more effectively	4 months ago
mackong	31891092d8	community[patch]: add missing chunk parameter for _stream/_astream (#17807 ) - Description: Add missing chunk parameter for _stream/_astream for some chat models, make all chat models in a consistent behaviour. - Issue: N/A - Dependencies: N/A	4 months ago
Aymeric Roucher	0d294760e7	Community: Fuse HuggingFace Endpoint-related classes into one (#17254 ) ## Description Fuse HuggingFace Endpoint-related classes into one: - [HuggingFaceHub](`5ceaf784f3/libs/community/langchain_community/llms/huggingface_hub.py`) - [HuggingFaceTextGenInference](`5ceaf784f3/libs/community/langchain_community/llms/huggingface_text_gen_inference.py`) - and [HuggingFaceEndpoint](`5ceaf784f3/libs/community/langchain_community/llms/huggingface_endpoint.py`) Are fused into - HuggingFaceEndpoint ## Issue The deduplication of classes was creating a lack of clarity, and additional effort to develop classes leads to issues like [this hack](`5ceaf784f3/libs/community/langchain_community/llms/huggingface_endpoint.py (L159)`). ## Dependancies None, this removes dependancies. ## Twitter handle If you want to post about this: @AymericRoucher --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	5 months ago
wulixuan	5d06797905	community[minor]: integrate chat models with Yuan2.0 (#16575 ) 1. integrate chat models with [`Yuan2.0`](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/README-EN.md) 2. add a new doc for [Yuan2.0 integration](docs/docs/integrations/llms/yuan2.ipynb) Yuan2.0 is a new generation Fundamental Large Language Model developed by IEIT System. We have published all three models, Yuan 2.0-102B, Yuan 2.0-51B, and Yuan 2.0-2B. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	5 months ago

1 2 3

108 Commits (12190ad7284f9cff6757a7dc7a133623c2e6368a)