langchain

Commit Graph

Author	SHA1	Message	Date
Anush	ade4bfdff1	qdrant: Updated class check in Self-Query Retriever factory (#25877 ) ## Description - Updates the self-query retriever factory to check for the new Qdrant vector store class. i.e. `langchain_qdrant.QdrantVectorstore`. - Deprecates `QdrantSparseVectorRetriever`, since the vector store implementation natively supports it now. Resolves #25798	3 weeks ago
Djordje	862ef32fdc	community: Fixed infinity embeddings async request (#25882 ) Description: Fix async infinity embeddings Issue: #24942 @baskaryan, @ccurme	3 weeks ago
rainsubtime	f75d5621e2	community:Fix a bug of LLM in moonshot (#25878 ) - Description: When useing LLM integration moonshot,it's occurring error "'Moonshot' object has no attribute '_client'",it's because of the "_client" that is private in pydantic v1.0 so that we can't use it.I turn "_client" into "client" , the error to be resolved! - Issue: the issue #24390 - Dependencies: none - Twitter handle: @Rainsubtime - [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/ Co-authored-by: Cyue <Cyue_work2001@163.com>	3 weeks ago
ZhangShenao	fd0f147df3	Improvement[Community] Add tool-calling test case for `ChatZhipuAI` (#25884 ) - Add tool-calling test case for `ChatZhipuAI`	3 weeks ago
k.muto	5bb810c5c6	docs: updated args_schema to be required when using callback handlers in custom tools. (#25887 ) - Description: if you use callback handlers when using tool, run_manager will be added to input, so you need to explicitly specify args_schema, but i was confused because it was not listed, so i added it. Also, it seems that the type does not work with pydantic.BaseModel. - Issue: None - Dependencies: None	3 weeks ago
默奕	6377185291	add neo4j query constructor for self query (#25288 ) - [x] PR title - community: add neo4j query constructor for self query - [x] PR message - Description: adding a Neo4jTranslator so that the Neo4j vector database can use SelfQueryRetriever - Issue: this issue had been raised before in #19748 - Dependencies: none. - Twitter handle: @moyi_dang - p.s. I have not added the query constructor in BUILTIN_TRANSLATORS in this PR, I want to make changes to only one package at a time. - [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, ccurme, vbarda, hwchase17. --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Chester Curme <chester.curme@gmail.com>	3 weeks ago
Ohad Eytan	b5d670498f	partners/milvus: allow creating a vectorstore with sparse embeddings (#25284 ) # Description Milvus (and `pymilvus`) recently added the option to use [sparse vectors](https://milvus.io/docs/sparse_vector.md#Sparse-Vector) with appropriate search methods (e.g., `SPARSE_INVERTED_INDEX`) and embeddings (e.g., `BM25`, `SPLADE`). This PR allow creating a vector store using langchain's `Milvus` class, setting the matching vector field type to `DataType.SPARSE_FLOAT_VECTOR` and the default index type to `SPARSE_INVERTED_INDEX`. It is only extending functionality, and backward compatible. ## Note I also interested in extending the Milvus class further to support multi vector search (aka hybrid search). Will be happy to discuss that. See [here](https://github.com/langchain-ai/langchain/discussions/19955), [here](https://github.com/langchain-ai/langchain/pull/20375), and [here](https://github.com/langchain-ai/langchain/discussions/22886) similar needs. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	3 weeks ago
Erick Friis	09b04c7e3b	"community: release 0.2.15" (#25867 )	3 weeks ago
Erick Friis	f7e62754a1	community: undo azure_ad_access_token breaking change (#25818 )	3 weeks ago
Leonid Ganeline	6047138379	docs: `arxiv` reference updates (#24949 ) Added: arxiv references to the concepts page. Regenerated: arxiv references page. Improved: formatting of the concepts page (moved the Partner packages section after langchain_community)	3 weeks ago
Bagatur	1759ff5836	infra: rm together lagnchain test dp (#25866 )	4 weeks ago
Erick Friis	24f0c232fe	docs: elastic feature (#25865 )	4 weeks ago
Erick Friis	1640872059	together: mv to external repo (#25863 )	4 weeks ago
Michael Paciullo	e7c856c298	langchain_openai: Add "strict" parameter to OpenAIFunctionsAgent (#25862 ) - Description: OpenAI recently introduced a "strict" parameter for [structured outputs in their API](https://openai.com/index/introducing-structured-outputs-in-the-api/). An optional `strict` parameter has been added to `create_openai_functions_agent()` and `create_openai_tools_agent()` so developers can use this feature in those agents. --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	4 weeks ago
Bagatur	fabd3295fa	core[patch]: dont mutate merged lists/dicts (#25858 ) Update merging utils to - not mutate objects - have special handling to 'type' keys in dicts	4 weeks ago
Kyle Winkelman	09c2d8faca	langchain_openai: Cleanup OpenAIEmbeddings validate_environment. (#25855 ) Description: [This portion of code](https://github.com/langchain-ai/langchain/blob/v0.1.16/libs/partners/openai/langchain_openai/embeddings/base.py#L189-L196) has no use as a couple lines later a [`ValueError` is thrown](https://github.com/langchain-ai/langchain/blob/v0.1.16/libs/partners/openai/langchain_openai/embeddings/base.py#L209-L213). Issue: A follow up to #25852.	4 weeks ago
Kyle Winkelman	201bdf7148	community: Cap AzureOpenAIEmbeddings chunk_size at 2048 instead of 16. (#25852 ) Description: Within AzureOpenAIEmbeddings there is a validation to cap `chunk_size` at 16. The value of 16 is either an old limitation or was erroneously chosen. I have checked all of the `preview` and `stable` releases to ensure that the `embeddings` endpoint can handle 2048 entries [Azure/azure-rest-api-specs](https://github.com/Azure/azure-rest-api-specs/tree/main/specification/cognitiveservices/data-plane/AzureOpenAI/inference). I have also found many locations that confirm this limit should be 2048: - https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#embeddings - https://learn.microsoft.com/en-us/azure/ai-services/openai/quotas-limits Issue: fixes #25462	4 weeks ago
Leonid Ganeline	08c9c683a7	docs: `integrations` reference updates 6 (#25188 ) Added missed provider pages. Added missed references to the integration components.	4 weeks ago
Allan Ascencio	a8af396a82	added octoai test (#21793 ) - [ ] PR title: community: add tests for ChatOctoAI - [ ] PR message: Description: Added unit tests for the ChatOctoAI class in the community package to ensure proper validation and default values. These tests verify the correct initialization of fields, the handling of missing required parameters, and the proper setting of aliases. Issue: N/A Dependencies: None --------- Co-authored-by: ccurme <chester.curme@gmail.com> Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>	4 weeks ago
Param Singh	69f9acb60f	premai[patch]: Standardize premai params (#21513 ) Thank you for contributing to LangChain! community:premai[patch]: standardize init args - updated `temperature` with Pydantic Field, updated the unit test. - updated `max_tokens` with Pydantic Field, updated the unit test. - updated `max_retries` with Pydantic Field, updated the unit test. Related to #20085 --------- Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com> Co-authored-by: ccurme <chester.curme@gmail.com>	4 weeks ago
Guangdong Liu	fcf9230257	community(sparkllm): Add function call support in Sparkllm chat model. (#20607 ) - Description: Add function call support in Sparkllm chat model. Related documents https://www.xfyun.cn/doc/spark/Web.html#_2-function-call%E8%AF%B4%E6%98%8E - @baskaryan --------- Co-authored-by: ccurme <chester.curme@gmail.com>	4 weeks ago
ChengZi	37f5ba416e	partners[milvus]: fix issue when metadata_schema is None (#25836 ) fix issue when metadata_schema is None Signed-off-by: ChengZi <chen.zhang@zilliz.com>	4 weeks ago
ccurme	426333ff6f	infra[patch]: remove AI21 from scheduled tests (#25847 ) These now run in https://github.com/langchain-ai/langchain-ai21	4 weeks ago
Jorge Piedrahita Ortiz	9ac953a948	Community: sambastudio embeddings GenericV2 API support (#25064 ) - Description: SambaStudio GenericV2 API support Minor changes for requests error handling	4 weeks ago
Sam Jove	bdce9a47d0	community[patch]: callback before yield for _astream (gigachat) (#25834 ) Description: Moves yield to after callback for _astream for gigachat in the community package Issue: #16913 --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	4 weeks ago
Jinoos Lee	703af9ffe3	Patch enable to use Amazon OpenSearch Serverless(aoss) for Semantic Cache store (#25833 ) - [x] PR title: "community: Patch enable to use Amazon OpenSearch Serverless for Semantic Cache store" - [x] PR message: - Description: OpenSearchSemanticCache class support Amazon OpenSearch Serverless for Semantic Cache store, it's only required to pass auth(http_auth) parameter to initializer - Dependencies: none If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Jinoos Lee <jinoos@amazon.com>	4 weeks ago
William FH	1ad621120d	docs: Update langgraph 0.2.0 checkpointer import path (#25205 ) And fix the description for timeout	4 weeks ago
Andrew Benton	c410545075	docs: add self-hosting row to code interpreter tools table (#25303 ) Description: Add information about self-hosting support to the code interpreter tools table. Issue: N/A Dependencies: N/A	4 weeks ago
Eugene Yurtsev	83327ac43a	docs: Fix typo in openai llm integration notebook (#25492 ) Fix typo in openai LLM integration notebook.	4 weeks ago
Leonid Ganeline	31f55781b3	docs: added ColBERT reference (#25452 ) Added references to the source papers. Fixed URL verification code. Improved arXive page formatting. Regenerated arXiv page.	4 weeks ago
Mikhail Khludnev	a017f49fd3	comminity[patch]: fix #25575 YandexGPTs for _grpc_metadata (#25617 ) it fixes two issues: ### YGPTs are broken #25575 ``` File ....conda/lib/python3.11/site-packages/langchain_community/embeddings/yandex.py:211, in _make_request(self, texts, **kwargs) .. --> 211 res = stub.TextEmbedding(request, metadata=self._grpc_metadata) # type: ignore[attr-defined] AttributeError: 'YandexGPTEmbeddings' object has no attribute '_grpc_metadata' ``` My gut feeling that #23841 is the cause. I have to drop leading underscore from `_grpc_metadata` for quickfix, but I just don't know how to do it _pydantic_ enough. ### minor issue: if we use `api_key`, which is not the best practice the code fails with ``` File ~/git/...../python3.11/site-packages/langchain_community/embeddings/yandex.py:119, in YandexGPTEmbeddings.validate_environment(cls, values) ... AttributeError: 'tuple' object has no attribute 'append' ``` - Added new integration test. But it requires YGPT env available and active account. I don't know how int tests dis\enabled in CI. - added small unit tests with mocks. Should be fine. --------- Co-authored-by: mikhail-khludnev <mikhail_khludnev@rntgroup.com>	4 weeks ago
Serena Ruan	850bf89e48	community[patch]: Support passing extra params for executing functions in UCFunctionToolkit (#25652 ) 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" Support passing extra params when executing UC functions: The params should be a dictionary with key EXECUTE_FUNCTION_ARG_NAME, the assumption is that the function itself doesn't use such variable name (starting and ending with double underscores), and if it does we raise Exception. If invalid params passing to the execute_statement, we raise Exception as well. - [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, ccurme, vbarda, hwchase17. --------- Signed-off-by: Serena Ruan <serena.rxy@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	4 weeks ago
崔浩	3555882a0d	community[patch]: optimize xinference llm import (#25809 ) Thank you for contributing to LangChain! - [ ] PR title: "community: optimize xinference llm import" - [ ] PR message: - Description: from xinferece_client import RESTfulClient when there is no importing xinference. - Dependencies: xinferece_client - Why do so: the total xinference(pip install xinference[all]) is too heavy for installing, let alone it is useless for langchain user except RESTfulClient. The modification has maintained consistency with the xinference embeddings [embeddings/xinference](../blob/master/libs/community/langchain_community/embeddings/xinference.py#L89).	4 weeks ago
Michael Rubél	9decd0b243	langchain[patch]: fix moderation chain init (#25778 ) [This commit](`d3ca2cc8c3`) has broken the moderation chain so we've faced a crash when migrating the LangChain from v0.1 to v0.2. The issue appears that the class attribute the code refers to doesn't hold the value processed in the `validate_environment` method. We had `extras={}` in this attribute, and it was casted to `True` when it should've been `False`. Adding a simple assignment seems to resolve the issue, though I'm not sure it's the right way. --- --------- Co-authored-by: Michael Rubél <mrubel@oroinc.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	4 weeks ago
Madhu Shantan	63a1569d5f	docs: fixed syntax error in ChatAnthropic Example - rag app tutorial notebook (#25824 ) Thank you for contributing to LangChain! - [ ] PR title: docs: fixed syntax error in ChatAnthropic Example - rag app tutorial notebook - generation - [ ] PR message: - Description: Fixed a syntax error in the ChatAnthropic initialization example in the RAG tutorial notebook. The original code had an extra set of quotation marks around the model parameter, which would cause a Python syntax error. The corrected version removes these unnecessary quotes. - Dependencies: No new dependencies required for this documentation fix. I've verified that the corrected code is syntactically valid and matches the expected format for initializing a ChatAnthropic instance in LangChain. - Twitter handle: madhu_shantan - [ ] Add tests and docs: the error in Jupyter notebook: <img width="1189" alt="Screenshot 2024-08-29 at 12 43 47 AM" src="https://github.com/user-attachments/assets/07148a93-300f-40e2-ad4a-ac219cbb56a4"> the corrected cell: <img width="983" alt="Screenshot 2024-08-29 at 12 44 18 AM" src="https://github.com/user-attachments/assets/75b1455a-3671-454e-ac16-8ca77c049dbd"> - [ ] Lint and test: As this is a documentation-only change, I have not run the full test suite. However, I have verified that the corrected code example is syntactically valid and matches the expected usage of the ChatAnthropic class. the error in the docs is here - <img width="1020" alt="Screenshot 2024-08-29 at 12 48 36 AM" src="https://github.com/user-attachments/assets/812ccb20-b411-4a5b-afc1-41742efb32a7">	4 weeks ago
Erick Friis	e5ae988505	prompty: bump core version (#25831 )	4 weeks ago
Erick Friis	c8b8335b82	core: prompt variable error msg (#25787 )	4 weeks ago
ccurme	ff168aaec0	prompty: release 0.0.3 (#25830 )	4 weeks ago
Matthieu	783397eacb	community: avoid double templating in `langchain_prompty` (#25777 ) ## Description In `langchain_prompty`, messages are templated by Prompty. However, a call to `ChatPromptTemplate` was initiating a second templating. We now convert parsed messages to `Message` objects before calling `ChatPromptTemplate`, signifying clearly that they are already templated. We also revert #25739 , which applied to this second templating, which we now avoid, and did not fix the original issue. ## Issue Closes #25703	4 weeks ago
ccurme	afe8ccaaa6	community[patch]: Add ID field back to Azure AI Search results (#25828 ) Commandeering https://github.com/langchain-ai/langchain/pull/23243 as maintainers don't have ability to modify that PR. Fixes https://github.com/langchain-ai/langchain/issues/22827 --------- Co-authored-by: Ming Quah <fleetadmiralbutter@icloud.com>	4 weeks ago
rbrugaro	9fa172bc26	add links in example nb with tei/tgi references (#25821 ) I have validated langchain interface with tei/tgi works as expected when TEI and TGI running on Intel Gaudi2. Adding some references to notebooks to help users find relevant info. --------- Co-authored-by: Rita Brugarolas <rbrugaro@idc708053.jf.intel.com> Co-authored-by: Chester Curme <chester.curme@gmail.com>	4 weeks ago
Erick Friis	8fb594fd2a	ai21: migrate to external repo (#25827 )	4 weeks ago
Erick Friis	095b712a26	ollama: bump core version (#25826 )	4 weeks ago
Erick Friis	5db6c6d96d	community: release 0.2.14 (#25822 )	4 weeks ago
Erick Friis	d6c4803ab0	core: release 0.2.36 (#25819 )	4 weeks ago
Erick Friis	5186325bc7	partners/ollama: release 0.1.2 (#25817 ) release for #25697	4 weeks ago
Rohit Gupta	aff50a1e6f	milvus: add array data type for collection create (#23219 ) Add array data type for milvus vector store collection create 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: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [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, ccurme, vbarda, hwchase17. --------- Signed-off-by: ChengZi <chen.zhang@zilliz.com> Co-authored-by: Rohit Gupta <rohit.gupta2@walmart.com> Co-authored-by: ChengZi <chen.zhang@zilliz.com> Co-authored-by: Erick Friis <erick@langchain.dev>	4 weeks ago
Cillian Berragan	754f3c41f9	community: add score to PineconeHybridSearchRetriever (#25781 ) Description: Adds the 'score' returned by Pinecone to the `PineconeHybridSearchRetriever` list of returned Documents. There is currently no way to return the score when using Pinecone hybrid search, so in this PR I include it by default. --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	4 weeks ago
ZhangShenao	3f1d652f15	Improvement[Community] Improve api doc for `PineconeHybridSearchRetriever` (#25803 ) - Complete missing args in api doc	4 weeks ago
Moritz Schlager	555f97becb	community[patch]: fix model initialization bug for deepinfra (#25727 ) ### Description adds an init method to ChatDeepInfra to set the model_name attribute accordings to the argument ### Issue currently, the model_name specified by the user during initialization of the ChatDeepInfra class is never set. Therefore, it always chooses the default model (meta-llama/Llama-2-70b-chat-hf, however probably since this is deprecated it always uses meta-llama/Llama-3-70b-Instruct). We stumbled across this issue and fixed it as proposed in this pull request. Feel free to change the fix according to your coding guidelines and style, this is just a proposal and we want to draw attention to this problem. ### Dependencies no additional dependencies required Feel free to contact me or @timo282 and @finitearth if you have any questions. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	4 weeks ago

... 2 3 4 5 6 ...

11320 Commits (bd42344b0ac5cdd3557d00661dbf44fbc62faf7d) All Branches Search

11320 Commits (bd42344b0ac5cdd3557d00661dbf44fbc62faf7d)

All Branches