langchain

Commit Graph

Author	SHA1	Message	Date
Eugene Yurtsev	f62b323108	core[minor]: Support all versions of pydantic base model in argsschema (#24418 ) This adds support to any pydantic base model for tools. The only potential issue is that `get_input_schema()` will not always return a v1 base model.	2 months ago
Prakul	b2bc15e640	docs: Update mongodb README.md (#24412 ) Thank you for contributing to LangChain! - [ ] 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" - [ ] 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! - [ ] 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. - [ ] 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.	2 months ago
Evan Harris	61ea7bf60b	Add a `ListRerank` document compressor (#13311 ) - Description: This PR adds a new document compressor called `ListRerank`. It's derived from `BaseDocumentCompressor`. It's a near exact implementation of introduced by this paper: [Zero-Shot Listwise Document Reranking with a Large Language Model](https://arxiv.org/pdf/2305.02156.pdf) which it finds to outperform pointwise reranking, which is somewhat implemented in LangChain as [LLMChainFilter](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/retrievers/document_compressors/chain_filter.py). - Issue: None - Dependencies: None - Tag maintainer: @hwchase17 @izzymsft - Twitter handle: @HarrisEMitchell Notes: 1. I didn't add anything to `docs`. I wasn't exactly sure which patterns to follow as [cohere reranker is under Retrievers](https://python.langchain.com/docs/integrations/retrievers/cohere-reranker) with other external document retrieval integrations, but other contextual compression is [here](https://python.langchain.com/docs/modules/data_connection/retrievers/contextual_compression/). Happy to contribute to either with some direction. 2. I followed syntax, docstrings, implementation patterns, etc. as well as I could looking at nearby modules. One thing I didn't do was put the default prompt in a separate `.py` file like [Chain Filter](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/retrievers/document_compressors/chain_filter_prompt.py) and [Chain Extract](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/retrievers/document_compressors/chain_extract_prompt.py). Happy to follow that pattern if it would be preferred. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Chester Curme <chester.curme@gmail.com>	2 months ago
Srijan Dubey	4c651ba13a	Adding LangChain v0.2 support for nvidia ai endpoint, langchain-nvidia-ai-endpoints. Removed deprecated classes from nvidia_ai_endpoints.ipynb (#24411 ) Description: added support for LangChain v0.2 for nvidia ai endpoint. Implremented inMemory storage for chains using RunnableWithMessageHistory which is analogous to using `ConversationChain` which was used in v0.1 with the default `ConversationBufferMemory`. This class is deprecated in favor of `RunnableWithMessageHistory` in LangChain v0.2 Issue: None Dependencies: None. --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	2 months ago
Erick Friis	334fc1ed1c	mongodb: release 0.1.7 (#24409 )	2 months ago
ccurme	ba74341eee	docs: update tool calling how-to to pass functions to bind_tools (#24402 )	2 months ago
Harrison Chase	3adf710f1d	docs: improve docs on tools (#24404 ) Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	2 months ago
Eun Hye Kim	07c5c60f63	community: fix tool appending logic and update planner prompt in OpenAPI agent toolkit (#24384 ) Description: - Updated the format for the 'Action' section in the planner prompt to ensure it must be one of the tools without additional words. Adjusted the phrasing from "should be" to "must be" for clarity and enforceability. - Corrected the tool appending logic in the `_create_api_controller_agent` function to ensure that `RequestsDeleteToolWithParsing` and `RequestsPatchToolWithParsing` are properly added to the tools list for "DELETE" and "PATCH" operations. Issue: #24382 Dependencies: None Twitter handle: @lunara_x --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	2 months ago
Casey Clements	aade1550c6	docs: Adds MongoDBAtlasVectorSearch to VectorStore list compatible with Indexing API (#24374 ) Adds MongoDBAtlasVectorSearch to list of VectorStores compatible with the Indexing API. (One line change.) As of `langchain-mongodb = "0.1.7"`, the requirements that the VectorStore have both add_documents and delete methods with an ids kwarg is satisfied. #23535 contains the implementation of that, and has been merged.	2 months ago
Chen Xiabin	63c60a31f0	[fix] baidu qianfan AiMessage with usage_metadata (#24389 ) make AIMessage usage_metadata has error	2 months ago
João Dinis Ferreira	242de9aa5e	docs: remove redundant `--quiet` option in `pip install` command (#24397 ) - Description: Removes a redundant option in a `pip install` command in the documentation. - Issue: N/A - Dependencies: N/A	2 months ago
ZhangShenao	916b813107	community[patch]: Fix spelling error in ConversationVectorStoreTokenBufferMemory doc-string (#24385 ) Fix word spelling error in `ConversationVectorStoreTokenBufferMemory`	2 months ago
Rajendra Kadam	1c65529fd7	community[minor]: [PebbloSafeLoader] Rename loader type and add SharePointLoader to supported loaders (#24393 ) Thank you for contributing to LangChain! - [x] PR title: [PebbloSafeLoader] Rename loader type and add SharePointLoader to supported loaders - Description: Minor fixes in the PebbloSafeLoader: - Renamed the loader type from `remote_db` to `cloud_folder`. - Added `SharePointLoader` to the list of loaders supported by PebbloSafeLoader. - Issue: NA - Dependencies: NA - [x] Add tests and docs: NA	2 months ago
Eugene Yurtsev	6182a402f1	experimental[patch]: block a few more things from PALValidator (#24379 ) * Please see security warning already in existing class. * The approach here is fundamentally insecure as it's relying on a block approach rather than an approach based on only running allowed nodes. So users should only use this code if its running from a properly sandboxed environment.	2 months ago
Paolo Ráez	0dec72cab0	Community[patch]: Missing "stream" parameter in cloudflare_workersai (#23987 ) ### Description Missing "stream" parameter. Without it, you'd never receive a stream of tokens when using stream() or astream() ### Issue No existing issue available	2 months ago
Eugene Yurtsev	570566b858	core[patch]: Update API reference for astream events (#24359 ) Update the API reference for astream events to include information about custom events.	2 months ago
Bagatur	f9baaae3ec	docs: clean up tool how to titles (#24373 )	2 months ago
Bagatur	4da1df568a	docs: tools concepts (#24368 )	2 months ago
Erick Friis	96ccba9c27	infra: 15s retry wait on test pypi (#24375 )	2 months ago
Bagatur	a4c101ae97	core[patch]: Release 0.2.21 (#24372 )	2 months ago
William FH	c5a07e2dd8	core[patch]: add InjectedToolArg annotation (#24279 ) ```python from typing_extensions import Annotated from langchain_core.tools import tool, InjectedToolArg from langchain_anthropic import ChatAnthropic @tool def multiply(x: int, y: int, not_for_model: Annotated[dict, InjectedToolArg]) -> str: """multiply.""" return x * y ChatAnthropic(model='claude-3-sonnet-20240229',).bind_tools([multiply]).invoke('5 times 3').tool_calls ''' -> [{'name': 'multiply', 'args': {'x': 5, 'y': 3}, 'id': 'toolu_01Y1QazYWhu4R8vF4hF4z9no', 'type': 'tool_call'}] ''' ``` --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	2 months ago
Erick Friis	80f3d48195	openai: release 0.1.18 (#24369 )	2 months ago
Bagatur	7d83189b19	openai[patch]: use model_name in AzureOpenAI.ls_model_name (#24366 )	2 months ago
Nithish Raghunandanan	eb26b5535a	couchbase: Add chat message history (#24356 ) Description: : Add support for chat message history using Couchbase - [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/ --------- Co-authored-by: Nithish Raghunandanan <nithishr@users.noreply.github.com>	2 months ago
Eugene Yurtsev	96bac8e20d	core[patch]: Fix regression requiring input_variables in few chat prompt templates (#24360 ) * Fix regression that requires users passing input_variables=[]. * Regression introduced by my own changes to this PR: https://github.com/langchain-ai/langchain/pull/22851	2 months ago
Brice Fotzo	034a8c7c1b	community: support advanced text extraction options for pdf documents (#20265 ) Description: - Updated constructors in PyPDFParser and PyPDFLoader to handle `extraction_mode` and additional kwargs, aligning with the capabilities of `PageObject.extract_text()` from pypdf. - Added `test_pypdf_loader_with_layout` along with a corresponding example text file to validate layout extraction from PDFs. Issue: fixes #19735 Dependencies: This change requires updating the pypdf dependency from version 3.4.0 to at least 4.0.0. Additional changes include the addition of a new test test_pypdf_loader_with_layout and an example text file to ensure the functionality of layout extraction from PDFs aligns with the new capabilities. --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Erick Friis <erick@langchain.dev>	2 months ago
hmasdev	a402de3dae	langchain[patch]: fix wrong `dict` key in `OutputFixingParser`, `RetryOutputParser` and `RetryWithErrorOutputParser` (#23967 ) # Description This PR aims to solve a bug in `OutputFixingParser`, `RetryOutputParser` and `RetryWithErrorOutputParser` The bug is that the wrong keyword argument was given to `retry_chain`. The correct keyword argument is 'completion', but 'input' is used. This pull request makes the following changes: 1. correct a `dict` key given to `retry_chain`; 2. add a test when using the default prompt. - `NAIVE_FIX_PROMPT` for `OutputFixingParser`; - `NAIVE_RETRY_PROMPT` for `RetryOutputParser`; - `NAIVE_RETRY_WITH_ERROR_PROMPT` for `RetryWithErrorOutputParser`; 3. ~~add comments on `retry_chain` input and output types~~ clarify `InputType` and `OutputType` of `retry_chain` # Issue The bug is pointed out in https://github.com/langchain-ai/langchain/pull/19792#issuecomment-2196512928 --------- Co-authored-by: Erick Friis <erick@langchain.dev>	2 months ago
Casey Clements	a47f69a120	partners/mongodb : Significant MongoDBVectorSearch ID enhancements (#23535 ) ## Description This pull-request improves the treatment of document IDs in `MongoDBAtlasVectorSearch`. Class method signatures of add_documents, add_texts, delete, and from_texts now include an `ids:Optional[List[str]]` keyword argument permitting the user greater control. Note that, as before, IDs may also be inferred from `Document.metadata['_id']` if present, but this is no longer required, IDs can also optionally be returned from searches. This PR closes the following JIRA issues. * [PYTHON-4446](https://jira.mongodb.org/browse/PYTHON-4446) MongoDBVectorSearch delete / add_texts function rework * [PYTHON-4435](https://jira.mongodb.org/browse/PYTHON-4435) Add support for "Indexing" * [PYTHON-4534](https://jira.mongodb.org/browse/PYTHON-4534) Ensure datetimes are json-serializable --------- Co-authored-by: Erick Friis <erick@langchain.dev>	2 months ago
Erick Friis	cc2cbfabfc	milvus: release 0.1.2 (#24365 )	2 months ago
Eugene Yurtsev	9e4a0e76f6	core[patch]: Fix one unit test for chat prompt template (#24362 ) Minor change that fixes a unit test that had missing assertions.	2 months ago
Erick Friis	81639243e2	openai: release 0.1.17 (#24361 )	2 months ago
Erick Friis	61976a4147	pinecone: release 0.1.2 (#24355 )	2 months ago
Bagatur	b5360e2e5f	community[patch]: Release 0.2.8 (#24354 )	2 months ago
ccurme	4cf67084d3	openai[patch]: fix key collision and _astream (#24345 ) Fixes small issues introduced in https://github.com/langchain-ai/langchain/pull/24150 (unreleased).	2 months ago
Luis Moros	bcb5f354ad	community: Fix SQLDatabse.from_databricks issue when ran from Job (#24346 ) - Description: When SQLDatabase.from_databricks is ran from a Databricks Workflow job, line 205 (default_host = context.browserHostName) throws an ``AttributeError`` as the ``context`` object has no ``browserHostName`` attribute. The fix handles the exception and sets the ``default_host`` variable to null --------- Co-authored-by: lmorosdb <lmorosdb> Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>	2 months ago
Bagatur	24e9b48d15	langchain[patch]: Release 0.2.9 (#24327 )	2 months ago
Rafael Pereira	cf28708e7b	Neo4j: Update with non-deprecated cypher methods, and new method to associate relationship embeddings (#23725 ) Description: At the moment neo4j wrapper is using setVectorProperty, which is deprecated ([link](https://neo4j.com/docs/operations-manual/5/reference/procedures/#procedure_db_create_setVectorProperty)). I replaced with the non-deprecated version. Neo4j recently introduced a new cypher method to associate embeddings into relations using "setRelationshipVectorProperty" method. In this PR I also implemented a new method to perform this association maintaining the same format used in the "add_embeddings" method which is used to associate embeddings into Nodes. I also included a test case for this new method.	2 months ago
maang-h	2a3288b15d	docs: Add ChatBaichuan docstrings (#24348 ) - Description: Add ChatBaichuan rich docstrings. - Issue: the issue #22296	2 months ago
Srijan Dubey	1792684e8f	removed deprecated classes from pipelineai.ipynb, added support for LangChain v0.2 for PipelineAI integration (#24333 ) Description: added support for LangChain v0.2 for PipelineAI integration. Removed deprecated classes and incorporated support for LangChain v0.2 to integrate with PipelineAI. Removed LLMChain and replaced it with Runnable interface. Also added StrOutputParser, that parses LLMResult into the top likely string. Issue: None Dependencies: None. --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	2 months ago
Tobias Sette	e60ad12521	docs(infobip.ipynb): fix typo (#24328 )	2 months ago
Rafael Pereira	fc41730e28	neo4j: Fix test for order-insensitive comparison and floating-point precision issues (#24338 ) Description: This PR addresses two main issues in the `test_neo4jvector.py`: 1. Order-insensitive Comparison: Modified the `test_retrieval_dictionary` to ensure that it passes regardless of the order of returned values by parsing `page_content` into a structured format (dictionary) before comparison. 2. Floating-point Precision: Updated `test_neo4jvector_relevance_score` to handle minor floating-point precision differences by using the `isclose` function for comparing relevance scores with a relative tolerance. Errors addressed: - test_neo4jvector_relevance_score: ``` AssertionError: assert [(Document(page_content='foo', metadata={'page': '0'}), 1.0000014305114746), (Document(page_content='bar', metadata={'page': '1'}), 0.9998371005058289), (Document(page_content='baz', metadata={'page': '2'}), 0.9993508458137512)] == [(Document(page_content='foo', metadata={'page': '0'}), 1.0), (Document(page_content='bar', metadata={'page': '1'}), 0.9998376369476318), (Document(page_content='baz', metadata={'page': '2'}), 0.9993523359298706)] At index 0 diff: (Document(page_content='foo', metadata={'page': '0'}), 1.0000014305114746) != (Document(page_content='foo', metadata={'page': '0'}), 1.0) Full diff: - [(Document(page_content='foo', metadata={'page': '0'}), 1.0), + [(Document(page_content='foo', metadata={'page': '0'}), 1.0000014305114746), ? +++++++++++++++ - (Document(page_content='bar', metadata={'page': '1'}), 0.9998376369476318), ? ^^^ ------ + (Document(page_content='bar', metadata={'page': '1'}), 0.9998371005058289), ? ^^^^^^^^^ - (Document(page_content='baz', metadata={'page': '2'}), 0.9993523359298706), ? ---------- + (Document(page_content='baz', metadata={'page': '2'}), 0.9993508458137512), ? ++++++++++ ] ``` - test_retrieval_dictionary: ``` AssertionError: assert [Document(page_content='skills:\n- Python\n- Data Analysis\n- Machine Learning\nname: John\nage: 30\n')] == [Document(page_content='skills:\n- Python\n- Data Analysis\n- Machine Learning\nage: 30\nname: John\n')] At index 0 diff: Document(page_content='skills:\n- Python\n- Data Analysis\n- Machine Learning\nname: John\nage: 30\n') != Document(page_content='skills:\n- Python\n- Data Analysis\n- Machine Learning\nage: 30\nname: John\n') Full diff: - [Document(page_content='skills:\n- Python\n- Data Analysis\n- Machine Learning\nage: 30\nname: John\n')] ? --------- + [Document(page_content='skills:\n- Python\n- Data Analysis\n- Machine Learning\nage: John\nage: 30\n')] ? +++++++++ ```	2 months ago
Erick Friis	47ed7f766a	infra: fix release prerelease deps bug (#24323 )	2 months ago
Bagatur	80e7cd6cff	core[patch]: Release 0.2.20 (#24322 )	2 months ago
Erick Friis	6c3e65a878	infra: prerelease dep checking on release (#23269 )	2 months ago
Eugene Yurtsev	616196c620	Docs: Add how to dispatch custom callback events (#24278 ) * Add how-to guide for dispatching custom callback events. * Add links from index to the how to guide * Add link from streaming from within a tool * Update versionadded to correct release https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.2.15	2 months ago
Erick Friis	dd7938ace8	docs: readthedocs deprecation fix (#24321 ) https://about.readthedocs.com/blog/2024/07/addons-by-default/#how-does-it-affect-my-projects we use build.command so we're already using addons, so I think this is it	2 months ago
Srijan Dubey	ef07308c30	Upgraded shaleprotocol to use langchain v0.2 removed deprecated classes (#24320 ) Description: Added support for langchain v0.2 for shale protocol. Replaced LLMChain with Runnable interface which allows any two Runnables to be 'chained' together into sequences. Also added StreamingStdOutCallbackHandler. Callback handler for streaming. Issue: None Dependencies: None.	2 months ago
pbharti0831	049bc37111	Cookbook for applying RAG locally using open source models and tools on CPU (#24284 ) This cookbook guides user to implement RAG locally on CPU using langchain tools and open source models. It enables Llama2 model to answer queries about Intel Q1 2024 earning release using RAG pipeline. Main libraries are langchain, llama-cpp-python and gpt4all. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Sriragavi <sriragavi.r@intel.com> Co-authored-by: Chester Curme <chester.curme@gmail.com>	2 months ago
Leonid Ganeline	5ccf8ebfac	core: docstrings `vectorstores` update (#24281 ) Added missed docstrings. Formatted docstrings to the consistent form. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	2 months ago
Erick Friis	1e9cc02ed8	openai: raw response headers (#24150 )	2 months ago

... 2 3 4 5 6 ...

10593 Commits (5f593c172a10f448f95f71bb40eb839aac327661) All Branches Search

10593 Commits (5f593c172a10f448f95f71bb40eb839aac327661)

All Branches