643 Commits (611d5a161868d6f83a88d6d47d5f7a4f79ff8045)

Author	SHA1	Message	Date
Nikhil Kumar	635b3372bd	community[minor]: Add support for translation in HuggingFacePipeline (#19190) ... - [x] **Support for translation**: "community: Add support for translation in `HuggingFacePipeline`" - [x] **Add support for translation in `HuggingFacePipeline`**: - **Description:** Add support for translation in `HuggingFacePipeline`, which earlier used to support only text summarization and generation. - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** None	5 months ago
k.muto	8d2c34e655	community: Fix all page numbers were the same for _BaseGoogleVertexAISearchRetriever (#19175) ... - Description: - This pull request is to fix a bug where page numbers were not set correctly. In the current code, all chunks share the same metadata object doc_metadata, so the page number is set with the same value for all documents. To fix this, I changed to using separate metadata objects for each chunk. - Issue: - None - Dependencies: - No additional dependencies are required for this change. - Twitter handle: - @eycjur - Test - Even if it's not a bug, there are cases where everything ends up with the same number of pages, so it's very difficult for me to write integration tests.	5 months ago
Cailin Wang	7cd87d2f6a	community: Add `partition` parameter to DashVector (#19023) ... **Description**: DashVector Add partition parameter **Twitter handle**: @CailinWang_ --------- Co-authored-by: root <root@Bluedot-AI>	5 months ago
Rodrigo Nogueira	e64cf1aba4	community: Add model argument for maritalk models and better error handling (#19187)	5 months ago
Sergey Kozlov	1a55e950aa	community[patch]: support fastembed v1 and v2 (#19125) ... **Description:** #18040 forces `fastembed>2.0`, and this causes dependency conflicts with the new `unstructured` package (different `onnxruntime`). There may be other dependency conflicts.. The only way to use `langchain-community>=0.0.28` is rollback to `unstructured 0.10.X`. But new `unstructured` contains many fixes. This PR allows to use both `fastembed` `v1` and `v2`. How to reproduce: `pyproject.toml`: ```toml [tool.poetry] name = "depstest" version = "0.0.0" description = "test" authors = ["<dev@example.org>"] [tool.poetry.dependencies] python = ">=3.10,<3.12" langchain-community = "^0.0.28" fastembed = "^0.2.0" unstructured = {extras = ["pdf"], version = "^0.12"} ``` ```bash $ poetry lock ``` Co-authored-by: Sergey Kozlov <sergey.kozlov@ludditelabs.io>	5 months ago
高远	ef9813dae6	docs: add vikingdb docstrings(#19016) ... Co-authored-by: gaoyuan <gaoyuan.20001218@bytedance.com>	5 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.	5 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):  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	5 months ago
Christophe Bornet	f2a7dda4bd	community[patch]: Use langchain-astradb for AstraDB doc loader (#19071) ... Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	5 months ago
Holt Skinner	cee03630d9	community[patch]: Add Blended Search Support to `GoogleVertexAISearchRetriever` (#19082) ... https://cloud.google.com/generative-ai-app-builder/docs/create-data-store-es#multi-data-stores --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	5 months ago
case-k	ebc4a64f9e	docs: fix databricks document url (#19096) ... Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	5 months ago
Guangdong Liu	cced3eb9bc	community[patch]: Fix sparkllm embeddings api bug. (#19122) ... - **Description:** Fix sparkllm embeddings api bug. @baskaryan PTAL	5 months ago
kaijietti	c20aeef79a	community[patch]: implement qdrant _aembed_query and use it in other async funcs (#19155) ... `amax_marginal_relevance_search ` and `asimilarity_search_with_score ` should use an async version of `_embed_query `.	5 months ago
Barun Amalkumar Halder	34d6f0557d	community[patch] : publishes duration as milliseconds to Fiddler (#19166) ... **Description:** Many LLM steps complete in sub-second duration, which can lead to non-collection of duration field for Fiddler. This PR updates duration from seconds to milliseconds. **Issue:** [INTERNAL] FDL-17568 **Dependencies:** NA **Twitter handle:** behalder Co-authored-by: Barun Halder <barun@fiddler.ai>	5 months ago
Barun Amalkumar Halder	b551d49cf5	community[patch] : adds feedback and status for Fiddler callback handler events (#19157) ... **Description:** This PR adds updates the fiddler events schema to also pass user feedback, and llm status to fiddler **Tickets:** [INTERNAL] FDL-17559 **Dependencies:** NA **Twitter handle:** behalder Co-authored-by: Barun Halder <barun@fiddler.ai>	5 months ago
Juan Felipe Arias	f5b9aedc48	community[patch]: add args_schema to sql_database tools for langGraph integration (#18595) ... - **Description:** This modification adds pydantic input definition for sql_database tools. This helps for function calling capability in LangGraph. Since actions nodes will usually check for the args_schema attribute on tools, This update should make these tools compatible with it (only implemented on the InfoSQLDatabaseTool) - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** juanfe8881	5 months ago
fengjial	c922ea36cb	community[minor]: Add Baidu VectorDB as vector store (#17997) ... Co-authored-by: fengjialin <fengjialin@MacBook-Pro.local>	5 months ago
Erick Friis	781aee0068	community, langchain, infra: revert store extended test deps outside of poetry (#19153) ... Reverts langchain-ai/langchain#18995 Because it makes installing dependencies in python 3.11 extended testing take 80 minutes	5 months ago
Erick Friis	9e569d85a4	community, langchain, infra: store extended test deps outside of poetry (#18995) ... poetry can't reliably handle resolving the number of optional "extended test" dependencies we have. If we instead just rely on pip to install extended test deps in CI, this isn't an issue.	5 months ago
Erick Friis	7ce81eb6f4	voyageai[patch]: init package (#19098) ... Co-authored-by: fodizoltan <zoltan@conway.expert> Co-authored-by: Yujie Qian <thomasq0809@gmail.com> Co-authored-by: fzowl <160063452+fzowl@users.noreply.github.com>	5 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>	5 months ago
Eugene Yurtsev	6cdca4355d	community[minor]: Revamp PGVector Filtering (#18992) ... This PR makes the following updates in the pgvector database: 1. Use JSONB field for metadata instead of JSON 2. Update operator syntax to include required `$` prefix before the operators (otherwise there will be name collisions with fields) 3. The change is non-breaking, old functionality is still the default, but it will emit a deprecation warning 4. Previous functionality has bugs associated with comparisons due to casting to text (so lexical ordering is used incorrectly for numeric fields) 5. Adds an a GIN index on the JSONB field for more efficient querying	5 months ago
Anton Parkhomenko	ae73b9d839	community[patch]: Fix NotionDBLoader 400 Error by conditionally adding filter parameter (#19075) ... - **Description:** This change fixes a bug where attempts to load data from Notion using the NotionDBLoader resulted in a 400 Bad Request error. The issue was traced to the unconditional addition of an empty 'filter' object in the request payload, which Notion's API does not accept. The modification ensures that the 'filter' object is only included in the payload when it is explicitly provided and not empty, thus preventing the 400 error from occurring. - **Issue:** Fixes [#18009](https://github.com/langchain-ai/langchain/issues/18009) - **Dependencies:** None - **Twitter handle:** @gunnzolder Co-authored-by: Anton Parkhomenko <anton@merge.rocks>	5 months ago
Leonid Ganeline	9c8523b529	community[patch]: flattening imports 3 (#18939) ... @eyurtsev	5 months ago
Erick Friis	af50f21765	community[patch]: release 0.0.28 (#18993)	5 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>	5 months ago
Tymofii	0bec1f6877	commnity[patch]: refactor code for faiss vectorstore, update faiss vectorstore documentation (#18092) ... **Description:** Refactor code of FAISS vectorcstore and update the related documentation. Details: - replace `.format()` with f-strings for strings formatting; - refactor definition of a filtering function to make code more readable and more flexible; - slightly improve efficiency of `max_marginal_relevance_search_with_score_by_vector` method by removing unnecessary looping over the same elements; - slightly improve efficiency of `delete` method by using set data structure for checking if the element was already deleted; **Issue:** fix small inconsistency in the documentation (the old example was incorrect and unappliable to faiss vectorstore) **Dependencies:** basic langchain-community dependencies and `faiss` (for CPU or for GPU) **Twitter handle:** antonenkodev	5 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	5 months ago
Virat Singh	cafffe8a21	community: Add PolygonAggregates tool (#18882) ... **Description:** In this PR, I am adding a `PolygonAggregates` tool, which can be used to get historical stock price data (called aggregates by Polygon) for a given ticker. Polygon [docs](https://polygon.io/docs/stocks/get_v2_aggs_ticker__stocksticker__range__multiplier___timespan___from___to) for this endpoint. **Twitter**: [@virattt](https://twitter.com/virattt)	5 months ago
Mohammad Mohtashim	43db4cd20e	core[major]: On Tool End Observation Casting Fix (#18798) ... This PR updates the on_tool_end handlers to return the raw output from the tool instead of casting it to a string. This is technically a breaking change, though it's impact is expected to be somewhat minimal. It will fix behavior in `astream_events` as well. Fixes the following issue #18760 raised by @eyurtsev --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	5 months ago
Massimiliano Pronesti	8113d612bb	community[patch]: support modin document loader (#18866) ... Langchain community document loaders support `pyspark`, `polars`, and `pandas` dataframes but not `modin`'s. This PR addresses this point.	6 months ago
Pol Ruiz Farre	a7f63d8cb4	community[patch]: Fix BasePDFLoader suffix for s3 presigned urls (#18844) ... BasePDFLoader doesn't parse the suffix of the file correctly when parsing S3 presigned urls. This fix enables the proper detection and parsing of S3 presigned URLs to prevent errors such as `OSError: [Errno 36] File name too long`. No additional dependencies required.	6 months ago
Joshua Carroll	ddaf9de169	community: Fix bug with StreamlitChatMessageHistory (#18834) ... - **Description:** Fix Streamlit bug which was introduced by https://github.com/langchain-ai/langchain/pull/18250, update integration test - **Issue:** https://github.com/langchain-ai/langchain/issues/18684 - **Dependencies:** None	6 months ago
Tomaz Bratanic	a28be31a96	Switch to md5 for deduplication in neo4j integrations (#18846) ... Deduplicate documents using MD5 of the page_content. Also allows for custom deduplication with graph ingestion method by providing metadata id attribute --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	6 months ago
Leonid Ganeline	476d6dc596	community[patch]: Use getattr for `toolkits` imports (#18825) ... This will preserve the namespace, without actually loading the underlying packages on init.	6 months ago
Luis Antonio Vieira Junior	67c880af74	community[patch]: adding linearization config to AmazonTextractPDFLoader (#17489) ... - **Description:** Adding an optional parameter `linearization_config` to the `AmazonTextractPDFLoader` so the caller can define how the output will be linearized, instead of forcing a predefined set of linearization configs. It will still have a default configuration as this will be an optional parameter. - **Issue:** #17457 - **Dependencies:** The same ones that already exist for `AmazonTextractPDFLoader` - **Twitter handle:** [@lvieirajr19](https://twitter.com/lvieirajr19) --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 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>	6 months ago
Keith Chan	914af69b44	community[patch]: Update azuresearch vectorstore from_texts() method to include fields argument (#17661) ... - **Description:** Update azuresearch vectorstore from_texts() method to include fields argument, necessary for creating an Azure AI Search index with custom fields. - **Issue:** Currently index fields are fixed to default fields if Azure Search index is created using from_texts() method - **Dependencies:** None - **Twitter handle:** None --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
al1p	46f0cea2b9	community[patch][: improved the suffix prompt to avoid loop (#17791) ... Small improvement to the openapi prompt. The agent was not finding the server base URL (looping through all nodes). This small change narrows the search and enables finding the url faster. No dependency Twitter : @al1pra	6 months ago
Théo LEBRUN	cf94091cd0	community[patch]: Skip nested directories when using S3DirectoryLoader (#17829) ... - **Description:** `S3DirectoryLoader` is failing if prefix is a folder (ex: `my_folder/`) because `S3FileLoader` will try to load that folder and will fail. This PR skip nested directories so prefix can be set to folder instead of `my_folder/files_prefix`. - **Issue:** - #11917 - #6535 - #4326 - **Dependencies:** none - **Twitter handle:** @Falydoor - [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/	6 months ago
Venkatesan	7a18b63dbf	community[patch]: Mongo index creation (#17748) ... - [ ] Title: Mongodb: MongoDB connection performance improvement. - [ ] Message: - **Description:** I made collection index_creation as optional. Index Creation is one time process. - **Issue:** MongoDBChatMessageHistory class object is attempting to create an index during connection, causing each request to take longer than usual. This should be optional with a parameter. - **Dependencies:** N/A - **Branch to be checked:** origin/mongo_index_creation --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
wt3639	5b5b37a999	community[patch]: Add embedding instruction to HuggingFaceBgeEmbeddings (#18017) ... - **Description:** Add embedding instruction to HuggingFaceBgeEmbeddings, so that it can be compatible with nomic and other models that need embedding instruction. --------- Co-authored-by: Tao Wu <tao.wu@rwth-aachen.de> Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Ishani Vyas	2b0cbd65ba	community[patch]: Add Passio Nutrition AI Food Search Tool to Community Package (#18278) ... ## Add Passio Nutrition AI Food Search Tool to Community Package ### Description We propose adding a new tool to the `community` package, enabling integration with Passio Nutrition AI for food search functionality. This tool will provide a simple interface for retrieving nutrition facts through the Passio Nutrition AI API, simplifying user access to nutrition data based on food search queries. ### Implementation Details - **Class Structure:** Implement `NutritionAI`, extending `BaseTool`. It includes an `_run` method that accepts a query string and, optionally, a `CallbackManagerForToolRun`. - **API Integration:** Use `NutritionAIAPI` for the API wrapper, encapsulating all interactions with the Passio Nutrition AI and providing a clean API interface. - **Error Handling:** Implement comprehensive error handling for API request failures. ### Expected Outcome - **User Benefits:** Enable easy querying of nutrition facts from Passio Nutrition AI, enhancing the utility of the `langchain_community` package for nutrition-related projects. - **Functionality:** Provide a straightforward method for integrating nutrition information retrieval into users' applications. ### Dependencies - `langchain_core` for base tooling support - `pydantic` for data validation and settings management - Consider `requests` or another HTTP client library if not covered by `NutritionAIAPI`. ### Tests and Documentation - **Unit Tests:** Include tests that mock network interactions to ensure tool reliability without external API dependency. - **Documentation:** Create an example notebook in `docs/docs/integrations/tools/passio_nutrition_ai.ipynb` showing usage, setup, and example queries. ### Contribution Guidelines Compliance - Adhere to the project's linting and formatting standards (`make format`, `make lint`, `make test`). - Ensure compliance with LangChain's contribution guidelines, particularly around dependency management and package modifications. ### Additional Notes - Aim for the tool to be a lightweight, focused addition, not introducing significant new dependencies or complexity. - Potential future enhancements could include caching for common queries to improve performance. ### Twitter Handle - Here is our Passio AI [twitter handle](https://twitter.com/@passio_ai) where we announce our products. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.	6 months ago
Kushagra	b1f22bf76c	community[minor]: added a feature to filter documents in Mongoloader (#18253) ... "community: added a feature to filter documents in Mongoloader" - **Description:** added a feature to filter documents in Mongoloader - **Feature:** the feature #18251 - **Dependencies:** No - **Twitter handle:** https://twitter.com/im_Kushagra	6 months ago
Eugene Yurtsev	1f50274df7	community[patch]: Add pgvector to docker compose and update settings used in integration test (#18815)	6 months ago
Christophe Bornet	e54a49b697	community[minor]: Add lazy_table_reflection param to SqlDatabase (#18742) ... For some DBs with lots of tables, reflection of all the tables can take very long. So this change will make the tables be reflected lazily when get_table_info() is called and `lazy_table_reflection` is True.	6 months ago
Christophe Bornet	ead2a74806	community: Implement lazy_load() for JSONLoader (#18643) ... Covered by `tests/unit_tests/document_loaders/test_json_loader.py`	6 months ago
Phat Vo	3ecb903d49	community[patch] : Tidy up and update Clarifai SDK functions (#18314) ... Description : * Tidy up, add missing docstring and fix unused params * Enable using session token	6 months ago
Tomaz Bratanic	4bfe888717	comunity[patch]: Fix neo4j sanitizing values (#18750) ... Fixing sanitization for when deeply nested lists appear	6 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	6 months ago