2828 Commits (0f99646ca6b2295e440447287bd4cbb0175e2d79)

Author	SHA1	Message	Date
Ashley Xu	0f99646ca6	docs: add the enrollment form for`BigQueryVectorSearch` (#16240) ... This PR adds the enrollment form for BigQueryVectorSearch.	8 months ago
Eugene Yurtsev	177af65dc4	core[minor]: RFC Add astream_events to Runnables (#16172) ... This PR adds `astream_events` method to Runnables to make it easier to stream data from arbitrary chains. * Streaming only works properly in async right now * One should use `astream()` with if mixing in imperative code as might be done with tool implementations * Astream_log has been modified with minimal additive changes, so no breaking changes are expected * Underlying callback code / tracing code should be refactored at some point to handle things more consistently (OK for now) - ~~[ ] verify event for on_retry~~ does not work until we implement streaming for retry - ~~[ ] Any rrenaming? Should we rename "event" to "hook"?~~ - [ ] Any other feedback from community? - [x] throw NotImplementedError for `RunnableEach` for now ## Example See this [Example Notebook](dbbc7fa0d6/docs/docs/modules/agents/how_to/streaming_events.ipynb) for an example with streaming in the context of an Agent ## Event Hooks Reference Here is a reference table that shows some events that might be emitted by the various Runnable objects. Definitions for some of the Runnable are included after the table. | event | name | chunk | input | output | |----------------------|------------------|---------------------------------|-----------------------------------------------|-------------------------------------------------| | on_chat_model_start | [model name] | | {"messages": [[SystemMessage, HumanMessage]]} | | | on_chat_model_stream | [model name] | AIMessageChunk(content="hello") | | | | on_chat_model_end | [model name] | | {"messages": [[SystemMessage, HumanMessage]]} | {"generations": [...], "llm_output": None, ...} | | on_llm_start | [model name] | | {'input': 'hello'} | | | on_llm_stream | [model name] | 'Hello' | | | | on_llm_end | [model name] | | 'Hello human!' | | on_chain_start | format_docs | | | | | on_chain_stream | format_docs | "hello world!, goodbye world!" | | | | on_chain_end | format_docs | | [Document(...)] | "hello world!, goodbye world!" | | on_tool_start | some_tool | | {"x": 1, "y": "2"} | | | on_tool_stream | some_tool | {"x": 1, "y": "2"} | | | | on_tool_end | some_tool | | | {"x": 1, "y": "2"} | | on_retriever_start | [retriever name] | | {"query": "hello"} | | | on_retriever_chunk | [retriever name] | {documents: [...]} | | | | on_retriever_end | [retriever name] | | {"query": "hello"} | {documents: [...]} | | on_prompt_start | [template_name] | | {"question": "hello"} | | | on_prompt_end | [template_name] | | {"question": "hello"} | ChatPromptValue(messages: [SystemMessage, ...]) | Here are declarations associated with the events shown above: `format_docs`: ```python def format_docs(docs: List[Document]) -> str: '''Format the docs.''' return ", ".join([doc.page_content for doc in docs]) format_docs = RunnableLambda(format_docs) ``` `some_tool`: ```python @tool def some_tool(x: int, y: str) -> dict: '''Some_tool.''' return {"x": x, "y": y} ``` `prompt`: ```python template = ChatPromptTemplate.from_messages( [("system", "You are Cat Agent 007"), ("human", "{question}")] ).with_config({"run_name": "my_template", "tags": ["my_template"]}) ```	8 months ago
Erick Friis	aa35b43bcd	docs, google-vertex[patch]: function docs (#16231)	8 months ago
Erick Friis	f2b2d59e82	docs: transport and client options docs (#16226) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ 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. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	8 months ago
Rajesh Thallam	6bc6d64a12	langchain_google_vertexai[patch]: Add support for SystemMessage for Gemini chat model (#15933) ... - **Description:** In Google Vertex AI, Gemini Chat models currently doesn't have a support for SystemMessage. This PR adds support for it only if a user provides additional convert_system_message_to_human flag during model initialization (in this case, SystemMessage would be prepended to the first HumanMessage). **NOTE:** The implementation is similar to #14824 - **Twitter handle:** rajesh_thallam --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
jzaldi	ed118950fe	docs: Updated integration docs structure for llm/google_vertex_ai_palm (#16091) ... - **Description**: Updated doc for llm/google_vertex_ai_palm with new functions: `invoke`, `stream`... Changed structure of the document to match the required one. - **Issue**: #15664 - **Dependencies**: None - **Twitter handle**: None --------- Co-authored-by: Jorge Zaldívar <jzaldivar@google.com>	8 months ago
Bagatur	aa2e642ce3	docs: tool use nits (#16211)	8 months ago
Eugene Zapolsky	6b9e3ed9e9	google-vertexai[minor]: added safety_settings property to gemini wrapper (#15344) ... **Description:** Gemini model has quite annoying default safety_settings settings. In addition, current VertexAI class doesn't provide a property to override such settings. So, this PR aims to - add safety_settings property to VertexAI - fix issue with incorrect LLM output parsing when LLM responds with appropriate 'blocked' response - fix issue with incorrect parsing LLM output when Gemini API blocks prompt itself as inappropriate - add safety_settings related tests I'm not enough familiar with langchain code base and guidelines. So, any comments and/or suggestions are very welcome. **Issue:** it will likely fix #14841 --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
Bagatur	27ad65cc68	docs: add tool use diagrams (#16207)	8 months ago
Bagatur	27ed2673da	docs: model io order (#16163)	8 months ago
Bagatur	2af813c7eb	docs: bump sphinx>=5 (#16162)	8 months ago
David DeCaprio	ec9642d667	docs: Updated MongoDB Chat history example notebook to use LCEL format. (#15750) ... - **Description:** Updated the MongoDB example integration notebook to latest standards - **Issue:** [15664](https://github.com/langchain-ai/langchain/issues/15664) - **Dependencies:** None - **Twitter handle:** @davedecaprio --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Bagatur	e7ddec1f2c	docs: change parallel doc name (#16152)	8 months ago
Joshua Carroll	bc0cb1148a	docs: Fix StreamlitChatMessageHistory docs to latest API (#16072) ... - **Description:** Update [this page](https://python.langchain.com/docs/integrations/memory/streamlit_chat_message_history) to use the latest API - **Issue:** https://github.com/langchain-ai/langchain/issues/13995 - **Dependencies:** None - **Twitter handle:** @OhSynap	8 months ago
David DeCaprio	9c2f1f07a0	docs: Updated SQLite example to use LCEL and SQLChatMessageHistory (#16094) ... - **Description:** Updated the SQLite example integration notebook to latest standards - **Issue:** [15664](https://github.com/langchain-ai/langchain/issues/15664) - **Dependencies:** None - **Twitter handle:** @davedecaprio	8 months ago
Abhinav	da96c511d1	docs: Replace azure_cosmos_db_vector_search with azure_cosmos_db in Cosmos DB Documentation (#16122) ... **Description**: This PR fixes an error in the documentation for Azure Cosmos DB Integration. **Issue**: The correct way to import `AzureCosmosDBVectorSearch` is ```python from langchain_community.vectorstores.azure_cosmos_db import ( AzureCosmosDBVectorSearch, ) ``` While the [documentation](https://python.langchain.com/docs/integrations/vectorstores/azure_cosmos_db) states it to be ```python from langchain_community.vectorstores.azure_cosmos_db_vector_search import ( AzureCosmosDBVectorSearch, CosmosDBSimilarityType, ) ``` As you can see in [azure_cosmos_db.py](c323742f4f/libs/langchain/langchain/vectorstores/azure_cosmos_db.py (L1C45-L2)) **Dependencies:**: None **Twitter handle**: None	8 months ago
purificant	3606c5d5e9	infra: update poetry 1.6.1 -> 1.7.1 (#15027)	8 months ago
Ikko Eltociear Ashimine	a35e5f19a8	docs: Update gradient.ipynb (#16149) ... Enviroment -> Environment	8 months ago
David	c323742f4f	mistralai[minor]: Add embeddings (#15282) ... - **Description:** Adds MistralAIEmbeddings class for embeddings, using the new official API. - **Dependencies:** mistralai - **Tag maintainer**: @efriis, @hwchase17 - **Twitter handle:** @LMS_David_RS Create `integrations/text_embedding/mistralai.ipynb`: an example notebook for MistralAIEmbeddings class Modify `embeddings/__init__.py`: Import the class Create `embeddings/mistralai.py`: The embedding class Create `integration_tests/embeddings/test_mistralai.py`: The test file. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	8 months ago
Leonid Ganeline	f974eb5b8b	docs: updated `Anyscale` page (#16107) ... - added description - fixed broken links - added setting instructions - added the Chat model reference	8 months ago
Bagatur	8840a8cc95	docs: tool-use use case (#15783) ... Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
Christophe Bornet	6b6269441c	docs: Add page for AstraDB self retriever (#16077) ... Preview: https://langchain-git-fork-cbornet-astra-self-retriever-docs-langchain.vercel.app/docs/integrations/retrievers/self_query/astradb	8 months ago
Juan Bustos	5f057f24ac	docs: Update elasticsearch.ipynb (#16090) ... Fixed a typo, the parameter used for the Elasticsearch API key was called api_key, but the parameter is called es_api_key.	8 months ago
高远	061e63eef2	community[minor]: add vikingdb vecstore (#15155) ... --------- Co-authored-by: gaoyuan <gaoyuan.20001218@bytedance.com>	8 months ago
Zhichao HAN	5cf06db3b3	community[minor]: add JsonRequestsWrapper tool (#15374) ... **Description:** This new feature enhances the flexibility of pipeline integration, particularly when working with RESTful APIs. ``JsonRequestsWrapper`` allows for the decoding of JSON output, instead of the only option for text output. --------- Co-authored-by: Zhichao HAN <hanzhichao2000@hotmail.com>	8 months ago
Averi Kitsch	ee378a0f40	docs: add page for Firestore Chat Message History integration (#15554) ... - **Description:** Adds documentation for the `FirestoreChatMessageHistory` integration and lists integration in Google's documentation - **Issue:** NA - **Dependencies:** No --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
盐粒 Yanli	ddf4e7c633	community[minor]: Update pgvecto_rs to use its high level sdk (#15574) ... - **Description:** Update pgvecto_rs to use its high level sdk, - **Issue:** fix #15173	8 months ago
axiangcoding	daa9ccae52	community[patch]: deprecate ErnieBotChat and ErnieEmbeddings classes (#15862) ... - **Description:** add deprecated warning for ErnieBotChat and ErnieEmbeddings. - These two classes **lack maintenance** and do not use the sdk provided by qianfan, which means hard to implement some key feature like streaming. - The alternative `langchain_community.chat_models.QianfanChatEndpoint` and `langchain_community.embeddings.QianfanEmbeddingsEndpoint` can completely replace these two classes, only need to change configuration items. - **Issue:** None, - **Dependencies:** None, - **Twitter handle:** None --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Eugene Yurtsev	7c57cfd8f0	docs: Update OpenAI functions agent (#15894) ... Add info and a tip explaining when to use this agent.	8 months ago
Eugene Yurtsev	beec7259c8	docs: Add info admonitions to a few agents (#15899) ... Add admonitions directly in the agent page to explain constraints and include a link to agent types.	8 months ago
Bigtable123	7306032dcf	docs: update baidu_qianfan_endpoint.ipynb doc (#15940) ... - **Description:** Updated the docs for the chat integration module baidu_qianfan_endpoint.ipynb - **Issue:** #15664 - **Dependencies:**N/A	8 months ago
Bhadresh Savani	6137c7608d	docs: Integration Documentation updated run to invoke for llms/ai21.ipynb (#15889) ... - **Description:** Updated Integration Documentation for [llms/ai21.ipynb](https://github.com/langchain-ai/langchain/blob/master/docs/docs/integrations/llms/ai21.ipynb) - **Issue:** #15664, - **Dependencies:** NA, - **Twitter handle:** @BhadreshSavani	8 months ago
Massimiliano Pronesti	e80aab2275	docs(community): update Amadeus toolkit to langchain v0.1 (#15976) ... - **Description:** docs update following the changes introduced in #15879 <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ 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. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	8 months ago
Ashley Xu	ce7723c1e5	community[minor]: add additional support for `BigQueryVectorSearch` (#15904) ... BigQuery vector search lets you use GoogleSQL to do semantic search, using vector indexes for fast but approximate results, or using brute force for exact results. This PR: 1. Add `metadata[_job_ib]` in Document returned by any similarity search 2. Add `explore_job_stats` to enable users to explore job statistics and better the debuggability 3. Set the minimum row limit for running create vector index.	8 months ago
Antonio Mindov	fb7e66b809	docs: fix typo in inspect runnables docs (#15994) ... - **Description:** Fixing a typo related to prompts in the inspecting runnables docs	8 months ago
Karim Lalani	14244bd7e5	community[minor]: Added document loader for SurrealDB (#15995) ... Added a simple document loader to work with SurrealDB.	8 months ago
Karim Lalani	768e5e33bc	community[minor]: Fix to match SurrealDB 0.3.2 SDK (#15996) ... New version of SurrealDB python sdk was causing the integration to break. This fix addresses that change.	8 months ago
Bagatur	60d6a416e6	docs: fix self query diagram (#16043)	8 months ago
Mahad	f7706637a8	docs: fix documentation broken link in integrations chroma (#16041) ... - **Description:** Fixed broken link in the documentation for Chroma., - **Issue:** - **Dependencies:**	8 months ago
Erick Friis	7b084b4cc7	docs: more pip installs (#15771) ... - vertex chat - google - some pip openai - percent and openai - all percent - more - pip - fmt - docs: google vertex partner docs - fmt - docs: more pip installs	8 months ago
Bagatur	3f75fd41cc	docs: agent table fix (#15964)	8 months ago
Virat Singh	eb6e385dc5	community: Add PolygonAPIWrapper and get_last_quote endpoint (#15971) ... - **Description:** Added a `PolygonAPIWrapper` and an initial `get_last_quote` endpoint, which allows us to get the last price quote for a given `ticker`. Once merged, I can add a Polygon tool in `tools/` for agents to use. - **Twitter handle:** [@virattt](https://twitter.com/virattt) The Polygon.io Stocks API provides REST endpoints that let you query the latest market data from all US stock exchanges.	8 months ago
Jonathan Algar	a74f3a4979	Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) ... **Description:** Batch update of alt text and title attributes for images in `md` & `mdx` files across the repo using [alttexter](https://github.com/jonathanalgar/alttexter)/[alttexter-ghclient](https://github.com/jonathanalgar/alttexter-ghclient) (built using LangChain/LangSmith). **Limitation:** cannot update `ipynb` files because of [this issue](https://github.com/langchain-ai/langchain/pull/15357#issuecomment-1885037250). Can revisit when Docusaurus is bumped to v3. I checked all the generated alt texts and titles and didn't find any technical inaccuracies. That's not to say they're _perfect_, but a lot better than what's there currently. [Deployed](https://langchain-819yf1tbk-langchain.vercel.app/docs/modules/model_io/) image example:  You can see LangSmith traces for all the calls out to the LLM in the PRs merged into this one: * https://github.com/jonathanalgar/langchain/pull/6 * https://github.com/jonathanalgar/langchain/pull/4 * https://github.com/jonathanalgar/langchain/pull/3 I didn't add the following files to the PR as the images already have OK alt texts: * 27dca2d92f/docs/docs/integrations/providers/argilla.mdx (L3) * 27dca2d92f/docs/docs/integrations/providers/apify.mdx (L11) --------- Co-authored-by: github-actions <github-actions@github.com>	8 months ago
Varik Matevosyan	efe6cfafe2	community: Added Lantern as VectorStore (#12951) ... Support [Lantern](https://github.com/lanterndata/lantern) as a new VectorStore type. - Added Lantern as VectorStore. It will support 3 distance functions `l2 squared`, `cosine` and `hamming` and will use `HNSW` index. - Added tests - Added example notebook	8 months ago
Christophe Bornet	bc60203d0f	Add documentation for AstraDBStore (#15953) ... Preview: https://langchain-git-fork-cbornet-astradb-store-doc-langchain.vercel.app/docs/integrations/stores/astradb	8 months ago
Bagatur	c697c89ca4	docs: add agent prompt creation examples (#15957)	8 months ago
Rihards Gravis	6a48ea43ec	docs: Update Robocorp Action Server installation instructions (#15943) ... **Description:** Remove section on how to install Action Server and direct the users t o the instructions on Robocorp repository. **Reason:** Robocorp Action Server has moved from a pip installation to a standalone cli application and is due for changes. Because of that, leaving only LangChain integration relevant part in the documentation.	8 months ago
Raunak	e26e1f8b37	community: Added functions to make async calls to HuggingFaceHub's embedding endpoint in HuggingFaceHubEmbeddings class (#15737) ... **Description:** Added aembed_documents() and aembed_query() async functions in HuggingFaceHubEmbeddings class in langchain_community\embeddings\huggingface_hub.py file. It will support to make async calls to HuggingFaceHub's embedding endpoint and generate embeddings asynchronously. Test Cases: Added test_huggingfacehub_embedding_async_documents() and test_huggingfacehub_embedding_async_query() functions in test_huggingface_hub.py file to test the two async functions created in HuggingFaceHubEmbeddings class. Documentation: Updated huggingfacehub.ipynb with steps to install huggingface_hub package and use HuggingFaceHubEmbeddings. **Dependencies:** None, **Twitter handle:** I do not have a Twitter account --------- Co-authored-by: H161961 <Raunak.Raunak@Honeywell.com>	8 months ago
Mu Xian Ming	560bb49c99	docs: redis_chat_message_history.ipynb integration doc (#15789) ... - **Description:** Updated the docs for the memory integration module redis_chat_message_history.ipynb - **Issue:** #15664 - **Dependencies:** N/A Co-authored-by: Mu Xianming <mu.xianming@lmwn.com>	8 months ago
Xin Liu	5efec068c9	feat: Implement `stream` interface (#15875) ... <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes if applicable, - **Dependencies:** any dependencies required for this change, - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ 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. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> Major changes: - Rename `wasm_chat.py` to `llama_edge.py` - Rename the `WasmChatService` class to `ChatService` - Implement the `stream` interface for `ChatService` - Add `test_chat_wasm_service_streaming` in the integration test - Update `llama_edge.ipynb` --------- Signed-off-by: Xin Liu <sam@secondstate.io>	8 months ago