2537 Commits (177af65dc4d0033330bd528eb7dd65d62b0d7dc3)

Author	SHA1	Message	Date
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"]}) ```	6 months ago
SN	f175bf7d7b	Use env for revision id if not passed in as param; use `git describe` as backup (#16227) ... Co-authored-by: William Fu-Hinthorn <13333726+hinthornw@users.noreply.github.com>	6 months ago
Erick Friis	b9495da92d	langchain[patch]: fix stuff documents chain api docs render (#16159)	6 months ago
Erick Friis	0e76d84137	google-vertexai[patch]: more integration test fixes (#16234)	6 months ago
Erick Friis	aa35b43bcd	docs, google-vertex[patch]: function docs (#16231)	6 months ago
Harrison Chase	f60f59d69f	google-vertexai[patch]: Harrison/vertex function calling (#16223) ... Co-authored-by: Erick Friis <erick@langchain.dev>	6 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>	6 months ago
Erick Friis	65b231d40b	mistralai[patch]: async integration tests (#16214)	6 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>	6 months ago
Eugene Yurtsev	ecd4f0a7ec	core[patch]: testing add chat model for unit-tests (#16209) ... This PR adds a fake chat model for testing purposes. Used in this PR: https://github.com/langchain-ai/langchain/pull/16172	6 months ago
SN	7d444724d7	Add revision identifier to run_on_dataset (#16167) ... Allow specifying revision identifier for better project versioning	6 months ago
Eugene Yurtsev	5d8c147332	docs: Document and test PydanticOutputFunctionsParser (#15759) ... This PR adds documentation and testing to `PydanticOutputFunctionsParser(OutputFunctionsParser)`.	6 months ago
Christophe Bornet	3502a407d9	infra: Use dotenv in langchain-community's integration tests (#16137) ... * Removed some env vars not used in langchain package IT * Added Astra DB env vars in langchain package, used for cache tests * Added conftest.py to load env vars in langchain_community IT * Added .env.example in langchain_community IT	6 months ago
Nuno Campos	ca014d5b04	Update readme (#16160) ... <!-- 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. -->	6 months ago
Tomaz Bratanic	1e80113ac9	community[patch]: Add neo4j timeout and value sanitization option (#16138) ... The timeout function comes in handy when you want to kill longrunning queries. The value sanitization removes all lists that are larger than 128 elements. The idea here is to remove embedding properties from results.	6 months ago
Krishna Shedbalkar	f238217cea	community[patch]: Basic Logging and Human input to ShellTool (#15932) ... - **Description:** As Shell tool is very versatile, while integrating it into applications as openai functions, developers have no clue about what command is being executed using the ShellTool. All one can see is:  Summarising my feature request: 1. There's no visibility about what command was executed. 2. There's no mechanism to prevent a command to be executed using ShellTool, like a y/n human input which can be accepted from user to proceed with executing the command., - **Issue:** the issue #15931 it fixes if applicable, - **Dependencies:** There isn't any dependancy, - **Twitter handle:** @krishnashed	6 months ago
Bagatur	679a3ae933	openai[patch]: clarify azure error (#16157)	6 months ago
Bagatur	7ad9eba8f4	core[patch]: Release 0.1.12 (#16161)	6 months ago
Leonid Kuligin	58f0ba306b	changed default params for gemini (#16044) ... Replace this entire comment with: - **Description:** changed default values for Vertex LLMs (to be handled on the SDK's side)	6 months ago
Bagatur	5c73fd5bba	core[patch]: support old core namespaces (#16155)	6 months ago
Christophe Bornet	fb940d11df	community[patch]: Use newer MetadataVectorCassandraTable in Cassandra vector store (#15987) ... as VectorTable is deprecated Tested manually with `test_cassandra.py` vector store integration test.	6 months ago
Mohammad Mohtashim	1fa056c324	community[patch]: Don't set search path for unknown SQL dialects (#16047) ... - **Description:** Made a small fix for the `SQLDatabase` highlighted in an issue. The issue pertains to switching schema for different SQL engines. - **Issue:** #16023 @baskaryan	6 months ago
Erick Friis	11327e6b64	google-vertexai[patch]: typing, release 0.0.2 (#16153)	6 months ago
Leonid Ganeline	2709d3e5f2	langchain[patch]: updated imports for `langchain.callbacks` (#16060) ... Updated imports from 'langchain` to `core` where it is possible --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Leonid Ganeline	c5f6b828ad	langchain[patch], community[minor]: move `output_parsers.ernie_functions` (#16057) ... `output_parsers.ernie_functions` moved into `community`	6 months ago
Leonid Ganeline	49aff3ea5b	langchain[patch]: updated `agents` imports (#16061) ... Updated imports into `langchain` to `core` where it is possible --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Leonid Ganeline	60b1bd02d7	langchain[patch]: updated imports for `output_parsers` (#16059) ... Updated imports from `langchain` to `core` where it is possible	6 months ago
Leonid Ganeline	9e9ad9b0e9	langchain[patch]: updated `retrievers` imports (#16062) ... Updated imports into `langchain` to `core` where it is possible --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Leonid Ganeline	d350be959d	langchain[patch]: updated `chains` imports (#16064) ... Updated imports into `langchain` to `core` where it is possible --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Fei Wang	d0e101e4e0	community[patch]: fix ollama astream (#16070) ... Update ollama.py	6 months ago
ChengZi	8597484195	langchain[patch]: support more comparators in Milvus self-querying retriever (#16076) ... - **Description:** Support IN and LIKE comparators in Milvus self-querying retriever, based on [Boolean Expression Rules](https://milvus.io/docs/boolean.md) - **Issue:** No - **Dependencies:** No - **Twitter handle:** No Signed-off-by: ChengZi <chen.zhang@zilliz.com>	6 months ago
Kapil Sachdeva	f406dc3872	docs: in RunnableRetry, correct the example snippet that uses with_retry method on Runnable (#16108) ... The example code snippet for with_retry is using incorrect argument names. This PR fixes that	6 months ago
BeatrixCohere	b0c3e3db2b	community[patch]: Handle when documents are not provided in the Cohere response (#16144) ... - **Description:** This handles the cohere response when documents aren't included in the response - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** N/A	6 months ago
Felix Krones	d91126fc64	community[patch]: missing unpack operator for or_clause in pgvector document filter (#16148) ... - Fix for #16146 - Adding unpack operation to "or" and "and" filter for pgvector retriever. #	6 months ago
Erick Friis	06fe2f4fb0	partners: add license field (#16117) ... - bumps package post versions for packages without current unreleased updates - will bump package version in release prs associated with packages that do have changes (mistral, vertex)	6 months ago
Erick Friis	ce10fe0c2f	mistralai[patch]: release 0.0.3 (#16116) ... embeddings	6 months ago
William FH	e5cf1e2414	Community[patch]use secret str in Tavily and HuggingFaceInferenceEmbeddings (#16109) ... So the api keys don't show up in repr's Still need to do tests	6 months ago
William FH	f3601b0aaf	Community[Patch] Remove docs form bm25 repr (#16110) ... Resolves: https://github.com/langchain-ai/langsmith-sdk/issues/356	6 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>	6 months ago
Leonid Kuligin	4df14a61fc	google-vertexai[minor]: add function calling on VertexAI (#15822) ... Replace this entire comment with: - **Description:** Description: added support for tools on VertexAI - **Issue:** #15073 - **Twitter handle:** lkuligin --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Bagatur	8840a8cc95	docs: tool-use use case (#15783) ... Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	6 months ago
Bagatur	3d34347a85	langchain[patch]: bump core dep to 0.1.9 (#16104)	6 months ago
Bagatur	62a2e9ee19	langchain[patch]: Release 0.1.1 (#16103)	6 months ago
Bagatur	076593382a	core[patch]: Release 0.1.11 (#16100)	6 months ago
Bagatur	c5656a4905	core[patch]: pass exceptions to fallbacks (#16048)	6 months ago
Nuno Campos	770f57196e	Add unit test for overridden lc_namespace (#16093)	6 months ago
Erick Friis	52114bdfac	community[patch]: release 0.0.13 (#16087)	6 months ago
James Briggs	ca288d8f2c	community[patch]: add vector param to index query for pinecone vec store (#16054)	6 months ago
Antonio Morales	476fb328ee	community[patch]: implement adelete from VectorStore in Qdrant (#16005) ... **Description:** Implement `adelete` function from `VectorStore` in `Qdrant` to support other asynchronous flows such as async indexing (`aindex`) which requires `adelete` to be implemented. Since `Qdrant` can be passed an async qdrant client, this can be supported easily. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Bagatur	697a6f2c80	langchain[patch]: fix requests lint (#16049)	6 months ago