langchain

Commit Graph

Author	SHA1	Message	Date
Bagatur	84bf5787a7	core[patch], openai[patch]: Chat openai stream logprobs (#16218 )	6 months ago
Bagatur	6f7a414955	docs: fix links (#16284 )	6 months ago
Eugene Yurtsev	cc2e30fa13	CI: update the description used for privileged issue template (#16277 ) Update description	6 months ago
Eugene Yurtsev	3b649f4331	CI: Add privileged version for issue creation (#16276 ) Add privileged version for issue creation. This adds a version of issue creation which is unstructured by design to make it easier for maintainers to create issues. Maintainers are expected to write / describe issues clearly.	6 months ago
Eugene Yurtsev	c0d453d8ac	CI: Disable blank issues, add links to QA discussions & show and tell (#16275 ) Update the issue template	6 months ago
Carey	021b0484a8	community[patch]: add skipped test for inner product normalization (#14989 ) --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Lance Martin	f63906a9c2	Test and update MultiON agent toolkit docs (#16235 )	6 months ago
Christophe Bornet	3ccbe11363	community[minor]: Add Cassandra document loader (#16215 ) - Description: document loader for Apache Cassandra - Twitter handle: cbornet_	6 months ago
Tomaz Bratanic	fc84083ce5	docs: Add neo4j semantic blog post link to templates (#16225 )	6 months ago
mikeFore4	9d32af72ce	community[patch]: huggingface hub character removal bug fix (#16233 ) - Description: Some text-generation models on huggingface repeat the prompt in their generated response, but not all do! The tests use "gpt2" which DOES repeat the prompt and as such, the HuggingFaceHub class is hardcoded to remove the first few characters of the response (to match the len(prompt)). However, if you are using a model (such as the very popular "meta-llama/Llama-2-7b-chat-hf") that DOES NOT repeat the prompt in it's generated text, then the beginning of the generated text will be cut off. This code change fixes that bug by first checking whether the prompt is repeated in the generated response and removing it conditionally. - Issue: #16232 - Dependencies: N/A - Twitter handle: N/A	6 months ago
Andreas Motl	3613d8a2ad	community[patch]: Use SQLAlchemy's `bulk_save_objects` method to improve insert performance (#16244 ) - Description: Improve [pgvector vector store adapter](https://github.com/langchain-ai/langchain/blob/v0.1.1/libs/community/langchain_community/vectorstores/pgvector.py) to save embeddings in batches, to improve its performance. - Issue: NA - Dependencies: NA - References: https://github.com/crate-workbench/langchain/pull/1 Hi again from the CrateDB team, following up on GH-16243, this is another minor patch to the pgvector vector store adapter. Inserting embeddings in batches, using [SQLAlchemy's `bulk_save_objects`](https://docs.sqlalchemy.org/en/20/orm/session_api.html#sqlalchemy.orm.Session.bulk_save_objects) method, can deliver substantial performance gains. With kind regards, Andreas. NB: As I am seeing just now that this method is a legacy feature of SA 2.0, it will need to be reworked on a future iteration. However, it is not deprecated yet, and I haven't been able to come up with a different implementation, yet.	6 months ago
Ashley Xu	0f99646ca6	docs: add the enrollment form for`BigQueryVectorSearch` (#16240 ) This PR adds the enrollment form for BigQueryVectorSearch.	6 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"]}) ```	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	e5878c467a	infra: scheduled testing env (#16239 )	6 months ago
Erick Friis	2f348c695a	infra: add nvidia api secret to integration testing (#15972 )	6 months ago
Erick Friis	50959abf0c	infra: google cse id integration test (#16238 )	6 months ago
Erick Friis	b9495da92d	langchain[patch]: fix stuff documents chain api docs render (#16159 )	6 months ago
Erick Friis	eec3347939	docs: together cookbook import (#16236 )	6 months ago
Erick Friis	92bc80483a	infra: google search api key (#16237 )	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
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. -->	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
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>	6 months ago
Bagatur	aa2e642ce3	docs: tool use nits (#16211 )	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
Bagatur	27ad65cc68	docs: add tool use diagrams (#16207 )	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
Bagatur	27ed2673da	docs: model io order (#16163 )	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: ![image](https://github.com/langchain-ai/langchain/assets/60742358/540e274a-debc-4564-9027-046b91424df3) 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	2af813c7eb	docs: bump sphinx>=5 (#16162 )	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
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>	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
Bagatur	e7ddec1f2c	docs: change parallel doc name (#16152 )	6 months ago

1 2 3 4 5 ...

6995 Commits (84bf5787a7036a33745e44de44aa89a074dcec55) All Branches Search

6995 Commits (84bf5787a7036a33745e44de44aa89a074dcec55)

All Branches