langchain

Commit Graph

Author	SHA1	Message	Date
killind-dev	f8a54d1d73	chroma: Add chroma partner package (#19292 ) Description: Adds chroma to the partners package. Tests & code mirror those in the community package. Dependencies: None Twitter handle: @akiradev0x --------- Co-authored-by: Erick Friis <erick@langchain.dev>	5 months ago
Yuki Watanabe	eef19954f3	core[patch]: fix duplicated kwargs in `_load_sql_databse_chain` (#19908 ) `kwargs` is specified twice in [this line](`3218463f6a/libs/langchain/langchain/chains/loading.py (L386)`), causing runtime error when passing any keyword arguments.	5 months ago
ccurme	39471a9c87	docs: update tool calling cookbook (#20290 ) Co-authored-by: Erick Friis <erick@langchain.dev>	5 months ago
Nuno Campos	15271ac832	core: mustache prompt templates (#19980 ) Co-authored-by: Erick Friis <erick@langchain.dev>	5 months ago
Leonid Ganeline	4cb5f4c353	community[patch]: import flattening fix (#20110 ) This PR should make it easier for linters to do type checking and for IDEs to jump to definition of code. See #20050 as a template for this PR. - As a byproduct: Added 3 missed `test_imports`. - Added missed `SolarChat` in to __init___.py Added it into test_import ut. - Added `# type: ignore` to fix linting. It is not clear, why linting errors appear after ^ changes. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	5 months ago
Yuki Oshima	12190ad728	openai[patch]: Fix langchain-openai unknown parameter error with gpt-4-turbo (#20271 ) Description: I fixed langchain-openai unknown parameter error with gpt-4-turbo. It seems that the behavior of the Chat Completions API implicitly changed when using the latest gpt-4-turbo model, differing from previous models. It now appears to reject parameters that are not listed in the [API Reference](https://platform.openai.com/docs/api-reference/chat/create). So I found some errors and fixed them. Issue: https://github.com/langchain-ai/langchain/issues/20264 Dependencies: none Twitter handle: https://twitter.com/oshima_123	5 months ago
ccurme	21c1ce0bc1	update agents to use tool call messages (#20074 ) ```python from langchain.agents import AgentExecutor, create_tool_calling_agent, tool from langchain_anthropic import ChatAnthropic from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder prompt = ChatPromptTemplate.from_messages( [ ("system", "You are a helpful assistant"), MessagesPlaceholder("chat_history", optional=True), ("human", "{input}"), MessagesPlaceholder("agent_scratchpad"), ] ) model = ChatAnthropic(model="claude-3-opus-20240229") @tool def magic_function(input: int) -> int: """Applies a magic function to an input.""" return input + 2 tools = [magic_function] agent = create_tool_calling_agent(model, tools, prompt) agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True) agent_executor.invoke({"input": "what is the value of magic_function(3)?"}) ``` ``` > Entering new AgentExecutor chain... Invoking: `magic_function` with `{'input': 3}` responded: [{'text': '<thinking>\nThe user has asked for the value of magic_function applied to the input 3. Looking at the available tools, magic_function is the relevant one to use here, as it takes an integer input and returns an integer output.\n\nThe magic_function has one required parameter:\n- input (integer)\n\nThe user has directly provided the value 3 for the input parameter. Since the required parameter is present, we can proceed with calling the function.\n</thinking>', 'type': 'text'}, {'id': 'toolu_01HsTheJPA5mcipuFDBbJ1CW', 'input': {'input': 3}, 'name': 'magic_function', 'type': 'tool_use'}] 5 Therefore, the value of magic_function(3) is 5. > Finished chain. {'input': 'what is the value of magic_function(3)?', 'output': 'Therefore, the value of magic_function(3) is 5.'} ``` --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	5 months ago
Erick Friis	9eb6f538f0	infra, multiple: rc release versions (#20252 )	5 months ago
Bagatur	0d0458d1a7	mistralai[patch]: Pre-release 0.1.2-rc.1 (#20251 )	5 months ago
Bagatur	e4046939d0	anthropic[patch]: Pre-release 0.1.8-rc.1 (#20250 )	5 months ago
Bagatur	a8eb0f5b1b	openai[patch]: pre-release 0.1.3-rc.1 (#20249 )	5 months ago
Bagatur	a43b9e4f33	core[patch]: Pre-release 0.1.42-rc.1 (#20248 )	5 months ago
Bagatur	9514bc4d67	core[minor], ...: add tool calls message (#18947 ) core[minor], langchain[patch], openai[minor], anthropic[minor], fireworks[minor], groq[minor], mistralai[minor] ```python class ToolCall(TypedDict): name: str args: Dict[str, Any] id: Optional[str] class InvalidToolCall(TypedDict): name: Optional[str] args: Optional[str] id: Optional[str] error: Optional[str] class ToolCallChunk(TypedDict): name: Optional[str] args: Optional[str] id: Optional[str] index: Optional[int] class AIMessage(BaseMessage): ... tool_calls: List[ToolCall] = [] invalid_tool_calls: List[InvalidToolCall] = [] ... class AIMessageChunk(AIMessage, BaseMessageChunk): ... tool_call_chunks: Optional[List[ToolCallChunk]] = None ... ``` Important considerations: - Parsing logic occurs within different providers; - ~Changing output type is a breaking change for anyone doing explicit type checking;~ - ~Langsmith rendering will need to be updated: https://github.com/langchain-ai/langchainplus/pull/3561~ - ~Langserve will need to be updated~ - Adding chunks: - ~AIMessage + ToolCallsMessage = ToolCallsMessage if either has non-null .tool_calls.~ - Tool call chunks are appended, merging when having equal values of `index`. - additional_kwargs accumulate the normal way. - During streaming: - ~Messages can change types (e.g., from AIMessageChunk to AIToolCallsMessageChunk)~ - Output parsers parse additional_kwargs (during .invoke they read off tool calls). Packages outside of `partners/`: - https://github.com/langchain-ai/langchain-cohere/pull/7 - https://github.com/langchain-ai/langchain-google/pull/123/files --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	5 months ago
Erick Friis	00552918ac	groq: xfail tool_choice tests (#20247 )	5 months ago
Bagatur	2d83505be9	experimental[patch]: Release 0.0.57 (#20243 )	5 months ago
Bagatur	f06cb59ab9	groq[patch]: Release 0.1.1 (#20242 )	5 months ago
Erick Friis	ad3f1a9e85	docs: fix external repo partner docs (#20238 )	5 months ago
Bagatur	0b2f0307d7	openai[patch]: Release 0.1.2 (#20241 )	5 months ago
Bagatur	4b84c9b28c	anthropic[patch]: Release 0.1.7 (#20240 )	5 months ago
Bagatur	74d04a4e80	mistralai[patch]: Release 0.1.1 (#20239 )	5 months ago
Bagatur	e5913c8758	langchain[patch]: Release 0.1.15 (#20237 )	5 months ago
Bagatur	e39fdfddf1	community[patch]: Release 0.0.32 (#20236 )	5 months ago
Bagatur	a07238d14e	core[patch]: Release 0.1.41 (#20233 )	5 months ago
Chip Davis	806d4ae48f	community[patch]: fixed multithreading returning List[List[Documents]] instead of List[Documents] (#20230 ) Description: When multithreading is set to True and using the DirectoryLoader, there was a bug that caused the return type to be a double nested list. This resulted in other places upstream not being able to utilize the from_documents method as it was no longer a `List[Documents]` it was a `List[List[Documents]]`. The change made was to just loop through the `future.result()` and yield every item. Issue: #20093 Dependencies: N/A Twitter handle: N/A	5 months ago
Sholto Armstrong	230376f183	docs: Fix typo in citations example (#20218 ) Small typo in the citations notebook "ojbects" changed to "objects"	5 months ago
Eugene Yurtsev	fe35e13083	langchain[patch]: Update unit test (#20228 ) This unit test fails likely validation by the openai client. Newer openai library seems to be doing more validation so the existing test fails since http_client needs to be of httpx instance	5 months ago
Casper da Costa-Luis	b972f394c8	langchain[patch]: make BooleanOutputParser check words not substrings (#20064 ) - Description: fixes BooleanOutputParser detecting sub-words ("NOW this is likely (YES)" -> `True`, not `AmbiguousError`) - Issue(s): fixes #11408 (follow-up to #17810) - Dependencies: None - GitHub handle: @casperdcl <!-- if unreviewd after a few days, @-mention one of baskaryan, efriis, eyurtsev, hwchase17 --> - [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. - [ ] 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: Eugene Yurtsev <eyurtsev@gmail.com>	5 months ago
seray	add31f46d0	community[patch]: OpenLLM Async Client Fixes and Timeout Parameter (#20007 ) Same changes as this merged [PR](https://github.com/langchain-ai/langchain/pull/17478) (https://github.com/langchain-ai/langchain/pull/17478), but for the async client, as the same issues persist. - Replaced 'responses' attribute of OpenLLM's GenerationOutput schema to 'outputs'. reference: `66de54eae7/openllm-core/src/openllm_core/_schemas.py (L135)` - Added timeout parameter for the async client. --------- Co-authored-by: Seray Arslan <seray.arslan@knime.com>	5 months ago
Erick Friis	37a9e23c05	community: switch to falkordb python client (#20229 )	5 months ago
Christophe Bornet	f43b48aebc	core[minor]: Implement aformat_messages for _StringImageMessagePromptTemplate (#20036 )	5 months ago
Christophe Bornet	19001e6cb9	core[minor]: Implement aformat for FewShotPromptWithTemplates (#20039 )	5 months ago
Erick Friis	855ba46f80	standard-tests: a standard unit and integration test set (#20182 ) just chat models for now	5 months ago
Erick Friis	9b5cae045c	together: release 0.1.0 (#20225 ) Resolved #20217	5 months ago
Eugene Yurtsev	7cfb643a1c	langchain-postgres: Remove remaining README.md file (#20221 ) Repository has moved to langchain-ai/langchain-postgres	5 months ago
Eugene Yurtsev	2fa7266ebb	Remove postgres package (#20207 ) Package moved	5 months ago
Simon Kelly	a682f0d12b	openai[patch]: wrap stream code in context manager blocks (#18013 ) Description: Use the `Stream` context managers in `ChatOpenAi` `stream` and `astream` method. Using the context manager returned by the OpenAI client makes it possible to terminate the stream early since the response connection will be closed when the context manager exists. Issue: #5340 Twitter handle: @snopoke --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	5 months ago
Shotaro Sano	6c11c8dac6	docs: Add documentation of `ElasticsearchStore.BM25RetrievalStrategy` (#20098 ) This pull request follows up on https://github.com/langchain-ai/langchain/pull/19314 and https://github.com/langchain-ai/langchain-elastic/pull/6, adding documentation for the `ElasticsearchStore.BM25RetrievalStrategy`. Like other retrieval strategies, we are now introducing BM25RetrievalStrategy. ### Background - The `BM25RetrievalStrategy` has been introduced to `langchain-elastic` via the pull request https://github.com/langchain-ai/langchain-elastic/pull/6. - This PR was initially created in the main `langchain` repository but was moved to `langchain-elastic` during the review process due to the migration of the partner package. - The original PR can be found at https://github.com/langchain-ai/langchain/pull/19314. - As [commented](https://github.com/langchain-ai/langchain/pull/19314#issuecomment-2023202401) by @joemcelroy, documenting the new retrieval strategy is part of the requirements for its introduction. Although the `BM25RetrievalStrategy` has been merged into `langchain-elastic`, its documentation is still to be maintained in the main `langchain` repository. Therefore, this pull request adds the documentation portion of `BM25RetrievalStrategy`. The content of the documentation remains the same as that included in the original PR, https://github.com/langchain-ai/langchain/pull/19314. --------- Co-authored-by: Max Jakob <max.jakob@elastic.co>	5 months ago
David Lee	0394c6e126	community[minor]: add allow_dangerous_requests for OpenAPI toolkits (#19493 ) OpenAPI allow_dangerous_requests: community: add allow_dangerous_requests for OpenAPI toolkits Description: a description of the change Due to BaseRequestsTool changes, we need to pass allow_dangerous_requests manually. `b617085af0/libs/community/langchain_community/tools/requests/tool.py (L26-L46)` While OpenAPI toolkits didn't pass it in the arguments. `b617085af0/libs/community/langchain_community/agent_toolkits/openapi/planner.py (L262-L269)` Issue: the issue # it fixes, if applicable https://github.com/langchain-ai/langchain/issues/19440 If not passing allow_dangerous_requests, it won't be able to do requests. Dependencies: any dependencies required for this change Not much --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	5 months ago
Guangdong Liu	301dc3dfd2	docs: Get rid of ZeroShotAgent and use create_react_agent instead (#20157 ) - Issue: #20122 - @baskaryan, @eyurtsev.	5 months ago
Timothy	0c848a25ad	community[patch]: GCSDirectoryLoader bugfix (#20005 ) - Description: Bug fix. Removed extra line in `GCSDirectoryLoader` to allow catching Exceptions. Now also logs the file path if Exception is raised for easier debugging. - Issue: #20198 Bug since langchain-community==0.0.31 - Dependencies: No change - Twitter handle: timothywong731 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	5 months ago
jeff kit	ac42e96e4c	community[patch], langchain[minor]: Enhance Tencent Cloud VectorDB, langchain: make Tencent Cloud VectorDB self query retrieve compatible (#19651 ) - make Tencent Cloud VectorDB support metadata filtering. - implement delete function for Tencent Cloud VectorDB. - support both Langchain Embedding model and Tencent Cloud VDB embedding model. - Tencent Cloud VectorDB support filter search keyword, compatible with langchain filtering syntax. - add Tencent Cloud VectorDB TranslationVisitor, now work with self query retriever. - more documentations. --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	5 months ago
Bagatur	1a34c65e01	community[patch]: pass through sql agent kwargs (#19962 ) Fix #19961	5 months ago
Haris Ali	1b480914b4	docs: Fix the class links in openai_tools and openai_functions description in output parser documentations (#20197 ) - Description: In this PR I fixed the links which points to the API docs for classes in OpenAI functions and OpenAI tools section of output parsers. - Issue: It fixed the issue #19969 Co-authored-by: Haris Ali <haris.ali@formulatrix.com>	5 months ago
Guangdong Liu	97d91ec17c	community[patch]: standardize baichuan init args (#20209 ) Related to https://github.com/langchain-ai/langchain/issues/20085 @baskaryan	5 months ago
Piyush Jain	cd7abc495a	community[minor]: add neptune analytics graph (#20047 ) Replacement for PR [#19772](https://github.com/langchain-ai/langchain/pull/19772). --------- Co-authored-by: Dave Bechberger <dbechbe@amazon.com> Co-authored-by: bechbd <bechbd@users.noreply.github.com>	5 months ago
Shuqian	ad9750403b	community[minor]: add bedrock anthropic callback for token usage counting (#19864 ) Description: add bedrock anthropic callback for token usage counting, consulted openai callback. --------- Co-authored-by: Massimiliano Pronesti <massimiliano.pronesti@gmail.com>	5 months ago
Prince Canuma	1f9f4d8742	community[minor]: Add support for MLX models (chat & llm) (#18152 ) Description: This PR adds support for MLX models both chat (i.e., instruct) and llm (i.e., pretrained) types/ Dependencies: mlx, mlx_lm, transformers Twitter handle: @Prince_Canuma --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	5 months ago
aditya thomas	6baeaf4802	docs: TogetherAI as a drop-in replacement for OpenAI (#19900 ) Description: TogetherAI as a drop-in replacement for OpenAI Issue: None Dependencies: None @baskaryan apropos #20032	5 months ago
Leonid Ganeline	2f8dd1a161	community[patch]: `cross_encoders` flatten namespaces (#20183 ) Issue `langchain_community.cross_encoders` didn't have flattening namespace code in the __init__.py file. Changes: - added code to flattening namespaces (used #20050 as a template) - added ut for a change - added missed `test_imports` for `chat_loaders` and `chat_message_histories` modules	5 months ago
Bagatur	1af7133828	docs: add vertexai to structured output (#20171 )	5 months ago

1 2 3 4 5 ...

8664 Commits (f8a54d1d731a816897d3b4b0a0f814a099231580) All Branches Search

8664 Commits (f8a54d1d731a816897d3b4b0a0f814a099231580)

All Branches