langchain

Commit Graph

Author	SHA1	Message	Date
Eugene Yurtsev	74e705250f	core[patch]: update some root_validators (#22787 ) Update some of the @root_validators to be explicit pre=True or pre=False, skip_on_failure=True for pydantic 2 compatibility.	3 months ago
William FH	dcec133b85	[Core] Update Tracing Interops (#22318 ) LangSmith and LangChain context var handling evolved in parallel since originally we didn't expect people to want to interweave the decorator and langchain code. Once we get a new langsmith release, this PR will let you seemlessly hand off between @traceable context and runnable config context so you can arbitrarily nest code. It's expected that this fails right now until we get another release of the SDK	4 months ago
Eugene Yurtsev	6ed0aa3239	core[major]: only use function description (#21622 ) Do not prefix function signature --- * Reason for this is that information is already present with tool calling models. * This will save on tokens for those models, and makes it more obvious what the description is! * The @tool can get more parameters to allow a user to re-introduce the the signature if we want	4 months ago
William FH	5c63ac3dd7	[Patch] Dedent docstring (#20959 ) Technically a slight prompt breaking change, but I think positive EV in that it saves tokens and results in more sane / in-distribution prompts	5 months ago
ccurme	b8db73233c	core, community: deprecate tool.__call__ (#20900 ) Does not update docs.	5 months ago
William FH	a936f696a6	[Core] Feat: update config CVar in tool.invoke (#20808 )	5 months ago
Eugene Yurtsev	38adbfdf34	community[patch],core[minor]: Move BaseToolKit to core.tools (#20669 )	5 months ago
ccurme	c010ec8b71	patch: deprecate (a)get_relevant_documents (#20477 ) - `.get_relevant_documents(query)` -> `.invoke(query)` - `.get_relevant_documents(query=query)` -> `.invoke(query)` - `.get_relevant_documents(query, callbacks=callbacks)` -> `.invoke(query, config={"callbacks": callbacks})` - `.get_relevant_documents(query, kwargs)` -> `.invoke(query, kwargs)` --------- Co-authored-by: Erick Friis <erick@langchain.dev>	5 months ago
Leonid Ganeline	45d045b2c5	core[minor], langchain[patch]: `tools` dependencies refactoring (#18759 ) The `langchain.tools` [namespace](https://api.python.langchain.com/en/latest/langchain_api_reference.html#module-langchain.tools) can be completely eliminated by moving one class and 3 functions into `core`. It makes sense since the class and functions are very core.	5 months ago
Kahlil Wehmeyer	9c08cdea92	core[patch]: ToolException docs/exception message (#17590 ) Description: This PR adds a slightly more helpful message to a Tool Exception ``` # current state langchain_core.tools.ToolException: Too many arguments to single-input tool # proposed state langchain_core.tools.ToolException: Too many arguments to single-input tool. Consider using a StructuredTool instead. ``` Issue: Somewhat discussed here 👉 #6197 Dependencies: None Twitter handle: N/A --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	6 months ago
William FH	780337488e	[Enhancement] Add support for directly providing a run_id (#18990 ) The root run id (~trace id's) is useful for assigning feedback, but the current recommended approach is to use callbacks to retrieve it, which has some drawbacks: 1. Doesn't work for streaming until after the first event 2. Doesn't let you call other endpoints with the same trace ID in parallel (since you have to wait until the call is completed/started to use This PR lets you provide = "run_id" in the runnable config. Couple considerations: 1. For batch calls, we split the trace up into separate trees (to permit better rendering). We keep the provided run ID for the first one and generate a unique one for other elements of the batch. 2. For nested calls, the provided ID is ONLY used on the top root/trace. ### Example Usage ``` chain.invoke("foo", {"run_id": uuid.uuid4()}) ```	6 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>	6 months ago
Eugene Yurtsev	8c71f92cb2	core: upgrade mypy to recent mypy (#18753 ) Testing this works per package on CI	7 months ago
Leonid Ganeline	2f2b77602e	docs: modules descriptions (#17844 ) Several `core` modules do not have descriptions, like the [agent](https://api.python.langchain.com/en/latest/core_api_reference.html#module-langchain_core.agents) module. - Added missed module descriptions. The descriptions are mostly copied from the `langchain` or `community` package modules.	7 months ago
Leonid Ganeline	ae66bcbc10	core[patch]: docstring update (#16813 ) - added missed docstrings - formated docstrings to consistent form	8 months ago
Erick Friis	06660bc78c	core[patch]: handle some optional cases in tools (#16954 ) primary problem in pydantic still exists, where `Optional[str]` gets turned to `string` in the jsonschema `.schema()` Also fixes the `SchemaSchema` naming issue --------- Co-authored-by: William Fu-Hinthorn <13333726+hinthornw@users.noreply.github.com>	8 months ago
hmasdev	cc17334473	core[minor]: add validation error handler to `BaseTool` (#14007 ) - Description: add a ValidationError handler as a field of [`BaseTool`](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/tools.py#L101) and add unit tests for the code change. - Issue: #12721 #13662 - Dependencies: None - Tag maintainer: - Twitter handle: @hmdev3 - NOTE: - I'm wondering if the update of document is required. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	8 months ago
arnob-sengupta	f9976b9630	core[patch]: consolidate conditional in BaseTool (#16530 ) - Description: Refactor contradictory conditional to single line - Issue: #16528	8 months ago
William FH	5de59f9236	Core[Patch] Parse tool input after on_start (#16430 ) For tracing, if a validation error occurs, currently it is attributed to the previous step of the chain. It would be nice to have the on_start and on_error callbacks called for tools when there is a validation error that occurs to more easily attribute the root-cause	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
Harrison Chase	1afac77439	stop making copies of inputs (#15926 )	8 months ago
Nuno Campos	eb5e250188	Propagate context vars in all classes/methods - Any direct usage of ThreadPoolExecutor or asyncio.run_in_executor needs manual handling of context vars	9 months ago
Bagatur	e327bb4ba4	IMPROVEMENT: Conditionally import core type hints (#13700 )	10 months ago
Bagatur	d32e511826	REFACTOR: Refactor langchain_core (#13627 ) Changes: - remove langchain_core/schema since no clear distinction b/n schema and non-schema modules - make every module that doesn't end in -y plural - where easy have 1-2 classes per file - no more than one level of nesting in directories - only import from top level core modules in langchain	10 months ago

24 Commits (9b3a025f9c806a6f8a00030c7058c689536ae5a0)