langchain

Commit Graph

Author	SHA1	Message	Date
David DeCaprio	a4bcb45f65	core:Add optional max_messages to MessagePlaceholder (#16098 ) - Description: Add optional max_messages to MessagePlaceholder - Issue: [16096](https://github.com/langchain-ai/langchain/issues/16096) - Dependencies: None - Twitter handle: @davedecaprio Sometimes it's better to limit the history in the prompt itself rather than the memory. This is needed if you want different prompts in the chain to have different history lengths. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	3 months ago
Eugene Yurtsev	c2d43544cc	core[patch]: Document messages namespace (#23154 ) - Moved doc-strings below attribtues in TypedDicts -- seems to render better on APIReference pages. * Provided more description and some simple code examples	3 months ago
Sergey Kozlov	94452a94b1	core[patch[: add exceptions propagation test for astream_events v2 (#23159 ) Description: `astream_events(version="v2")` didn't propagate exceptions in `langchain-core<=0.2.6`, fixed in the #22916. This PR adds a unit test to check that exceptions are propagated upwards. Co-authored-by: Sergey Kozlov <sergey.kozlov@ludditelabs.io>	3 months ago
Bagatur	677408bfc9	core[patch]: fix chat history circular import (#23182 )	3 months ago
Eugene Yurtsev	883e90d06e	core[patch]: Add an example to the Document schema doc-string (#23131 ) Add an example to the document schema	3 months ago
ccurme	2b08e9e265	core[patch]: update test to catch circular imports (#23172 ) This raises ImportError due to a circular import: ```python from langchain_core import chat_history ``` This does not: ```python from langchain_core import runnables from langchain_core import chat_history ``` Here we update `test_imports` to run each import in a separate subprocess. Open to other ways of doing this!	3 months ago
Bagatur	e8a8286012	core[patch]: runnablewithchathistory from core.runnables (#23136 )	3 months ago
Eugene Yurtsev	aa6415aa7d	core[minor]: Support multiple keys in get_from_dict_or_env (#23086 ) Support passing multiple keys for ge_from_dict_or_env	3 months ago
Nuno Campos	f01f12ce1e	Include "no escape" and "inverted section" mustache vars in Prompt.input_variables and Prompt.input_schema (#22981 )	3 months ago
Bagatur	c2b2e3266c	core[minor]: message transformer utils (#22752 )	3 months ago
Nuno Campos	bd4b68cd54	core: run_in_executor: Wrap StopIteration in RuntimeError (#22997 ) - StopIteration can't be set on an asyncio.Future it raises a TypeError and leaves the Future pending forever so we need to convert it to a RuntimeError	3 months ago
Eugene Yurtsev	4a77a3ab19	core[patch]: fix validation of @deprecated decorator (#22513 ) This PR moves the validation of the decorator to a better place to avoid creating bugs while deprecating code. Prevent issues like this from arising: https://github.com/langchain-ai/langchain/issues/22510 we should replace with a linter at some point that just does static analysis	3 months ago
Jacob Lee	bcbb43480c	core[patch]: Treat type as a special field when merging lists (#22750 ) Should we even log a warning? At least for Anthropic, it's expected to get e.g. `text_block` followed by `text_delta`. @ccurme @baskaryan @efriis	3 months ago
Nuno Campos	bae82e966a	core: In astream_events v2 propagate cancel/break to the inner astream call (#22865 ) - previous behavior was for the inner astream to continue running with no interruption - also propagate break in core runnable methods	3 months ago
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
Erick Friis	2aaf86ddae	core: fix mustache falsy cases (#22747 )	3 months ago
Eugene Yurtsev	5a7eac191a	core[patch]: Add missing type annotations (#22756 ) Add missing type annotations. The missing type annotations will raise exceptions with pydantic 2.	3 months ago
William FH	be79ce9336	[Core] Unified Enable/Disable Tracing (#22576 )	4 months ago
Eugene Yurtsev	28f744c1f5	core[patch]: Correctly order parent ids in astream events (from root to immediate parent), add defensive check for cycles (#22637 ) This PR makes two changes: 1. Fixes the order of parent IDs to be from root to immediate parent 2. Adds a simple defensive check for cycles	4 months ago
Eugene Yurtsev	035a9c9609	core[minor]: Add parent_ids to astream_events API (#22563 ) Include a list of parent ids for each event in astream events.	4 months ago
Nicolas Nkiere	51005e2776	core[minor]: Add an async root listener and with_alisteners method (#22151 ) - [x] Adding AsyncRootListener: "langchain_core: Adding AsyncRootListener" - Description: Adding an AsyncBaseTracer, AsyncRootListener and `with_alistener` function. This is to enable binding async root listener to runnables. This currently only supported for sync listeners. - Issue: None - Dependencies: None - [x] Add tests and docs: Added units tests and example snippet code within the function description of `with_alistener` - [x] Lint and test: Run make format_diff, make lint_diff and make test	4 months ago
Eugene Yurtsev	9120cf5df2	core[patch]: Deduplicate of callback handlers in merge_configs (#22478 ) This PR adds deduplication of callback handlers in merge_configs. Fix for this issue: https://github.com/langchain-ai/langchain/issues/22227 The issue appears when the code is: 1) running python >=3.11 2) invokes a runnable from within a runnable 3) binds the callbacks to the child runnable from the parent runnable using with_config In this case, the same callbacks end up appearing twice: (1) the first time from with_config, (2) the second time with langchain automatically propagating them on behalf of the user. Prior to this PR this will emit duplicate events: ```python @tool async def get_items(question: str, callbacks: Callbacks): # <--- Accept callbacks """Ask question""" template = ChatPromptTemplate.from_messages( [ ( "human", "'{question}" ) ] ) chain = template \| chat_model.with_config( { "callbacks": callbacks, # <-- Propagate callbacks } ) return await chain.ainvoke({"question": question}) ``` Prior to this PR this will work work correctly (no duplicate events): ```python @tool async def get_items(question: str, callbacks: Callbacks): # <--- Accept callbacks """Ask question""" template = ChatPromptTemplate.from_messages( [ ( "human", "'{question}" ) ] ) chain = template \| chat_model return await chain.ainvoke({"question": question}, {"callbacks": callbacks}) ``` This will also work (as long as the user is using python >= 3.11) -- as langchain will automatically propagate callbacks ```python @tool async def get_items(question: str,): """Ask question""" template = ChatPromptTemplate.from_messages( [ ( "human", "'{question}" ) ] ) chain = template \| chat_model return await chain.ainvoke({"question": question}) ```	4 months ago
Guangdong Liu	bc7e32f315	core(patch):fix partial_variables not working with SystemMessagePromptTemplate (#20711 ) - Issue: close #17560 - @baskaryan, @eyurtsev	4 months ago
Jacob Lee	c01467b1f4	core[patch]: RFC: Allow concatenation of messages with multi part content (#22002 ) Anthropic's streaming treats tool calls as different content parts (streamed back with a different index) from normal content in the `content`. This means that we need to update our chunk-merging logic to handle chunks with multi-part content. The alternative is coerceing Anthropic's responses into a string, but we generally like to preserve model provider responses faithfully when we can. This will also likely be useful for multimodal outputs in the future. This current PR does unfortunately make `index` a magic field within content parts, but Anthropic and OpenAI both use it at the moment to determine order anyway. To avoid cases where we have content arrays with holes and to simplify the logic, I've also restricted merging to chunks in order. TODO: tests CC @baskaryan @ccurme @efriis	4 months ago
Nuno Campos	ed8e9c437a	core: In RunnableSequence pass kwargs to the first step (#22393 ) - This is a pattern that shows up occasionally in langgraph questions, people chain a graph to something else after, and want to pass the graph some kwargs (eg. stream_mode)	4 months ago
Harrison Chase	ee32369265	core[patch]: fix runnable history and add docs (#22283 )	4 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
Bagatur	d61bdeba25	core[patch]: allow access RunnableWithFallbacks.runnable attrs (#22139 ) RFC, candidate fix for #13095 #22134	4 months ago
hmasdev	bbd7015b5d	core[patch]: Add `TypeError` handler into `get_graph` of `Runnable` (#19856 ) # Description ## Problem `Runnable.get_graph` fails when `InputType` or `OutputType` property raises `TypeError`. - `003c98e5b4/libs/core/langchain_core/runnables/base.py (L250-L274)` - `003c98e5b4/libs/core/langchain_core/runnables/base.py (L394-L396)` This problem prevents getting a graph of `Runnable` objects whose `InputType` or `OutputType` property raises `TypeError` but whose `invoke` works well, such as `langchain.output_parsers.RegexParser`, which I have already pointed out in #19792 that a `TypeError` would occur. ## Solution - Add `try-except` syntax to handle `TypeError` to the codes which get `input_node` and `output_node`. # Issue - #19801 # Twitter Handle - [hmdev3](https://twitter.com/hmdev3) --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	4 months ago
Eugene Yurtsev	2d693c484e	docs: fix some spelling mistakes caught by newest version of code spell (#22090 ) Going to merge this even though it doesn't pass all tests, and open a separate PR for the remaining spelling mistakes.	4 months ago
ccurme	fbfed65fb1	core, partners: add token usage attribute to AIMessage (#21944 ) ```python class UsageMetadata(TypedDict): """Usage metadata for a message, such as token counts. Attributes: input_tokens: (int) count of input (or prompt) tokens output_tokens: (int) count of output (or completion) tokens total_tokens: (int) total token count """ input_tokens: int output_tokens: int total_tokens: int ``` ```python class AIMessage(BaseMessage): ... usage_metadata: Optional[UsageMetadata] = None """If provided, token usage information associated with the message.""" ... ```	4 months ago
Bagatur	50186da0a1	infra: rm unused # noqa violations (#22049 ) Updating #21137	4 months ago
Eugene Yurtsev	ded53297e0	core[patch]: Add unit test for RunnableGenerator for eventstream v2 (#21990 ) No unit tests with runnable generator	4 months ago
Nuno Campos	fb6108c8f5	core[patch]: In astream_events(version=v2) tap output of root run (#21977 ) - if tap_output_iter/aiter is called multiple times for the same run issue events only once - if chat model run is tapped don't issue duplicate on_llm_new_token events - if first chunk arrives after run has ended do not emit it as a stream event --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	4 months ago
Michael Reed	7a5e1bcf99	core[patch]: Fix NPE in function_calling._get_python_function_required_args (#21863 ) Example error message: line 206, in _get_python_function_required_args if is_function_type and required[0] == "self": ~~~~~~~~^^^ IndexError: list index out of range Thank you for contributing to LangChain! - [x] PR title: "package: description" - Where "package" is whichever of langchain, community, core, experimental, etc. is being modified. Use "docs: ..." for purely docs changes, "templates: ..." for template changes, "infra: ..." for CI changes. - Example: "community: add foobar LLM" - [x] PR message: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [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. - [x] 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/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	4 months ago
Nuno Campos	b1e7b40b6a	core: Tap output of sync iterators for astream_events (#21842 ) Thank you for contributing to LangChain! - [ ] PR title: "package: description" - Where "package" is whichever of langchain, community, core, experimental, etc. is being modified. Use "docs: ..." for purely docs changes, "templates: ..." for template changes, "infra: ..." for CI changes. - Example: "community: add foobar LLM" - [ ] PR message: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [ ] 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/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.	4 months ago
Eugene Yurtsev	67b6f6c82a	core[patch]: Check if event loop is closed in memory stream (#21841 ) Check if event stream is closed in memory loop. Using try/except here to avoid race condition, but this may incur a small overhead in versions prios to 3.11	4 months ago
ccurme	181dfef118	core, standard tests, partner packages: add test for model params (#21677 ) 1. Adds `.get_ls_params` to BaseChatModel which returns ```python class LangSmithParams(TypedDict, total=False): ls_provider: str ls_model_name: str ls_model_type: Literal["chat"] ls_temperature: Optional[float] ls_max_tokens: Optional[int] ls_stop: Optional[List[str]] ``` by default it will only return ```python {ls_model_type="chat", ls_stop=stop} ``` 2. Add these params to inheritable metadata in `CallbackManager.configure` 3. Implement `.get_ls_params` and populate all params for Anthropic + all subclasses of BaseChatOpenAI Sample trace: https://smith.langchain.com/public/d2962673-4c83-47c7-b51e-61d07aaffb1b/r OpenAI: <img width="984" alt="Screenshot 2024-05-17 at 10 03 35 AM" src="https://github.com/langchain-ai/langchain/assets/26529506/2ef41f74-a9df-4e0e-905d-da74fa82a910"> Anthropic: <img width="978" alt="Screenshot 2024-05-17 at 10 06 07 AM" src="https://github.com/langchain-ai/langchain/assets/26529506/39701c9f-7da5-4f1a-ab14-84e9169d63e7"> Mistral (and all others for which params are not yet populated): <img width="977" alt="Screenshot 2024-05-17 at 10 08 43 AM" src="https://github.com/langchain-ai/langchain/assets/26529506/37d7d894-fec2-4300-986f-49a5f0191b03">	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	ca768c8353	[Core] Check is async callable (#21714 ) To permit proper coercion of objects like the following: ```python class MyAsyncCallable: async def __call__(self, foo): return await ... class MyAsyncGenerator: async def __call__(self, foo): await ... yield ```	4 months ago
Eugene Yurtsev	5c2cfabec6	core[minor]: Add v2 implementation of astream events (#21638 ) This PR introduces a v2 implementation of astream events that removes intermediate abstractions and fixes some issues with v1 implementation. The v2 implementation significantly reduces relevant code that's associated with the astream events implementation together with overhead. After this PR, the astream events implementation: - Uses an async callback handler - No longer relies on BaseTracer - No longer relies on json patch As a result of this re-write, a number of issues were discovered with the existing implementation. ## Changes in V2 vs. V1 ### on_chat_model_end `output` The outputs associated with `on_chat_model_end` changed depending on whether it was within a chain or not. As a root level runnable the output was: ```python "data": {"output": AIMessageChunk(content="hello world!", id='some id')} ``` As part of a chain the output was: ``` "data": { "output": { "generations": [ [ { "generation_info": None, "message": AIMessageChunk( content="hello world!", id=AnyStr() ), "text": "hello world!", "type": "ChatGenerationChunk", } ] ], "llm_output": None, } }, ``` After this PR, we will always use the simpler representation: ```python "data": {"output": AIMessageChunk(content="hello world!", id='some id')} ``` NOTE Non chat models (i.e., regular LLMs) are still associated with the more verbose format. ### Remove some `_stream` events `on_retriever_stream` and `on_tool_stream` events were removed -- these were not real events, but created as an artifact of implementing on top of astream_log. The same information is already available in the `x_on_end` events. ### Propagating Names Names of runnables have been updated to be more consistent ```python model = GenericFakeChatModel(messages=infinite_cycle).configurable_fields( messages=ConfigurableField( id="messages", name="Messages", description="Messages return by the LLM", ) ) ``` Before: ```python "name": "RunnableConfigurableFields", ``` After: ```python "name": "GenericFakeChatModel", ``` ### on_retriever_end on_retriever_end will always return `output` which is a list of documents (rather than a dict containing a key called "documents") ### Retry events Removed the `on_retry` callback handler. It was incorrectly showing that the failed function being retried has invoked `on_chain_end` https://github.com/langchain-ai/langchain/pull/21638/files#diff-e512e3f84daf23029ebcceb11460f1c82056314653673e450a5831147d8cb84dL1394	4 months ago
Eugene Yurtsev	5c64c004cc	core[patch]: Add unit tests with some streaming scenarios (#21668 ) Add unit tests that show differences between sync / async versions when streaming. The inner on_chain_chunk event is missing if mixing sync and async functionality. Likely due to missing tap_output_iter implementation on the sync variant of `_transform_stream_with_config`	4 months ago
Eugene Yurtsev	2ac4d2960c	core[patch]: Add unit test to catch ordering (#21669 ) Add unit test to catch ordering issues	4 months ago
Guangdong Liu	a156aace2b	core[patch]:Fix Incorrect listeners parameters for Runnable.with_listeners() and .map() (#20661 ) - Issue: fix #20509 - @baskaryan, @eyurtsev ![image](https://github.com/langchain-ai/langchain/assets/48236177/f799a976-b983-4d8b-b373-64392e1fd6c6)	4 months ago
Nuno Campos	ad0f3c14c2	core: allow mermaid node labels to have any characters (#21385 ) - it's only node ids that are limited Thank you for contributing to LangChain! - [ ] PR title: "package: description" - Where "package" is whichever of langchain, community, core, experimental, etc. is being modified. Use "docs: ..." for purely docs changes, "templates: ..." for template changes, "infra: ..." for CI changes. - Example: "community: add foobar LLM" - [ ] PR message: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [ ] 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/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.	5 months ago
Nuno Campos	6f17158606	fix: core: Include in json output also fields set outside the constructor (#21342 )	5 months ago
Leonid Ganeline	3ef8b24277	core[patch]: `utils.guard_import` fix (#21133 ) Issues (nit): 1. `utils.guard_import` prints wrong error message when there is an import `error.` It prints the whole `module_name` but should be only the first part as the pip package name. E.i. `langchain_core.utils` -> print not `langchain-core` but `langchain_core.utils`. Also replace '_' with '-' in the pip package name. 2. it does not handle the `ModuleNotFoundError` which raised if `guard_import("wrong_module")` Fixed issues; added ut-s. Controversial: I've reraised `ModuleNotFoundError` as `ImportError`, since in case of the error, the proposed action is the same - we need to install a missed package.	5 months ago
Nuno Campos	47ce8d5a57	core: tracer: remove numeric execution order (#21220 ) - this hasn't been used in a long time and requires some additional bookkeeping i'm going to streamline in the next pr	5 months ago
Nuno Campos	663747b730	core[patch]: Fixes for convert_messages (#21207 ) - support two-tuples of any sequence type (eg. json.loads never produces tuples) - support type alias for role key - if id is passed in in dict form use it - if tool_calls passed in in dict form use them --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	5 months ago
William FH	ab55f6996d	[Core] Tracing: update parent run_tree's child_runs (#21049 )	5 months ago

1 2 3 4 5

241 Commits (9b3a025f9c806a6f8a00030c7058c689536ae5a0)