langchain

Commit Graph

Author	SHA1	Message	Date
Maxime Perrin	aa785fa6ec	core[minor]: allow LLMs async streaming to fallback on sync streaming (#18960 ) - Description: Handling fallbacks when calling async streaming for a LLM that doesn't support it. - Issue: #18920 - Twitter handle:@maximeperrin_ --------- Co-authored-by: Maxime Perrin <mperrin@doing.fr>	6 months ago
Eugene Yurtsev	06165efb5b	core[patch]: RunnablePassthrough transform to autoupgrade to AddableDict (#19051 ) Follow up on https://github.com/langchain-ai/langchain/pull/18743 which missed RunnablePassthrough Issues: https://github.com/langchain-ai/langchain/issues/18741 https://github.com/langchain-ai/langgraph/issues/136 https://github.com/langchain-ai/langserve/issues/504	6 months ago
Nuno Campos	751fb7de20	Add new beta StructuredPrompt (#19080 ) 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.	6 months ago
Nuno Campos	2b7c3c548d	core[minor]: Add Runnable.batch_as_completed (#17603 ) This PR adds `batch as completed` method to the standard Runnable interface. It takes in a list of inputs and yields the corresponding outputs as the inputs are completed.	6 months ago
Naman Jain	75122646b5	core[patch]: fixed circular dependency with json schema (#18657 ) Description: Circular dependencies when parsing references leading to `RecursionError: maximum recursion depth exceeded` issue. This PR address the issue by handling previously seen refs as in any typical DFS to avoid infinite depths. Issue: https://github.com/langchain-ai/langchain/issues/12163 Twitter handle: https://twitter.com/theBhulawat - [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/ --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	6 months ago
Bagatur	18de77cc8c	core[minor]: add streaming support to OAI tool parsers (#18940 ) Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Bagatur	e0e688a277	core[minor]: generation info on msg (#18592 ) related to #16403 #17188	6 months ago
Bagatur	19721246f5	core[patch]: support labeled json schema as tools (#18935 )	6 months ago
Erick Friis	bbb609ac9d	core[patch]: fix arbitrary config keys (#18827 )	6 months ago
Eugene Yurtsev	cdfb5b4ca1	core[minor]: Chat Models to fallback astream to fallback on sync stream if available (#18748 ) Allows all chat models that implement _stream, but not _astream to still have async streaming to work. Amongst other things this should resolve issues with streaming community model implementations through langserve since langserve is exclusively async.	6 months ago
Bagatur	3e29c04213	core[minor]: add BaseMessage.response_metadata (#18699 )	6 months ago
Eugene Yurtsev	6caceb5473	core[patch]: Automatic upgrade to AddableDict in transform and atransform (#18743 ) Automatic upgrade to transform and atransform Closes: https://github.com/langchain-ai/langchain/issues/18741 https://github.com/langchain-ai/langgraph/issues/136 https://github.com/langchain-ai/langserve/issues/504	6 months ago
Eugene Yurtsev	ca299a8e08	Docs: Add custom parsing documentation and extending langchain (#18331 ) * Added extending langchain.mdx -- we'll need to add links as we add more custom documentation * Added partial documentation about parsers	6 months ago
Eugene Yurtsev	8c71f92cb2	core: upgrade mypy to recent mypy (#18753 ) Testing this works per package on CI	6 months ago
Christophe Bornet	4a7d73b39d	community: If load() has been overridden, use it in default lazy_load() (#18690 )	6 months ago
Erick Friis	e1924b3e93	core[patch]: deprecate hwchase17/langchain-hub, address path traversal (#18600 ) Deprecates the old langchain-hub repository. Does not deprecate the new https://smith.langchain.com/hub @PinkDraconian has correctly raised that in the event someone is loading unsanitized user input into the `try_load_from_hub` function, they have the ability to load files from other locations in github than the hwchase17/langchain-hub repository. This PR adds some more path checking to that function and deprecates the functionality in favor of the hub built into LangSmith.	7 months ago
William De Vena	42341bc787	infra: fake model invoke callback prior to yielding token (#18286 ) ## PR title core[patch]: Invoke callback prior to yielding ## PR message Description: Invoke on_llm_new_token callback prior to yielding token in _stream and _astream methods. Issue: https://github.com/langchain-ai/langchain/issues/16913 Dependencies: None Twitter handle: None	7 months ago
William FH	fdab931fd3	[Core] Patch: rm dumpd of outputs from runnables/base (#18295 ) It obstructs evaluations when your return a pydantic object.	7 months ago
Nuno Campos	d9fd1194f5	Remove check preventing passing non-declared config keys (#18276 ) 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.	7 months ago
Harrison Chase	d7c607ca00	core[minor]: move document compressor base (#17910 )	7 months ago
Bagatur	767523f364	core[patch], langchain[patch], templates: move openai functions parsers to core (#18060 ) ![Screenshot 2024-02-23 at 7 48 03 PM](https://github.com/langchain-ai/langchain/assets/22008038/e5540c4d-0020-4ece-869f-ae19db2a1f3f)	7 months ago
Nuno Campos	b1d9ce541d	Add BaseMessage.id (#17835 ) 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.	7 months ago
Bagatur	b5f8cf9509	core[minor], openai[minor], langchain[patch]: BaseLanguageModel.with_structured_output #17302 ) ```python class Foo(BaseModel): bar: str structured_llm = ChatOpenAI().with_structured_output(Foo) ``` --------- Co-authored-by: Erick Friis <erick@langchain.dev>	7 months ago
ccurme	1b0802babe	core: fix .bind when used with RunnableLambda async methods (#17739 ) Description: Here is a minimal example to illustrate behavior: ```python from langchain_core.runnables import RunnableLambda def my_function(args, kwargs): return 3 + kwargs.get("n", 0) runnable = RunnableLambda(my_function).bind(n=1) assert 4 == runnable.invoke({}) assert [4] == list(runnable.stream({})) assert 4 == await runnable.ainvoke({}) assert [4] == [item async for item in runnable.astream({})] ``` Here, `runnable.invoke({})` and `runnable.stream({})` work fine, but `runnable.ainvoke({})` raises ``` TypeError: RunnableLambda._ainvoke.<locals>.func() got an unexpected keyword argument 'n' ``` and similarly for `runnable.astream({})`: ``` TypeError: RunnableLambda._atransform.<locals>.func() got an unexpected keyword argument 'n' ``` Here we assume that this behavior is undesired and attempt to fix it. Issue:* https://github.com/langchain-ai/langchain/issues/17241, https://github.com/langchain-ai/langchain/discussions/16446	7 months ago
Nuno Campos	223e5eff14	Add JSON representation of runnable graph to serialized representation (#17745 ) Sent to LangSmith Thank you for contributing to LangChain! Checklist: - [ ] PR title: Please title your PR "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 template message and replace it with the following bulleted list - 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! - [ ] Pass lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified to check that you're passing lint and testing. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ - [ ] 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. 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.	7 months ago
Leonid Ganeline	1d2aa19aee	docs: Fix bug that caused the word "Beta" to appear twice in doc-strings (#17704 ) The current issue: Several beta descriptions in the API Reference are duplicated. For example: `[Beta] Get a context value.[Beta] Get a context value.` for the [ContextGet class](https://api.python.langchain.com/en/latest/core_api_reference.html#module-langchain_core.beta) description. NOTE: I've tested it only with a new ut! I cannot build API Reference locally :( This PR related to #17615	7 months ago
Leonid Ganeline	0835ebad70	docs: Fix bug that caused the word "Deprecated" to appear twice in doc-strings (#17615 ) The current issue: Most of the deprecation descriptions are duplicated. For example: `[Deprecated] Chat Agent.[Deprecated] Chat Agent.` for the [ChatAgent class](https://api.python.langchain.com/en/latest/langchain_api_reference.html#classes) description. NOTE: I've tested it only with new ut! I cannot build API Reference locally :(	7 months ago
Erick Friis	86d3e42853	core[minor]: add name to basemessage (#17539 ) Adds an optional name param to our base message to support passing names into LLMs. OpenAI supports having a name on anything except tool message now (system, ai, user/human).	7 months ago
JongRok BAEK	8d6cc90fc5	langchain.core : Use shallow copy for schema manipulation in JsonOutputParser.get_format_instructions (#17162 ) - Description : Fix: Use shallow copy for schema manipulation in get_format_instructions Prevents side effects on the original schema object by using a dictionary comprehension for a safer and more controlled manipulation of schema key-value pairs, enhancing code reliability. - Issue: #17161 - Dependencies: None - Twitter handle: None	7 months ago
Sergey Kozlov	db6f266d97	core: improve None value processing in merge_dicts() (#17462 ) - Description: fix `None` and `0` merging in `merge_dicts()`, add tests. ```python from langchain_core.utils._merge import merge_dicts assert merge_dicts({"a": None}, {"a": 0}) == {"a": 0} ``` --------- Co-authored-by: Sergey Kozlov <sergey.kozlov@ludditelabs.io>	7 months ago
James Braza	64938ae6f2	infra: unit testing `check_package_version` (#16825 ) Wrote a unit test for `check_package_version` in the core package. Note that this is a revival of https://github.com/langchain-ai/langchain/pull/16387 after GitHub incident (see https://github.com/langchain-ai/langchain/discussions/16796).	7 months ago
Eugene Yurtsev	93472ee9e6	core[patch]: Replace memory stream implementation used by LogStreamCallbackHandler (#17185 ) This PR replaces the memory stream implementation used by the LogStreamCallbackHandler. This implementation resolves an issue in which streamed logs and streamed events originating from sync code would arrive only after the entire sync code would finish execution (rather than arriving in real time as they're generated). One example is if trying to stream tokens from an llm within a tool. If the tool was an async tool, but the llm was invoked via stream (sync variant) rather than astream (async variant), then the tokens would fail to stream in real time and would all arrived bunched up after the tool invocation completed.	7 months ago
William FH	7c03cc5ed4	Support serialization when inputs/outputs contain generators (#17338 ) Pydantic's `dict()` function raises an error here if you pass in a generator. We have a more robust serialization function in lagnsmith that we will use instead.	7 months ago
Leonid Ganeline	ae66bcbc10	core[patch]: docstring update (#16813 ) - added missed docstrings - formated docstrings to consistent form	7 months ago
Eugene Yurtsev	e10030e241	core[patch]: Add unit test to cover different streaming format for json parsing (#17063 ) Add unit test to cover this issue: https://github.com/langchain-ai/langchain/issues/16423 which was resolved by this PR: https://github.com/langchain-ai/langchain/pull/16670/files --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
Bagatur	852973d616	langchain[minor], core[minor]: update json, pydantic parser. add openai-json structured output runnable (#16914 )	7 months ago
Eugene Yurtsev	fbab8baac5	core[patch]: Add astream events config test (#17055 ) Verify that astream events propagates config correctly --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
William FH	3d5e988c55	Add prompt metadata + tags (#17054 )	7 months ago
Christophe Bornet	2ef69fe11b	Add async methods to BaseChatMessageHistory and BaseMemory (#16728 ) Adds: * async methods to BaseChatMessageHistory * async methods to ChatMessageHistory * async methods to BaseMemory * async methods to BaseChatMemory * async methods to ConversationBufferMemory * tests of ConversationBufferMemory's async methods Twitter handle: cbornet_	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
Bagatur	c29e9b6412	core[patch]: fix chat prompt partial messages placeholder var (#16918 )	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
William FH	131c043864	Fix loading of ImagePromptTemplate (#16868 ) We didn't override the namespace of the ImagePromptTemplate, so it is listed as being in langchain.schema This updates the mapping to let the loader deserialize. Alternatively, we could make a slight breaking change and update the namespace of the ImagePromptTemplate since we haven't broadly publicized/documented it yet..	8 months ago
Eugene Yurtsev	2e5949b6f8	core(minor): Add bulk add messages to BaseChatMessageHistory interface (#15709 ) * Add bulk add_messages method to the interface. * Update documentation for add_ai_message and add_human_message to denote them as being marked for deprecation. We should stop using them as they create more incorrect (inefficient) ways of doing things	8 months ago
Yudhajit Sinha	1703fe2361	core[patch]: preserve inspect.iscoroutinefunction with @beta decorator (#16440 ) Adjusted deprecate decorator to make sure decorated async functions are still recognized as "coroutinefunction" by inspect Addresses #16402 <!-- 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. --> --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	8 months ago
Tze Min	6ef718c5f4	Core: fix Anthropic json issue in streaming (#16670 ) Description: fix ChatAnthropic json issue in streaming Issue: https://github.com/langchain-ai/langchain/issues/16423 Dependencies: n/a --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	8 months ago
William FH	38425c99d2	core[minor]: Image prompt template (#14263 ) Builds on Bagatur's (#13227). See unit test for example usage (below) ```python def test_chat_tmpl_from_messages_multipart_image() -> None: base64_image = "abcd123" other_base64_image = "abcd123" template = ChatPromptTemplate.from_messages( [ ("system", "You are an AI assistant named {name}."), ( "human", [ {"type": "text", "text": "What's in this image?"}, # OAI supports all these structures today { "type": "image_url", "image_url": "data:image/jpeg;base64,{my_image}", }, { "type": "image_url", "image_url": {"url": "data:image/jpeg;base64,{my_image}"}, }, {"type": "image_url", "image_url": "{my_other_image}"}, { "type": "image_url", "image_url": {"url": "{my_other_image}", "detail": "medium"}, }, { "type": "image_url", "image_url": {"url": "https://www.langchain.com/image.png"}, }, { "type": "image_url", "image_url": {"url": "data:image/jpeg;base64,foobar"}, }, ], ), ] ) messages = template.format_messages( name="R2D2", my_image=base64_image, my_other_image=other_base64_image ) expected = [ SystemMessage(content="You are an AI assistant named R2D2."), HumanMessage( content=[ {"type": "text", "text": "What's in this image?"}, { "type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}, }, { "type": "image_url", "image_url": { "url": f"data:image/jpeg;base64,{other_base64_image}" }, }, { "type": "image_url", "image_url": {"url": f"{other_base64_image}"}, }, { "type": "image_url", "image_url": { "url": f"{other_base64_image}", "detail": "medium", }, }, { "type": "image_url", "image_url": {"url": "https://www.langchain.com/image.png"}, }, { "type": "image_url", "image_url": {"url": "data:image/jpeg;base64,foobar"}, }, ] ), ] assert messages == expected ``` --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Brace Sproul <braceasproul@gmail.com>	8 months ago
Nuno Campos	52ccae3fb1	Accept message-like things in Chat models, LLMs and MessagesPlaceholder (#16418 )	8 months ago
Bagatur	ef42d9d559	core[patch], community[patch], openai[patch]: consolidate openai tool… (#16485 ) … converters One way to convert anything to an OAI function: convert_to_openai_function One way to convert anything to an OAI tool: convert_to_openai_tool Corresponding bind functions on OAI models: bind_functions, bind_tools	8 months ago
James Braza	d511366dd3	infra: absolute `EXAMPLE_DIR` path in core unit tests (#16325 ) If you invoked testing from places besides `core/`, this `EXAMPLE_DIR` path won't work. This PR makes`EXAMPLE_DIR` robust against invocation location	8 months ago

1 2 3

124 Commits (611d5a161868d6f83a88d6d47d5f7a4f79ff8045)