langchain

Commit Graph

Author	SHA1	Message	Date
ccurme	e77eeee6ee	core[patch]: add standard tracing params for retrievers (#25240 )	1 month ago
gbaian10	aa2722cbe2	docs: update numbering of items in docstring (#25267 ) A problem similar to #25093 . Co-authored-by: ccurme <chester.curme@gmail.com>	1 month ago
Eugene Yurtsev	6dd9f053e3	core[patch]: Deprecating beta upsert APIs in vectorstore (#25069 ) This PR deprecates the beta upsert APIs in vectorstore. We'll introduce them in a V2 abstraction instead to keep the existing vectorstore implementations lighter weight. The main problem with the existing APIs is that it's a bit more challenging to implement the correct behavior w/ respect to IDs since ID can be present in both the function signature and as an optional attribute on the document object. But VectorStores that pass the standard tests should have implemented the semantics properly! --------- Co-authored-by: Erick Friis <erick@langchain.dev>	1 month ago
Eugene Yurtsev	b6f0174bb9	community[patch],core[patch]: Update EdenaiTool root_validator and add unit test in core (#25233 ) This PR gets rid `root_validators(allow_reuse=True)` logic used in EdenAI Tool in preparation for pydantic 2 upgrade. - add another test to secret_from_env_factory	1 month ago
blueoom	c3ced4c6ce	core[patch]: use time.monotonic() instead time.time() in InMemoryRateLimiter Description: The get time point method in the _consume() method of core.rate_limiters.InMemoryRateLimiter uses time.time(), which can be affected by system time backwards. Therefore, it is recommended to use the monotonically increasing monotonic() to obtain the time ```python with self._consume_lock: now = time.time() # time.time() -> time.monotonic() # initialize on first call to avoid a burst if self.last is None: self.last = now elapsed = now - self.last # when use time.time(), elapsed may be negative when system time backwards ```	1 month ago
Bagatur	7040013140	core[patch]: fix deprecation pydantic bug (#25204 ) #25004 is incompatible with pydantic < 1.10.17. Introduces fix for this.	1 month ago
Eugene Yurtsev	429a0ee7fd	core[minor]: Add factory for looking up secrets from the env (#25198 ) Add factory method for looking secrets from the env.	1 month ago
Erick Friis	c6ece6a96d	core: autodetect more ls params (#25044 ) Co-authored-by: ccurme <chester.curme@gmail.com>	1 month ago
Eugene Yurtsev	30fb345342	core[minor]: Add from_env utility (#25189 ) Add a utility that can be used as a default factory The goal will be to start migrating from of the pydantic models to use `from_env` as a default factory if possible. ```python from pydantic import Field, BaseModel from langchain_core.utils import from_env class Foo(BaseModel): name: str = Field(default_factory=from_env('HELLO')) ```	1 month ago
Eugene Yurtsev	2f209d84fa	core[patch]: Add pydantic get_fields adapter (#25187 ) Add adapter to get fields	1 month ago
Eugene Yurtsev	425f6ffa5b	core[patch]: Fix aindex API (#25155 ) A previous PR accidentally broke the aindex API by renaming a positional argument vectorstore into vector_store. This PR reverts this change.	1 month ago
Eugene Yurtsev	7b1a132aff	core[patch]: Add unit tests for Serializable (#25152 ) Add a few test cases for serializable (many other test cases already covered throguh runnable tests).	1 month ago
Bagatur	df99b832a7	core[patch]: support Field deprecation (#25004 ) ![Screenshot 2024-08-02 at 4 23 17 PM](https://github.com/user-attachments/assets/c757e093-877e-4af6-9dcd-984195454158)	1 month ago
ccurme	803eba3163	core[patch]: check for model_fields attribute (#25108 ) `__fields__` raises a warning in pydantic v2	1 month ago
Bagatur	b4c12346cc	core[patch]: Release 0.2.29 (#25126 )	1 month ago
Erick Friis	dff83cce66	core[patch]: base language model disable_streaming (#25070 ) Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	1 month ago
Eugene Yurtsev	28e0958ff4	core[patch]: Relax rate limit unit tests in terms of timing (#25140 ) Relax rate limit unit tests	1 month ago
Eugene Yurtsev	4d28c70000	core[patch]: Sort Config attributes (#25127 ) This PR does an aesthetic sort of the config object attributes. This will make it a bit easier to go back and forth between pydantic v1 and pydantic v2 on the 0.3.x branch	1 month ago
Bagatur	70677202c7	core[patch]: Release 0.2.29rc1 (#25115 )	1 month ago
Bagatur	78403a3746	core[patch], openai[patch]: enable strict tool calling (#25111 ) Introduced https://openai.com/index/introducing-structured-outputs-in-the-api/	1 month ago
Eugene Yurtsev	d283f452cc	core[minor]: Add support for DocumentIndex in the index api (#25100 ) Support document index in the index api.	2 months ago
William FH	267855b3c1	Set Context in RunnableSequence & RunnableParallel (#25073 )	2 months ago
Bagatur	2c798622cd	docs: runnable docstring space (#25106 )	2 months ago
Eugene Yurtsev	293a4a78de	core[patch]: Include dependencies in sys_info (#25076 ) `python -m langchain_core.sys_info` ```bash System Information ------------------ > OS: Linux > OS Version: #44~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Jun 18 14:36:16 UTC 2 > Python Version: 3.11.4 (main, Sep 25 2023, 10:06:23) [GCC 11.4.0] Package Information ------------------- > langchain_core: 0.2.28 > langchain: 0.2.8 > langsmith: 0.1.85 > langchain_anthropic: 0.1.20 > langchain_openai: 0.1.20 > langchain_standard_tests: 0.1.1 > langchain_text_splitters: 0.2.2 > langgraph: 0.1.19 Optional packages not installed ------------------------------- > langserve Other Dependencies ------------------ > aiohttp: 3.9.5 > anthropic: 0.31.1 > async-timeout: Installed. No version info available. > defusedxml: 0.7.1 > httpx: 0.27.0 > jsonpatch: 1.33 > numpy: 1.26.4 > openai: 1.39.0 > orjson: 3.10.6 > packaging: 24.1 > pydantic: 2.8.2 > pytest: 7.4.4 > PyYAML: 6.0.1 > requests: 2.32.3 > SQLAlchemy: 2.0.31 > tenacity: 8.5.0 > tiktoken: 0.7.0 > typing-extensions: 4.12.2 ```	2 months ago
orkhank	111c7df117	docs: update numbering of items in method docs (#25093 ) Some methods' doc strings have a wrong numbering of items. The numbers were adjusted accordingly	2 months ago
Bagatur	6eb42c657e	core[patch]: Remove default BaseModel init docstring (#25009 ) Currently a default init docstring gets appended to the class docstring of every BaseModel inherited object. This removes the default init docstring. ![Screenshot 2024-08-02 at 5 09 55 PM](https://github.com/user-attachments/assets/757fe4ae-a793-4e7d-8354-512de2c06818)	2 months ago
Gram Liu	88a9a6a758	core[patch]: Add pydantic metadata to subset model (#25032 ) - Description: This includes Pydantic field metadata in `_create_subset_model_v2` so that it gets included in the final serialized form that get sent out. - Issue: #25031 - Dependencies: n/a - Twitter handle: @gramliu --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	2 months ago
BhujayKumarBhatta	8f33fce871	docs: change for optional variables in chatprompt (#25017 ) Fixes #24884	2 months ago
Bagatur	e572521f2a	core[patch]: exclude special pydantic init params (#25084 )	2 months ago
Eugene Yurtsev	4bcd2aad6c	core[patch]: Relax time constraints on rate limit test (#25071 ) Try to keep the unit test fast, but also have it repeat more robustly	2 months ago
Eugene Yurtsev	41dfad5104	core[minor]: Introduce DocumentIndex abstraction (#25062 ) This PR adds a minimal document indexer abstraction. The goal of this abstraction is to allow developers to create custom retrievers that also have a standard indexing API and allow updating the document content in them. The abstraction comes with a test suite that can verify that the indexer implements the correct semantics. This is an iteration over a previous PRs (https://github.com/langchain-ai/langchain/pull/24364). The main difference is that we're sub-classing from BaseRetriever in this iteration and as so have consolidated the sync and async interfaces. The main problem with the current design is that runt time search configuration has to be specified at init rather than provided at run time. We will likely resolve this issue in one of the two ways: (1) Define a method (`get_retriever`) that will allow creating a retriever at run time with a specific configuration.. If we do this, we will likely break the subclass on BaseRetriever (2) Generalize base retriever so it can support structured queries --------- Co-authored-by: Erick Friis <erick@langchain.dev>	2 months ago
Bagatur	1dcee68cb8	docs: show beta directive (#25013 ) ![Screenshot 2024-08-02 at 7 15 34 PM](https://github.com/user-attachments/assets/086831c7-36f3-4962-98dc-d707b6289747)	2 months ago
Bagatur	e81ddb32a6	docs: fix kwargs docstring (#25010 ) Fix: ![Screenshot 2024-08-02 at 5 33 37 PM](https://github.com/user-attachments/assets/7c56cdeb-ee81-454c-b3eb-86aa8a9bdc8d)	2 months ago
Bagatur	57747892ce	docs: show deprecation warning first in api ref (#25001 ) OLD ![Screenshot 2024-08-02 at 3 29 39 PM](https://github.com/user-attachments/assets/7f169121-1202-4770-a006-d72ac7a1aa33) NEW ![Screenshot 2024-08-02 at 3 29 45 PM](https://github.com/user-attachments/assets/9cc07cbd-2ae9-4077-95c5-03cb051e6cd7)	2 months ago
Bagatur	4305f78e40	core[patch]: Release 0.2.28 (#25000 )	2 months ago
Bagatur	0de0cd2d31	core[patch]: merge message runs nit (#24997 ) Only add separator if both chunks are non-empty	2 months ago
Bagatur	245cb5a252	core[patch]: Release 0.2.27 (#24952 )	2 months ago
Bagatur	199e9c5ae0	core[patch]: Fix tool args schema inherited field parsing (#24936 ) Fix #24925	2 months ago
Leonid Ganeline	4092876863	core: docstrings `BaseCallbackHandler update (#24948 ) Added missed docstrings	2 months ago
WU LIFU	ad16eed119	core[patch]: runnable config ensure_config deep copy from var_child_runnable… (#24862 ) issue: #24660 RunnableWithMessageHistory.stream result in error because the [evaluation](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/runnables/branch.py#L220) of the branch [condition](`99eb31ec41/libs/core/langchain_core/runnables/history.py (L328C1-L329C1)`) unexpectedly trigger the "[on_end](`99eb31ec41/libs/core/langchain_core/runnables/history.py (L332)`)" (exit_history) callback of the default branch descriptions After a lot of investigation I'm convinced that the root cause is that 1. during the execution of the runnable, the [var_child_runnable_config](`99eb31ec41/libs/core/langchain_core/runnables/config.py (L122)`) is shared between the branch [condition](`99eb31ec41/libs/core/langchain_core/runnables/history.py (L328C1-L329C1)`) runnable and the [default branch runnable](`99eb31ec41/libs/core/langchain_core/runnables/history.py (L332)`) within the same context 2. when the default branch runnable runs, it gets the [var_child_runnable_config](`99eb31ec41/libs/core/langchain_core/runnables/config.py (L163)`) and may unintentionally [add more handlers ](`99eb31ec41/libs/core/langchain_core/runnables/config.py (L325)`)to the callback manager of this config 3. when it is again the turn for the [condition](`99eb31ec41/libs/core/langchain_core/runnables/history.py (L328C1-L329C1)`) to run, it gets the `var_child_runnable_config` whose callback manager has the handlers added by the default branch. When it runs that handler (`exit_history`) it leads to the error with the assumption that, the `ensure_config` function actually does want to create a immutable copy from `var_child_runnable_config` because it starts with an [`empty` variable ](`99eb31ec41/libs/core/langchain_core/runnables/config.py (L156)`), i go ahead to do a deepcopy to ensure that future modification to the returned value won't affect the `var_child_runnable_config` variable Having said that I actually 1. don't know if this is a proper fix 2. don't know whether it will lead to other unintended consequence 3. don't know why only "stream" runs into this issue while "invoke" runs without problem so @nfcampos @hwchase17 please help review, thanks! --------- Co-authored-by: Lifu Wu <lifu@nextbillion.ai> Co-authored-by: Nuno Campos <nuno@langchain.dev> Co-authored-by: Bagatur <baskaryan@gmail.com>	2 months ago
Eugene Yurtsev	75776e4a54	core[patch]: In unit tests, use `_schema()` instead of BaseModel.schema() (#24930 ) This PR introduces a module with some helper utilities for the pydantic 1 -> 2 migration. They're meant to be used in the following way: 1) Use the utility code to get unit tests pass without requiring modification to the unit tests 2) (If desired) upgrade the unit tests to match pydantic 2 output 3) (If desired) stop using the utility code Currently, this module contains a way to map `schema()` generated by pydantic 2 to (mostly) match the output from pydantic v1.	2 months ago
Bagatur	25b93cc4c0	core[patch]: stringify tool non-content blocks (#24626 ) Slightly breaking bugfix. Shouldn't cause too many issues since no models would be able to handle non-content block ToolMessage.content anyways.	2 months ago
Eugene Yurtsev	210623b409	core[minor]: Add support for pydantic 2 to utility to get fields (#24899 ) Add compatibility for pydantic 2 for a utility function. This will help push some small changes to master, so they don't have to be kept track of on a separate branch.	2 months ago
Bagatur	7d1694040d	core[patch]: Release 0.2.26 (#24898 )	2 months ago
Eugene Yurtsev	5099a9c9b4	core[patch]: Update unit tests with a workaround for using AnyID in pydantic 2 (#24892 ) Pydantic 2 ignores __eq__ overload for subclasses of strings.	2 months ago
Bagatur	8461934c2b	core[patch], integrations[patch]: convert TypedDict to tool schema support (#24641 ) supports following UX ```python class SubTool(TypedDict): """Subtool docstring""" args: Annotated[Dict[str, Any], {}, "this does bar"] class Tool(TypedDict): """Docstring Args: arg1: foo """ arg1: str arg2: Union[int, str] arg3: Optional[List[SubTool]] arg4: Annotated[Literal["bar", "baz"], ..., "this does foo"] arg5: Annotated[Optional[float], None] ``` - can parse google style docstring - can use Annotated to specify default value (second arg) - can use Annotated to specify arg description (third arg) - can have nested complex types	2 months ago
Erick Friis	88418af3f5	core: release 0.2.25 (#24833 )	2 months ago
Nuno Campos	68ecebf1ec	core: Fix implementation of trim_first_node/trim_last_node to use exact same definition of first/last node as in the getter methods (#24802 )	2 months ago
Bagatur	a6d1fb4275	core[patch]: introduce ToolMessage.status (#24628 ) Anthropic models (including via Bedrock and other cloud platforms) accept a status/is_error attribute on tool messages/results (specifically in `tool_result` content blocks for Anthropic API). Adding a ToolMessage.status attribute so that users can set this attribute when using those models	2 months ago
ccurme	9998e55936	core[patch]: support tool calls with non-pickleable args in tools (#24741 ) Deepcopy raises with non-pickleable args.	2 months ago

1 2 3 4 5 ...

742 Commits (ccff1ba8b852e6c768ffae4aa3b36d4d8e292951)