langchain

Commit Graph

Author	SHA1	Message	Date
Christophe Bornet	038c287b3a	all: Improve make lint command (#25344 ) * Removed `ruff check --select I` as `I` is already selected and checked in the main `ruff check` command * Added checks for non-empty `PYTHON_FILES` * Run `ruff check` only on `PYTHON_FILES` Co-authored-by: Erick Friis <erick@langchain.dev>	4 weeks ago
ccurme	b83f1eb0d5	core, partners: implement standard tracing params for LLMs (#25410 )	1 month ago
Eugene Yurtsev	e18511bb22	core[minor], anthropic[patch]: Upgrade @root_validator usage to be consistent with pydantic 2 (#25457 ) anthropic: Upgrade `@root_validator` usage to be consistent with pydantic 2 core: support looking up multiple keys from env in from_env factory	1 month ago
Bagatur	eec7bb4f51	anthropic[patch]: Release 0.1.23 (#25394 )	1 month ago
ZhangShenao	2c3e3dc6b1	patch[Partners] Unified fix of incorrect variable declarations in all check_imports (#25014 ) There are some incorrect declarations of variable `has_failure` in check_imports. The purpose of this PR is to uniformly fix these errors.	2 months ago
Bagatur	752a71b688	integrations[patch]: release model packages (#24900 )	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
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
Bagatur	b3a23ddf93	integration releases (#24725 ) Release anthropic, openai, groq, mistralai, robocorp	2 months ago
Erick Friis	3dce2e1d35	all: add release notes to pypi (#24519 )	2 months ago
Bagatur	236e957abb	core,groq,openai,mistralai,robocorp,fireworks,anthropic[patch]: Update BaseModel subclass and instance checks to handle both v1 and proper namespaces (#24417 ) After this PR chat models will correctly handle pydantic 2 with bind_tools and with_structured_output. ```python import pydantic print(pydantic.__version__) ``` 2.8.2 ```python from langchain_openai import ChatOpenAI from pydantic import BaseModel, Field class Add(BaseModel): x: int y: int model = ChatOpenAI().bind_tools([Add]) print(model.invoke('2 + 5').tool_calls) model = ChatOpenAI().with_structured_output(Add) print(type(model.invoke('2 + 5'))) ``` ``` [{'name': 'Add', 'args': {'x': 2, 'y': 5}, 'id': 'call_PNUFa4pdfNOYXxIMHc6ps2Do', 'type': 'tool_call'}] <class '__main__.Add'> ``` ```python from langchain_openai import ChatOpenAI from pydantic.v1 import BaseModel, Field class Add(BaseModel): x: int y: int model = ChatOpenAI().bind_tools([Add]) print(model.invoke('2 + 5').tool_calls) model = ChatOpenAI().with_structured_output(Add) print(type(model.invoke('2 + 5'))) ``` ```python [{'name': 'Add', 'args': {'x': 2, 'y': 5}, 'id': 'call_hhiHYP441cp14TtrHKx3Upg0', 'type': 'tool_call'}] <class '__main__.Add'> ``` Addresses issues: https://github.com/langchain-ai/langchain/issues/22782 --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	2 months ago
Bagatur	259d4d2029	anthropic[patch]: Release 0.1.20 (#24204 )	2 months ago
Bagatur	cb5031f22f	integrations[patch]: require core >=0.2.17 (#24207 )	2 months ago
Bagatur	5fd1e67808	core[minor], integrations...[patch]: Support ToolCall as Tool input and ToolMessage as Tool output (#24038 ) Changes: - ToolCall, InvalidToolCall and ToolCallChunk can all accept a "type" parameter now - LLM integration packages add "type" to all the above - Tool supports ToolCall inputs that have "type" specified - Tool outputs ToolMessage when a ToolCall is passed as input - Tools can separately specify ToolMessage.content and ToolMessage.raw_output - Tools emit events for validation errors (using on_tool_error and on_tool_end) Example: ```python @tool("structured_api", response_format="content_and_raw_output") def _mock_structured_tool_with_raw_output( arg1: int, arg2: bool, arg3: Optional[dict] = None ) -> Tuple[str, dict]: """A Structured Tool""" return f"{arg1} {arg2}", {"arg1": arg1, "arg2": arg2, "arg3": arg3} def test_tool_call_input_tool_message_with_raw_output() -> None: tool_call: Dict = { "name": "structured_api", "args": {"arg1": 1, "arg2": True, "arg3": {"img": "base64string..."}}, "id": "123", "type": "tool_call", } expected = ToolMessage("1 True", raw_output=tool_call["args"], tool_call_id="123") tool = _mock_structured_tool_with_raw_output actual = tool.invoke(tool_call) assert actual == expected tool_call.pop("type") with pytest.raises(ValidationError): tool.invoke(tool_call) actual_content = tool.invoke(tool_call["args"]) assert actual_content == expected.content ``` --------- Co-authored-by: Erick Friis <erick@langchain.dev>	2 months ago
Bagatur	a0c2281540	infra: update mypy 1.10, ruff 0.5 (#23721 ) ```python """python scripts/update_mypy_ruff.py""" import glob import tomllib from pathlib import Path import toml import subprocess import re ROOT_DIR = Path(__file__).parents[1] def main(): for path in glob.glob(str(ROOT_DIR / "libs/*/pyproject.toml"), recursive=True): print(path) with open(path, "rb") as f: pyproject = tomllib.load(f) try: pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = ( "^1.10" ) pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = ( "^0.5" ) except KeyError: continue with open(path, "w") as f: toml.dump(pyproject, f) cwd = "/".join(path.split("/")[:-1]) completed = subprocess.run( "poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color", cwd=cwd, shell=True, capture_output=True, text=True, ) logs = completed.stdout.split("\n") to_ignore = {} for l in logs: if re.match("^(.)\:(\d+)\: error:.\[(.)\]", l): path, line_no, error_type = re.match( "^(.)\:(\d+)\: error:.\[(.*)\]", l ).groups() if (path, line_no) in to_ignore: to_ignore[(path, line_no)].append(error_type) else: to_ignore[(path, line_no)] = [error_type] print(len(to_ignore)) for (error_path, line_no), error_types in to_ignore.items(): all_errors = ", ".join(error_types) full_path = f"{cwd}/{error_path}" try: with open(full_path, "r") as f: file_lines = f.readlines() except FileNotFoundError: continue file_lines[int(line_no) - 1] = ( file_lines[int(line_no) - 1][:-1] + f" # type: ignore[{all_errors}]\n" ) with open(full_path, "w") as f: f.write("".join(file_lines)) subprocess.run( "poetry run ruff format .; poetry run ruff --select I --fix .", cwd=cwd, shell=True, capture_output=True, text=True, ) if __name__ == "__main__": main() ```	3 months ago
Bagatur	ebb404527f	anthropic[patch]: Release 0.1.19 (#23783 )	3 months ago
Bagatur	ed200bf2c4	anthropic[patch]: expose payload (#23291 ) ![Screenshot 2024-06-21 at 4 56 02 PM](https://github.com/langchain-ai/langchain/assets/22008038/a2c6224f-3741-4502-9607-1a726a0551c9)	3 months ago
ccurme	7c1cddf1b7	anthropic[patch]: release 0.1.18 (#23778 )	3 months ago
ccurme	c9dac59008	anthropic[patch]: fix model name in some integration tests (#23779 )	3 months ago
Bagatur	7a6c06cadd	anthropic[patch]: tool output parser fix (#23647 )	3 months ago
ccurme	46cbf0e4aa	anthropic[patch]: use core output parsers for structured output (#23776 ) Also add to standard tests for structured output.	3 months ago
kiarina	dc396835ed	langchain_anthropic: add stop_reason in ChatAnthropic stream result (#23689 ) `ChatAnthropic` can get `stop_reason` from the resulting `AIMessage` in `invoke` and `ainvoke`, but not in `stream` and `astream`. This is a different behavior from `ChatOpenAI`. It is possible to get `stop_reason` from `stream` as well, since it is needed to determine the next action after the LLM call. This would be easier to handle in situations where only `stop_reason` is needed. - Issue: NA - Dependencies: NA - Twitter handle: https://x.com/kiarina37	3 months ago
Bagatur	389a568f9a	standard-tests[patch]: add anthropic format integration test (#23717 )	3 months ago
Bagatur	b63c7f10bc	anthropic[patch]: Release 0.1.17 (#23650 )	3 months ago
Bagatur	fc8fd49328	openai, anthropic, ...: with_structured_output to pass in explicit tool choice (#23645 ) ...community, mistralai, groq, fireworks part of #23644	3 months ago
Bagatur	a7ab93479b	anthropic[patch]: Release 0.1.16 (#23549 )	3 months ago
Bagatur	93d0ad97fe	anthropic[patch]: test image input (#23155 )	3 months ago
Leonid Ganeline	3dfd055411	anthropic: docstrings (#23145 ) Added missed docstrings. Format docstrings to the consistent format (used in the API Reference)	3 months ago
Bagatur	90559fde70	openai[patch], standard-tests[patch]: don't pass in falsey stop vals (#23153 ) adds an image input test to standard-tests as well	3 months ago
Bagatur	d96f67b06f	standard-tests[patch]: Update chat model standard tests (#22378 ) - Refactor standard test classes to make them easier to configure - Update openai to support stop_sequences init param - Update groq to support stop_sequences init param - Update fireworks to support max_retries init param - Update ChatModel.bind_tools to type tool_choice - Update groq to handle tool_choice="any". this may be controversial --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	3 months ago
Jacob Lee	181a61982f	anthropic[minor]: Adds streaming tool call support for Anthropic (#22687 ) Preserves string content chunks for non tool call requests for convenience. One thing - Anthropic events look like this: ``` RawContentBlockStartEvent(content_block=TextBlock(text='', type='text'), index=0, type='content_block_start') RawContentBlockDeltaEvent(delta=TextDelta(text='<thinking>\nThe', type='text_delta'), index=0, type='content_block_delta') RawContentBlockDeltaEvent(delta=TextDelta(text=' provide', type='text_delta'), index=0, type='content_block_delta') ... RawContentBlockStartEvent(content_block=ToolUseBlock(id='toolu_01GJ6x2ddcMG3psDNNe4eDqb', input={}, name='get_weather', type='tool_use'), index=1, type='content_block_start') RawContentBlockDeltaEvent(delta=InputJsonDelta(partial_json='', type='input_json_delta'), index=1, type='content_block_delta') ``` Note that `delta` has a `type` field. With this implementation, I'm dropping it because `merge_list` behavior will concatenate strings. We currently have `index` as a special field when merging lists, would it be worth adding `type` too? If so, what do we set as a context block chunk? `text` vs. `text_delta`/`tool_use` vs `input_json_delta`? CC @ccurme @efriis @baskaryan	3 months ago
ccurme	73c76b9628	anthropic[patch]: always add tool_result type to ToolMessage content (#22721 ) Anthropic tool results can contain image data, which are typically represented with content blocks having `"type": "image"`. Currently, these content blocks are passed as-is as human/user messages to Anthropic, which raises BadRequestError as it expects a tool_result block to follow a tool_use. Here we update ChatAnthropic to nest the content blocks inside a tool_result content block. Example: ```python import base64 import httpx from langchain_anthropic import ChatAnthropic from langchain_core.messages import AIMessage, HumanMessage, ToolMessage from langchain_core.pydantic_v1 import BaseModel, Field # Fetch image image_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" image_data = base64.b64encode(httpx.get(image_url).content).decode("utf-8") class FetchImage(BaseModel): should_fetch: bool = Field(..., description="Whether an image is requested.") llm = ChatAnthropic(model="claude-3-sonnet-20240229").bind_tools([FetchImage]) messages = [ HumanMessage(content="Could you summon a beautiful image please?"), AIMessage( content=[ { "type": "tool_use", "id": "toolu_01Rn6Qvj5m7955x9m9Pfxbcx", "name": "FetchImage", "input": {"should_fetch": True}, }, ], tool_calls=[ { "name": "FetchImage", "args": {"should_fetch": True}, "id": "toolu_01Rn6Qvj5m7955x9m9Pfxbcx", }, ], ), ToolMessage( name="FetchImage", content=[ { "type": "image", "source": { "type": "base64", "media_type": "image/jpeg", "data": image_data, }, }, ], tool_call_id="toolu_01Rn6Qvj5m7955x9m9Pfxbcx", ), ] llm.invoke(messages) ``` Trace: https://smith.langchain.com/public/d27e4fc1-a96d-41e1-9f52-54f5004122db/r	3 months ago
ccurme	f32d57f6f0	anthropic: refactor streaming to use events api; add streaming usage metadata (#22628 ) - Refactor streaming to use raw events; - Add `stream_usage` class attribute and kwarg to stream methods that, if True, will include separate chunks in the stream containing usage metadata. There are two ways to implement streaming with anthropic's python sdk. They have slight differences in how they surface usage metadata. 1. [Use helper functions](https://github.com/anthropics/anthropic-sdk-python?tab=readme-ov-file#streaming-helpers). This is what we are doing now. ```python count = 1 with client.messages.stream(params) as stream: for text in stream.text_stream: snapshot = stream.current_message_snapshot print(f"{count}: {snapshot.usage} -- {text}") count = count + 1 final_snapshot = stream.get_final_message() print(f"{count}: {final_snapshot.usage}") ``` ``` 1: Usage(input_tokens=8, output_tokens=1) -- Hello 2: Usage(input_tokens=8, output_tokens=1) -- ! 3: Usage(input_tokens=8, output_tokens=1) -- How 4: Usage(input_tokens=8, output_tokens=1) -- can 5: Usage(input_tokens=8, output_tokens=1) -- I 6: Usage(input_tokens=8, output_tokens=1) -- assist 7: Usage(input_tokens=8, output_tokens=1) -- you 8: Usage(input_tokens=8, output_tokens=1) -- today 9: Usage(input_tokens=8, output_tokens=1) -- ? 10: Usage(input_tokens=8, output_tokens=12) ``` To do this correctly, we need to emit a new chunk at the end of the stream containing the usage metadata. 2. [Handle raw events](https://github.com/anthropics/anthropic-sdk-python?tab=readme-ov-file#streaming-responses) ```python stream = client.messages.create(params, stream=True) count = 1 for event in stream: print(f"{count}: {event}") count = count + 1 ``` ``` 1: RawMessageStartEvent(message=Message(id='msg_01Vdyov2kADZTXqSKkfNJXcS', content=[], model='claude-3-haiku-20240307', role='assistant', stop_reason=None, stop_sequence=None, type='message', usage=Usage(input_tokens=8, output_tokens=1)), type='message_start') 2: RawContentBlockStartEvent(content_block=TextBlock(text='', type='text'), index=0, type='content_block_start') 3: RawContentBlockDeltaEvent(delta=TextDelta(text='Hello', type='text_delta'), index=0, type='content_block_delta') 4: RawContentBlockDeltaEvent(delta=TextDelta(text='!', type='text_delta'), index=0, type='content_block_delta') 5: RawContentBlockDeltaEvent(delta=TextDelta(text=' How', type='text_delta'), index=0, type='content_block_delta') 6: RawContentBlockDeltaEvent(delta=TextDelta(text=' can', type='text_delta'), index=0, type='content_block_delta') 7: RawContentBlockDeltaEvent(delta=TextDelta(text=' I', type='text_delta'), index=0, type='content_block_delta') 8: RawContentBlockDeltaEvent(delta=TextDelta(text=' assist', type='text_delta'), index=0, type='content_block_delta') 9: RawContentBlockDeltaEvent(delta=TextDelta(text=' you', type='text_delta'), index=0, type='content_block_delta') 10: RawContentBlockDeltaEvent(delta=TextDelta(text=' today', type='text_delta'), index=0, type='content_block_delta') 11: RawContentBlockDeltaEvent(delta=TextDelta(text='?', type='text_delta'), index=0, type='content_block_delta') 12: RawContentBlockStopEvent(index=0, type='content_block_stop') 13: RawMessageDeltaEvent(delta=Delta(stop_reason='end_turn', stop_sequence=None), type='message_delta', usage=MessageDeltaUsage(output_tokens=12)) 14: RawMessageStopEvent(type='message_stop') ``` Here we implement the second option, in part because it should make things easier when implementing streaming tool calls in the near future. This would add two new chunks to the stream-- one at the beginning and one at the end-- with blank content and containing usage metadata. We add kwargs to the stream methods and a class attribute allowing for this behavior to be toggled. I enabled it by default. If we merge this we can add the same kwargs / attribute to OpenAI. Usage: ```python from langchain_anthropic import ChatAnthropic model = ChatAnthropic( model="claude-3-haiku-20240307", temperature=0 ) full = None for chunk in model.stream("hi"): full = chunk if full is None else full + chunk print(chunk) print(f"\nFull: {full}") ``` ``` content='' id='run-8a20843f-25c7-4025-ad72-9add395899e3' usage_metadata={'input_tokens': 8, 'output_tokens': 0, 'total_tokens': 8} content='Hello' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content='!' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content=' How' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content=' can' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content=' I' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content=' assist' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content=' you' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content=' today' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content='?' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content='' id='run-8a20843f-25c7-4025-ad72-9add395899e3' usage_metadata={'input_tokens': 0, 'output_tokens': 12, 'total_tokens': 12} Full: content='Hello! How can I assist you today?' id='run-8a20843f-25c7-4025-ad72-9add395899e3' usage_metadata={'input_tokens': 8, 'output_tokens': 12, 'total_tokens': 20} ```	4 months ago
ccurme	c1ef731503	anthropic: update attribute name and alias (#22625 ) update name to `stop_sequences` and alias to `stop` (instead of the other way around), since `stop_sequences` is the name used by anthropic.	4 months ago
ccurme	3999761201	multiple: add `stop` attribute (#22573 )	4 months ago
ccurme	e08879147b	Revert "anthropic: stream token usage" (#22624 ) Reverts langchain-ai/langchain#20180	4 months ago
Bagatur	0d495f3f63	anthropic: stream token usage (#20180 ) open to other ideas <img width="1181" alt="Screenshot 2024-04-08 at 5 34 08 PM" src="https://github.com/langchain-ai/langchain/assets/22008038/03eb11c4-5eb5-43e3-9109-a13f76098fa4"> --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	4 months ago
Bagatur	cb183a9bf1	docs: update anthropic chat model (#22483 ) Related to #22296 And update anthropic to accept base_url	4 months ago
Bagatur	678a19a5f7	infra: bump anthropic mypy 1 (#22373 )	4 months ago
Bagatur	a8098f5ddb	anthropic[patch]: Release 0.1.15, fix sdk tools break (#22369 )	4 months ago
Erick Friis	42ffcb2ff1	anthropic: release 0.1.14rc2, test release note gen (#22147 )	4 months ago
Bagatur	baa3c975cb	anthropic[patch]: allow tool call mutation (#22130 ) If tool_use blocks and tool_calls with overlapping IDs are present, prefer the values of the tool_calls. Allows for mutating AIMessages just via tool_calls.	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	152c8cac33	anthropic, openai: cut pre-releases (#22083 )	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
ccurme	4be5537837	Revert "anthropic: set default model" (#21987 ) Reverts langchain-ai/langchain#21986	4 months ago
ccurme	35439cf3bd	anthropic: set default model (#21986 ) Various docs reference `ChatAnthropic()`, but this currently raises ValidationError.	4 months ago
ccurme	4470d3b4a0	partners: bump core in packages implementing ls_params (#21868 ) These packages all import `LangSmithParams` which was released in langchain-core==0.2.0. N.B. we will need to release `openai` and then bump `langchain-openai` in `together` and `upstage`.	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

1 2 3

110 Commits (09c2d8faca42f09a924599c9d75cc38e05ba1ad4)