langchain

Commit Graph

Author	SHA1	Message	Date
Bagatur	8698cb9b28	infra: add more formatter rules to openai (#23189 ) Turns on https://docs.astral.sh/ruff/settings/#format_docstring-code-format and https://docs.astral.sh/ruff/settings/#format_skip-magic-trailing-comma ```toml [tool.ruff.format] docstring-code-format = true skip-magic-trailing-comma = true ```	3 months ago
Bagatur	0a4ee864e9	openai[patch]: image token counting (#23147 ) Resolves #23000 --------- Co-authored-by: isaac hershenson <ihershenson@hmc.edu> Co-authored-by: ccurme <chester.curme@gmail.com>	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
ccurme	722c8f50ea	openai[patch]: add stream_usage parameter (#22854 ) Here we add `stream_usage` to ChatOpenAI as: 1. a boolean attribute 2. a kwarg to _stream and _astream. Question: should the `stream_usage` attribute be `bool`, or `bool \| None`? Currently I've kept it `bool` and defaulted to False. It was implemented on [ChatAnthropic](`e832bbb486/libs/partners/anthropic/langchain_anthropic/chat_models.py (L535)`) as a bool. However, to maintain support for users who access the behavior via OpenAI's `stream_options` param, this ends up being possible: ```python llm = ChatOpenAI(model_kwargs={"stream_options": {"include_usage": True}}) assert not llm.stream_usage ``` (and this model will stream token usage). Some options for this: - it's ok - make the `stream_usage` attribute bool or None - make an \_\_init\_\_ for ChatOpenAI, set a `._stream_usage` attribute and read `.stream_usage` from a property Open to other ideas as well.	3 months ago
Hakan Özdemir	c437b1aab7	[Partner]: Add metadata to stream response (#22716 ) Adds `response_metadata` to stream responses from OpenAI. This is returned with `invoke` normally, but wasn't implemented for `stream`. --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	3 months ago
ccurme	af1f723ada	openai: don't override stream_options default (#22242 ) ChatOpenAI supports a kwarg `stream_options` which can take values `{"include_usage": True}` and `{"include_usage": False}`. Setting include_usage to True adds a message chunk to the end of the stream with usage_metadata populated. In this case the final chunk no longer includes `"finish_reason"` in the `response_metadata`. This is the current default and is not yet released. Because this could be disruptive to workflows, here we remove this default. The default will now be consistent with OpenAI's API (see parameter [here](https://platform.openai.com/docs/api-reference/chat/create#chat-create-stream_options)). Examples: ```python from langchain_openai import ChatOpenAI llm = ChatOpenAI() for chunk in llm.stream("hi"): print(chunk) ``` ``` content='' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92' content='Hello' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92' content='!' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92' content='' response_metadata={'finish_reason': 'stop'} id='run-8cff4721-2acd-4551-9bf7-1911dae46b92' ``` ```python for chunk in llm.stream("hi", stream_options={"include_usage": True}): print(chunk) ``` ``` content='' id='run-39ab349b-f954-464d-af6e-72a0927daa27' content='Hello' id='run-39ab349b-f954-464d-af6e-72a0927daa27' content='!' id='run-39ab349b-f954-464d-af6e-72a0927daa27' content='' response_metadata={'finish_reason': 'stop'} id='run-39ab349b-f954-464d-af6e-72a0927daa27' content='' id='run-39ab349b-f954-464d-af6e-72a0927daa27' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17} ``` ```python llm = ChatOpenAI().bind(stream_options={"include_usage": True}) for chunk in llm.stream("hi"): print(chunk) ``` ``` content='' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' content='Hello' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' content='!' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' content='' response_metadata={'finish_reason': 'stop'} id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' content='' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17} ```	4 months ago
ccurme	9a010fb761	openai: read stream_options (#21548 ) OpenAI recently added a `stream_options` parameter to its chat completions API (see [release notes](https://platform.openai.com/docs/changelog/added-chat-completions-stream-usage)). When this parameter is set to `{"usage": True}`, an extra "empty" message is added to the end of a stream containing token usage. Here we propagate token usage to `AIMessage.usage_metadata`. We enable this feature by default. Streams would now include an extra chunk at the end, after the chunk with `response_metadata={'finish_reason': 'stop'}`. New behavior: ``` [AIMessageChunk(content='', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'), AIMessageChunk(content='Hello', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'), AIMessageChunk(content='!', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'), AIMessageChunk(content='', response_metadata={'finish_reason': 'stop'}, id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'), AIMessageChunk(content='', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde', usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17})] ``` Old behavior (accessible by passing `stream_options={"include_usage": False}` into (a)stream: ``` [AIMessageChunk(content='', id='run-1312b971-c5ea-4d92-9015-e6604535f339'), AIMessageChunk(content='Hello', id='run-1312b971-c5ea-4d92-9015-e6604535f339'), AIMessageChunk(content='!', id='run-1312b971-c5ea-4d92-9015-e6604535f339'), AIMessageChunk(content='', response_metadata={'finish_reason': 'stop'}, id='run-1312b971-c5ea-4d92-9015-e6604535f339')] ``` From what I can tell this is not yet implemented in Azure, so we enable only for ChatOpenAI.	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	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
ccurme	4170e72a42	openai: fix loads unit test (#21542 ) following changes to tests in core here: https://github.com/langchain-ai/langchain/pull/21342/files	4 months ago
Bagatur	6ac6158a07	openai[patch]: support tool_choice="required" (#21216 ) Co-authored-by: ccurme <chester.curme@gmail.com>	5 months ago
Bagatur	6fa8626e2f	openai[patch]: fix azure open lc serialization, release 0.1.5 (#21159 )	5 months ago
aditya thomas	12b1caf295	openai[patch]: add tests for secret_str for keys (#20982 ) Description: Add tests to check API keys and Active Directory tokens are masked Issue: Resolves #12165 for OpenAI and Azure OpenAI models Dependencies: None Also resolves #12473 which may be closed. Additional contributors @alex4321 (#12473) and @onesolpark (#12542)	5 months ago
Bagatur	bef50ded63	openai[patch]: fix special token default behavior (#21131 ) By default handle special sequences as regular text	5 months ago
ccurme	fe1304afc4	openai: add unit test (#20931 ) Test a helper function that was added earlier.	5 months ago
ccurme	fdabd3cdf5	mistral, openai: support custom tokenizers in chat models (#20901 )	5 months ago
ccurme	481d3855dc	patch: remove usage of llm, chat model __call__ (#20788 ) - `llm(prompt)` -> `llm.invoke(prompt)` - `llm(prompt=prompt` -> `llm.invoke(prompt)` (same with `messages=`) - `llm(prompt, callbacks=callbacks)` -> `llm.invoke(prompt, config={"callbacks": callbacks})` - `llm(prompt, kwargs)` -> `llm.invoke(prompt, kwargs)`	5 months ago
ccurme	7a922f3e48	core, openai: support custom token encoders (#20762 )	5 months ago
ccurme	22da9f5f3f	update scheduled tests (#20526 ) repurpose scheduled tests to test over provider packages	5 months ago
Bagatur	c706689413	openai[patch]: use tool_calls in request (#20272 )	5 months ago
Yuki Oshima	12190ad728	openai[patch]: Fix langchain-openai unknown parameter error with gpt-4-turbo (#20271 ) Description: I fixed langchain-openai unknown parameter error with gpt-4-turbo. It seems that the behavior of the Chat Completions API implicitly changed when using the latest gpt-4-turbo model, differing from previous models. It now appears to reject parameters that are not listed in the [API Reference](https://platform.openai.com/docs/api-reference/chat/create). So I found some errors and fixed them. Issue: https://github.com/langchain-ai/langchain/issues/20264 Dependencies: none Twitter handle: https://twitter.com/oshima_123	5 months ago
Bagatur	9514bc4d67	core[minor], ...: add tool calls message (#18947 ) core[minor], langchain[patch], openai[minor], anthropic[minor], fireworks[minor], groq[minor], mistralai[minor] ```python class ToolCall(TypedDict): name: str args: Dict[str, Any] id: Optional[str] class InvalidToolCall(TypedDict): name: Optional[str] args: Optional[str] id: Optional[str] error: Optional[str] class ToolCallChunk(TypedDict): name: Optional[str] args: Optional[str] id: Optional[str] index: Optional[int] class AIMessage(BaseMessage): ... tool_calls: List[ToolCall] = [] invalid_tool_calls: List[InvalidToolCall] = [] ... class AIMessageChunk(AIMessage, BaseMessageChunk): ... tool_call_chunks: Optional[List[ToolCallChunk]] = None ... ``` Important considerations: - Parsing logic occurs within different providers; - ~Changing output type is a breaking change for anyone doing explicit type checking;~ - ~Langsmith rendering will need to be updated: https://github.com/langchain-ai/langchainplus/pull/3561~ - ~Langserve will need to be updated~ - Adding chunks: - ~AIMessage + ToolCallsMessage = ToolCallsMessage if either has non-null .tool_calls.~ - Tool call chunks are appended, merging when having equal values of `index`. - additional_kwargs accumulate the normal way. - During streaming: - ~Messages can change types (e.g., from AIMessageChunk to AIToolCallsMessageChunk)~ - Output parsers parse additional_kwargs (during .invoke they read off tool calls). Packages outside of `partners/`: - https://github.com/langchain-ai/langchain-cohere/pull/7 - https://github.com/langchain-ai/langchain-google/pull/123/files --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	6 months ago
Erick Friis	855ba46f80	standard-tests: a standard unit and integration test set (#20182 ) just chat models for now	6 months ago
Erick Friis	be92cf57ca	openai[patch]: fix azure embedding length check (#19870 )	6 months ago
Shuqian	332996b4b2	openai[patch]: fix ChatOpenAI model's openai proxy (#19559 ) Due to changes in the OpenAI SDK, the previous method of setting the OpenAI proxy in ChatOpenAI no longer works. This PR fixes this issue, making the previous way of setting the OpenAI proxy in ChatOpenAI effective again. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Bagatur	d93d49bc43	openai[patch]: tool use integration test (#19460 )	6 months ago
Erick Friis	a99e644913	openai[patch]: integration test structured output (#19459 )	6 months ago
Luca Dorigo	47cfbe7522	openai[patch]: [URGENT REGRESSION FIX] Don't fail if tool message already doesn't contain name (#19435 ) - [ ] 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. --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Erick Friis	69e9610f62	openai[patch]: pass message name (#17537 )	6 months ago
Jacob Lee	bd329e9aad	core[patch]: Add LLM output to message response_metadata (#19158 ) This will more easily expose token usage information. CC @baskaryan --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Bagatur	e0e688a277	core[minor]: generation info on msg (#18592 ) related to #16403 #17188	6 months ago
aditya thomas	e00c1ff2b0	infra: ChatOpenAI unit tests for invoke() and ainvoke() (#18792 ) Description: Replacing the deprecated predict() and apredict() methods in the unit tests Issue: Not applicable Dependencies: None Lint and test: `make format`, `make lint` and `make test` have been run	7 months ago
Erick Friis	687d27567d	openai[patch]: unit test azure init (#18703 )	7 months ago
Erick Friis	a05fb19f42	openai[patch]: remove numpy dep (#18034 )	7 months ago
Bagatur	35446c814e	openai[patch]: rm tiktoken model warning (#16964 )	8 months ago
Erick Friis	bb3b6bde33	openai[minor]: change to secretstr (#16803 )	8 months ago
Bagatur	61e876aad8	openai[patch]: Explicitly support embedding dimensions (#16596 )	8 months ago
Bagatur	84bf5787a7	core[patch], openai[patch]: Chat openai stream logprobs (#16218 )	8 months ago
Erick Friis	91ec9da534	openai[patch]: unit test load (#15624 )	9 months ago
Erick Friis	ebc75c5ca7	openai[minor]: implement langchain-openai package (#15503 ) Todo - [x] copy over integration tests - [x] update docs with new instructions in #15513 - [x] add linear ticket to bump core -> community, community->langchain, and core->openai deps - [ ] (optional): add `pip install langchain-openai` command to each notebook using it - [x] Update docstrings to not need `openai` install - [x] Add serialization - [x] deprecate old models Contributor steps: - [x] Add secret names to manual integrations workflow in .github/workflows/_integration_test.yml - [x] Add secrets to release workflow (for pre-release testing) in .github/workflows/_release.yml Maintainer steps (Contributors should not do these): - [x] set up pypi and test pypi projects - [x] add credential secrets to Github Actions - [ ] add package to conda-forge Functional changes to existing classes: - now relies on openai client v1 (1.6.1) via concrete dep in langchain-openai package Codebase organization - some function calling stuff moved to `langchain_core.utils.function_calling` in order to be used in both community and langchain-openai	9 months ago

41 Commits (9b3a025f9c806a6f8a00030c7058c689536ae5a0)