`BaseOpenAI.modelname_to_contextsize` now reads `max_input_tokens` from
the partner's model profile registry instead of a hand-maintained dict,
with a `@deprecated(since="1.2", removal="2.0")` marker steering callers
at the profile directly. The legacy mapping is trimmed to models that
have no profile (completion-only and dated chat variants) so existing
lookups keep working.
Documents the env vars that influence `base_url` resolution on
`ChatOpenAI`, `OpenAIEmbeddings`, and `BaseOpenAI`. The previous
docstrings only said "leave blank if not using a proxy or service
emulator" and did not explain that two different env vars are consulted
by two different layers.
Concretely:
- `OPENAI_API_BASE` is read explicitly by LangChain at init and passed
as `base_url` to the underlying client.
- `OPENAI_BASE_URL` is read by the underlying `openai` SDK client
itself. LangChain only inspects its presence to decide whether to
default-enable `stream_usage` (left off when set, because many
non-OpenAI endpoints do not support streaming token usage).
Precedence: explicit `base_url=` kwarg → `OPENAI_API_BASE` →
`OPENAI_BASE_URL` (via SDK fallback).
Docs-only change — no behavior change.
> AI-agent involvement: drafted by an AI agent and reviewed before
submission.
_Opened collaboratively by Mason Daugherty and open-swe._
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Mason Daugherty <61371264+mdrxy@users.noreply.github.com>
Largely:
- Remove explicit `"Default is x"` since new refs show default inferred
from sig
- Inline code (useful for eventual parsing)
- Fix code block rendering (indentations)
Ensures proper reStructuredText formatting by adding the required blank
line before closing docstring quotes, which resolves the "Block quote
ends without a blank line; unexpected unindent" warning.
- **Description:** Fix typo in code samples for max_tokens_for_prompt.
Code blocks had singular "token" but the method has plural "tokens".
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** N/A
- This pull request includes various changes to add a `user_agent`
parameter to Azure OpenAI, Azure Search and Whisper in the Community and
Partner packages. This helps in identifying the source of API requests
so we can better track usage and help support the community better. I
will also be adding the user_agent to the new `langchain-azure` repo as
well.
- No issue connected or updated dependencies.
- Utilises existing tests and docs
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
This PR introduces a new `azure_ad_async_token_provider` attribute to
the `AzureOpenAI` and `AzureChatOpenAI` classes in `partners/openai` and
`community` packages, given it's currently supported on `openai` package
as
[AsyncAzureADTokenProvider](https://github.com/openai/openai-python/blob/main/src/openai/lib/azure.py#L33)
type.
The reason for creating a new attribute is to avoid breaking changes.
Let's say you have an existing code that uses a `AzureOpenAI` or
`AzureChatOpenAI` instance to perform both sync and async operations.
The `azure_ad_token_provider` will work exactly as it is today, while
`azure_ad_async_token_provider` will override it for async requests.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
Given the current erroring behavior, every time we've moved a kwarg from
model_kwargs and made it its own field that was a breaking change.
Updating this behavior to support the old instantiations /
serializations.
Assuming build_extra_kwargs was not something that itself is being used
externally and needs to be kept backwards compatible
**Description:** Explicitly add parameters from openai API
- [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: Erick Friis <erick@langchain.dev>
- 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>
**Description:**: adding checking codes for calling AI model get error
in chat_models/base.py and llms/base.py
**Issue**: Sometimes the AI Model calling will get error, we should
raise it.
Otherwise, the next code 'choices.extend(response["choices"])' will
throw a "TypeError: 'NoneType' object is not iterable" error to mask the
true error.
Because 'response["choices"]' is None.
**Dependencies**: None
---------
Co-authored-by: yangkx <yangkx@asiainfo-int.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
**Description:** Update the docstring of OpenAI, OpenAIEmbeddings and
ChatOpenAI classes
**Issue:** Update import module paths to the current LangChain API
**Dependencies:** None
**Lint and test**: `make format` and `make lint` were run
This incorporates the review comments from langchain-ai/langchain#18637
which I closed due to an issue I had in updating that pr branch
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
