github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2026-06-09 10:17:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

style: some cleanup (#33857)

Browse Source
This commit is contained in:
Mason Daugherty
2025-11-06 23:50:46 -05:00
committed by GitHub
parent d40e340479
commit e023201d42
79 changed files with 662 additions and 531 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
libs/partners/openai/langchain_openai/chat_models/azure.py
View File

@@ -837,10 +837,10 @@ class AzureChatOpenAI(BaseChatOpenAI):
Args:
schema: The output schema. Can be passed in as:
- a JSON Schema,
- a `TypedDict` class,
- a Pydantic class,
- or an OpenAI function/tool schema.
- A JSON Schema,
- A `TypedDict` class,
- A Pydantic class,
- Or an OpenAI function/tool schema.
If `schema` is a Pydantic class then the model output will be a
Pydantic instance of that class, and the model-generated fields will be
@@ -869,11 +869,15 @@ class AzureChatOpenAI(BaseChatOpenAI):
support which methods [here](https://platform.openai.com/docs/guides/structured-outputs/function-calling-vs-response-format).
include_raw:
If `False` then only the parsed structured output is returned. If
an error occurs during model output parsing it will be raised. If `True`
then both the raw model response (a `BaseMessage`) and the parsed model
response will be returned. If an error occurs during output parsing it
will be caught and returned as well.
If `False` then only the parsed structured output is returned.
If an error occurs during model output parsing it will be raised.
If `True` then both the raw model response (a `BaseMessage`) and the
parsed model response will be returned.
If an error occurs during output parsing it will be caught and returned
as well.
The final output is always a `dict` with keys `'raw'`, `'parsed'`, and
`'parsing_error'`.

78
libs/partners/openai/langchain_openai/chat_models/base.py
View File

@@ -463,16 +463,23 @@ _DictOrPydantic: TypeAlias = dict | _BM
class BaseChatOpenAI(BaseChatModel):
"""Base wrapper around OpenAI large language models for chat."""
client: Any = Field(default=None, exclude=True) #: :meta private:
async_client: Any = Field(default=None, exclude=True) #: :meta private:
root_client: Any = Field(default=None, exclude=True) #: :meta private:
root_async_client: Any = Field(default=None, exclude=True) #: :meta private:
client: Any = Field(default=None, exclude=True)
async_client: Any = Field(default=None, exclude=True)
root_client: Any = Field(default=None, exclude=True)
root_async_client: Any = Field(default=None, exclude=True)
model_name: str = Field(default="gpt-3.5-turbo", alias="model")
"""Model name to use."""
temperature: float | None = None
"""What sampling temperature to use."""
model_kwargs: dict[str, Any] = Field(default_factory=dict)
"""Holds any model parameters valid for `create` call not explicitly specified."""
openai_api_key: (
SecretStr | None | Callable[[], str] | Callable[[], Awaitable[str]]
) = Field(
@@ -524,19 +531,24 @@ class BaseChatOpenAI(BaseChatModel):
model = ChatOpenAI(model="gpt-5-nano", api_key=get_api_key)
```
"""
openai_api_base: str | None = Field(default=None, alias="base_url")
"""Base URL path for API requests, leave blank if not using a proxy or service emulator.""" # noqa: E501
openai_organization: str | None = Field(default=None, alias="organization")
"""Automatically inferred from env var `OPENAI_ORG_ID` if not provided."""
# to support explicit proxy for OpenAI
openai_proxy: str | None = Field(
default_factory=from_env("OPENAI_PROXY", default=None)
)
request_timeout: float | tuple[float, float] | Any | None = Field(
default=None, alias="timeout"
)
"""Timeout for requests to OpenAI completion API. Can be float, `httpx.Timeout` or
`None`."""
stream_usage: bool | None = None
"""Whether to include usage metadata in streaming output. If enabled, an additional
message chunk will be generated during the stream including usage metadata.
@@ -550,30 +562,42 @@ class BaseChatOpenAI(BaseChatModel):
!!! warning "Behavior changed in `langchain-openai` 0.3.35"
Enabled for default base URL and client.
"""
max_retries: int | None = None
"""Maximum number of retries to make when generating."""
presence_penalty: float | None = None
"""Penalizes repeated tokens."""
frequency_penalty: float | None = None
"""Penalizes repeated tokens according to frequency."""
seed: int | None = None
"""Seed for generation"""
logprobs: bool | None = None
"""Whether to return logprobs."""
top_logprobs: int | None = None
"""Number of most likely tokens to return at each token position, each with an
associated log probability. `logprobs` must be set to true if this parameter is
used."""
logit_bias: dict[int, int] | None = None
"""Modify the likelihood of specified tokens appearing in the completion."""
streaming: bool = False
"""Whether to stream the results or not."""
n: int | None = None
"""Number of chat completions to generate for each prompt."""
top_p: float | None = None
"""Total probability mass of tokens to consider at each step."""
max_tokens: int | None = Field(default=None)
"""Maximum number of tokens to generate."""
reasoning_effort: str | None = None
"""Constrains effort on reasoning for reasoning models. For use with the Chat
Completions API.
@@ -584,6 +608,7 @@ class BaseChatOpenAI(BaseChatModel):
`'high'`. Reducing reasoning effort can result in faster responses and fewer
tokens used on reasoning in a response.
"""
reasoning: dict[str, Any] | None = None
"""Reasoning parameters for reasoning models. For use with the Responses API.
@@ -596,6 +621,7 @@ class BaseChatOpenAI(BaseChatModel):
!!! version-added "Added in `langchain-openai` 0.3.24"
"""
verbosity: str | None = None
"""Controls the verbosity level of responses for reasoning models. For use with the
Responses API.
@@ -604,6 +630,7 @@ class BaseChatOpenAI(BaseChatModel):
!!! version-added "Added in `langchain-openai` 0.3.28"
"""
tiktoken_model_name: str | None = None
"""The model name to pass to tiktoken when using this class.
Tiktoken is used to count the number of tokens in documents to constrain
@@ -614,19 +641,25 @@ class BaseChatOpenAI(BaseChatModel):
when using one of the many model providers that expose an OpenAI-like
API but with different models. In those cases, in order to avoid erroring
when tiktoken is called, you can specify a model name to use here."""
default_headers: Mapping[str, str] | None = None
default_query: Mapping[str, object] | None = None
# Configure a custom httpx client. See the
# [httpx documentation](https://www.python-httpx.org/api/#client) for more details.
http_client: Any | None = Field(default=None, exclude=True)
"""Optional `httpx.Client`. Only used for sync invocations. Must specify
`http_async_client` as well if you'd like a custom client for async invocations.
"""
http_async_client: Any | None = Field(default=None, exclude=True)
"""Optional `httpx.AsyncClient`. Only used for async invocations. Must specify
`http_client` as well if you'd like a custom client for sync invocations."""
stop: list[str] | str | None = Field(default=None, alias="stop_sequences")
"""Default stop sequences."""
extra_body: Mapping[str, Any] | None = None
"""Optional additional JSON properties to include in the request parameters when
making requests to OpenAI compatible APIs, such as vLLM, LM Studio, or other
@@ -649,6 +682,7 @@ class BaseChatOpenAI(BaseChatModel):
include_response_headers: bool = False
"""Whether to include response headers in the output message `response_metadata`."""
disabled_params: dict[str, Any] | None = Field(default=None)
"""Parameters of the OpenAI client or `chat.completions` endpoint that should be
disabled for the given model.
@@ -1823,10 +1857,10 @@ class BaseChatOpenAI(BaseChatModel):
Args:
schema: The output schema. Can be passed in as:
- an OpenAI function/tool schema,
- a JSON Schema,
- a `TypedDict` class,
- or a Pydantic class.
- An OpenAI function/tool schema,
- A JSON Schema,
- A `TypedDict` class,
- Or a Pydantic class.
If `schema` is a Pydantic class then the model output will be a
Pydantic instance of that class, and the model-generated fields will be
@@ -1850,11 +1884,15 @@ class BaseChatOpenAI(BaseChatModel):
formatting the output into the desired schema into the model call
include_raw:
If `False` then only the parsed structured output is returned. If
an error occurs during model output parsing it will be raised. If `True`
then both the raw model response (a `BaseMessage`) and the parsed model
response will be returned. If an error occurs during output parsing it
will be caught and returned as well.
If `False` then only the parsed structured output is returned.
If an error occurs during model output parsing it will be raised.
If `True` then both the raw model response (a `BaseMessage`) and the
parsed model response will be returned.
If an error occurs during output parsing it will be caught and returned
as well.
The final output is always a `dict` with keys `'raw'`, `'parsed'`, and
`'parsing_error'`.
@@ -2957,11 +2995,15 @@ class ChatOpenAI(BaseChatOpenAI): # type: ignore[override]
Learn more about the [differences between methods](https://platform.openai.com/docs/guides/structured-outputs/function-calling-vs-response-format).
include_raw:
If `False` then only the parsed structured output is returned. If
an error occurs during model output parsing it will be raised. If `True`
then both the raw model response (a `BaseMessage`) and the parsed model
response will be returned. If an error occurs during output parsing it
will be caught and returned as well.
If `False` then only the parsed structured output is returned.
If an error occurs during model output parsing it will be raised.
If `True` then both the raw model response (a `BaseMessage`) and the
parsed model response will be returned.
If an error occurs during output parsing it will be caught and returned
as well.
The final output is always a `dict` with keys `'raw'`, `'parsed'`, and
`'parsing_error'`.

34
libs/partners/openai/langchain_openai/embeddings/base.py
View File

@@ -159,44 +159,55 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
```
"""
client: Any = Field(default=None, exclude=True) #: :meta private:
async_client: Any = Field(default=None, exclude=True) #: :meta private:
client: Any = Field(default=None, exclude=True)
async_client: Any = Field(default=None, exclude=True)
model: str = "text-embedding-ada-002"
dimensions: int | None = None
"""The number of dimensions the resulting output embeddings should have.
Only supported in `text-embedding-3` and later models.
"""
# to support Azure OpenAI Service custom deployment names
deployment: str | None = model
# TODO: Move to AzureOpenAIEmbeddings.
openai_api_version: str | None = Field(
default_factory=from_env("OPENAI_API_VERSION", default=None),
alias="api_version",
)
"""Automatically inferred from env var `OPENAI_API_VERSION` if not provided."""
# to support Azure OpenAI Service custom endpoints
openai_api_base: str | None = Field(
alias="base_url", default_factory=from_env("OPENAI_API_BASE", default=None)
)
"""Base URL path for API requests, leave blank if not using a proxy or service
emulator."""
# to support Azure OpenAI Service custom endpoints
openai_api_type: str | None = Field(
default_factory=from_env("OPENAI_API_TYPE", default=None)
)
# to support explicit proxy for OpenAI
openai_proxy: str | None = Field(
default_factory=from_env("OPENAI_PROXY", default=None)
)
embedding_ctx_length: int = 8191
"""The maximum number of tokens to embed at once."""
openai_api_key: (
SecretStr | None | Callable[[], str] | Callable[[], Awaitable[str]]
) = Field(
alias="api_key", default_factory=secret_from_env("OPENAI_API_KEY", default=None)
)
"""Automatically inferred from env var `OPENAI_API_KEY` if not provided."""
openai_organization: str | None = Field(
alias="organization",
default_factory=from_env(
@@ -204,21 +215,29 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
),
)
"""Automatically inferred from env var `OPENAI_ORG_ID` if not provided."""
allowed_special: Literal["all"] | set[str] | None = None
disallowed_special: Literal["all"] | set[str] | Sequence[str] | None = None
chunk_size: int = 1000
"""Maximum number of texts to embed in each batch"""
max_retries: int = 2
"""Maximum number of retries to make when generating."""
request_timeout: float | tuple[float, float] | Any | None = Field(
default=None, alias="timeout"
)
"""Timeout for requests to OpenAI completion API. Can be float, `httpx.Timeout` or
None."""
headers: Any = None
tiktoken_enabled: bool = True
"""Set this to False for non-OpenAI implementations of the embeddings API, e.g.
the `--extensions openai` extension for `text-generation-webui`"""
tiktoken_model_name: str | None = None
"""The model name to pass to tiktoken when using this class.
Tiktoken is used to count the number of tokens in documents to constrain
@@ -229,28 +248,39 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
when using one of the many model providers that expose an OpenAI-like
API but with different models. In those cases, in order to avoid erroring
when tiktoken is called, you can specify a model name to use here."""
show_progress_bar: bool = False
"""Whether to show a progress bar when embedding."""
model_kwargs: dict[str, Any] = Field(default_factory=dict)
"""Holds any model parameters valid for `create` call not explicitly specified."""
skip_empty: bool = False
"""Whether to skip empty strings when embedding or raise an error."""
default_headers: Mapping[str, str] | None = None
default_query: Mapping[str, object] | None = None
# Configure a custom httpx client. See the
# [httpx documentation](https://www.python-httpx.org/api/#client) for more details.
retry_min_seconds: int = 4
"""Min number of seconds to wait between retries"""
retry_max_seconds: int = 20
"""Max number of seconds to wait between retries"""
http_client: Any | None = None
"""Optional `httpx.Client`. Only used for sync invocations. Must specify
`http_async_client` as well if you'd like a custom client for async
invocations.
"""
http_async_client: Any | None = None
"""Optional `httpx.AsyncClient`. Only used for async invocations. Must specify
`http_client` as well if you'd like a custom client for sync invocations."""
check_embedding_ctx_length: bool = True
"""Whether to check the token length of inputs and automatically split inputs
longer than embedding_ctx_length."""

33
libs/partners/openai/langchain_openai/llms/base.py
View File

@@ -164,37 +164,50 @@ class BaseOpenAI(BaseLLM):
"""
client: Any = Field(default=None, exclude=True) #: :meta private:
async_client: Any = Field(default=None, exclude=True) #: :meta private:
client: Any = Field(default=None, exclude=True)
async_client: Any = Field(default=None, exclude=True)
model_name: str = Field(default="gpt-3.5-turbo-instruct", alias="model")
"""Model name to use."""
temperature: float = 0.7
"""What sampling temperature to use."""
max_tokens: int = 256
"""The maximum number of tokens to generate in the completion.
-1 returns as many tokens as possible given the prompt and
the models maximal context size."""
top_p: float = 1
"""Total probability mass of tokens to consider at each step."""
frequency_penalty: float = 0
"""Penalizes repeated tokens according to frequency."""
presence_penalty: float = 0
"""Penalizes repeated tokens."""
n: int = 1
"""How many completions to generate for each prompt."""
best_of: int = 1
"""Generates best_of completions server-side and returns the "best"."""
model_kwargs: dict[str, Any] = Field(default_factory=dict)
"""Holds any model parameters valid for `create` call not explicitly specified."""
openai_api_key: SecretStr | None | Callable[[], str] = Field(
alias="api_key", default_factory=secret_from_env("OPENAI_API_KEY", default=None)
)
"""Automatically inferred from env var `OPENAI_API_KEY` if not provided."""
openai_api_base: str | None = Field(
alias="base_url", default_factory=from_env("OPENAI_API_BASE", default=None)
)
"""Base URL path for API requests, leave blank if not using a proxy or service
emulator."""
openai_organization: str | None = Field(
alias="organization",
default_factory=from_env(
@@ -202,32 +215,43 @@ class BaseOpenAI(BaseLLM):
),
)
"""Automatically inferred from env var `OPENAI_ORG_ID` if not provided."""
# to support explicit proxy for OpenAI
openai_proxy: str | None = Field(
default_factory=from_env("OPENAI_PROXY", default=None)
)
batch_size: int = 20
"""Batch size to use when passing multiple documents to generate."""
request_timeout: float | tuple[float, float] | Any | None = Field(
default=None, alias="timeout"
)
"""Timeout for requests to OpenAI completion API. Can be float, `httpx.Timeout` or
None."""
logit_bias: dict[str, float] | None = None
"""Adjust the probability of specific tokens being generated."""
max_retries: int = 2
"""Maximum number of retries to make when generating."""
seed: int | None = None
"""Seed for generation"""
logprobs: int | None = None
"""Include the log probabilities on the logprobs most likely output tokens,
as well the chosen tokens."""
streaming: bool = False
"""Whether to stream the results or not."""
allowed_special: Literal["all"] | set[str] = set()
"""Set of special tokens that are allowed。"""
disallowed_special: Literal["all"] | Collection[str] = "all"
"""Set of special tokens that are not allowed。"""
tiktoken_model_name: str | None = None
"""The model name to pass to tiktoken when using this class.
Tiktoken is used to count the number of tokens in documents to constrain
@@ -238,8 +262,11 @@ class BaseOpenAI(BaseLLM):
when using one of the many model providers that expose an OpenAI-like
API but with different models. In those cases, in order to avoid erroring
when tiktoken is called, you can specify a model name to use here."""
default_headers: Mapping[str, str] | None = None
default_query: Mapping[str, object] | None = None
# Configure a custom httpx client. See the
# [httpx documentation](https://www.python-httpx.org/api/#client) for more details.
http_client: Any | None = None
@@ -247,9 +274,11 @@ class BaseOpenAI(BaseLLM):
`http_async_client` as well if you'd like a custom client for async
invocations.
"""
http_async_client: Any | None = None
"""Optional `httpx.AsyncClient`. Only used for async invocations. Must specify
`http_client` as well if you'd like a custom client for sync invocations."""
extra_body: Mapping[str, Any] | None = None
"""Optional additional JSON properties to include in the request parameters when
making requests to OpenAI compatible APIs, such as vLLM."""

11
libs/partners/openai/pyproject.toml
View File

@@ -3,18 +3,19 @@ requires = ["hatchling"]
build-backend = "hatchling.build"
[project]
authors = []
name = "langchain-openai"
description = "An integration package connecting OpenAI and LangChain"
license = { text = "MIT" }
readme = "README.md"
authors = []
version = "1.0.2"
requires-python = ">=3.10.0,<4.0.0"
dependencies = [
"langchain-core>=1.0.2,<2.0.0",
"openai>=1.109.1,<3.0.0",
"tiktoken>=0.7.0,<1.0.0",
]
name = "langchain-openai"
version = "1.0.2"
description = "An integration package connecting OpenAI and LangChain"
readme = "README.md"
[project.urls]
Homepage = "https://docs.langchain.com/oss/python/integrations/providers/openai"