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

docs: more fixes for refs (#33554)

Browse Source
This commit is contained in:
Mason Daugherty
2025-10-16 22:54:16 -04:00
committed by GitHub
parent 9dd494ddcd
commit 1d2273597a
41 changed files with 1305 additions and 1238 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
libs/partners/openai/langchain_openai/chat_models/azure.py
View File

@@ -49,30 +49,30 @@ class AzureChatOpenAI(BaseChatOpenAI):
```
Key init args — completion params:
azure_deployment: str
azure_deployment:
Name of Azure OpenAI deployment to use.
temperature: float
temperature:
Sampling temperature.
max_tokens: int | None
max_tokens:
Max number of tokens to generate.
logprobs: bool | None
logprobs:
Whether to return logprobs.
Key init args — client params:
api_version: str
api_version:
Azure OpenAI REST API version to use (distinct from the version of the
underlying model). [See more on the different versions.](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#rest-api-versioning)
timeout: Union[float, Tuple[float, float], Any, None]
timeout:
Timeout for requests.
max_retries: int | None
max_retries:
Max number of retries.
organization: str | None
organization:
OpenAI organization ID. If not passed in will be read from env
var `OPENAI_ORG_ID`.
model: str | None
model:
The name of the underlying OpenAI model. Used for tracing and token
counting. Does not affect completion. E.g. `'gpt-4'`, `'gpt-35-turbo'`, etc.
model_version: str | None
model_version:
The version of the underlying OpenAI model. Used for tracing and token
counting. Does not affect completion. E.g., `'0125'`, `'0125-preview'`, etc.
@@ -835,15 +835,17 @@ class AzureChatOpenAI(BaseChatOpenAI):
- a JSON Schema,
- a `TypedDict` class,
- or a Pydantic class,
- an OpenAI function/tool schema.
- 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
validated by the Pydantic class. Otherwise the model output will be a
dict and will not be validated. See `langchain_core.utils.function_calling.convert_to_openai_tool`
for more on how to properly specify types and descriptions of
schema fields when specifying a Pydantic or `TypedDict` class.
dict and will not be validated.
See `langchain_core.utils.function_calling.convert_to_openai_tool` for
more on how to properly specify types and descriptions of schema fields
when specifying a Pydantic or `TypedDict` class.
method: The method for steering model generation, one of:
@@ -867,8 +869,10 @@ class AzureChatOpenAI(BaseChatOpenAI):
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'`.
will be caught and returned as well.
The final output is always a `dict` with keys `'raw'`, `'parsed'`, and
`'parsing_error'`.
strict:
- True:
@@ -934,16 +938,18 @@ class AzureChatOpenAI(BaseChatOpenAI):
kwargs: Additional keyword args are passed through to the model.
Returns:
A Runnable that takes same inputs as a `langchain_core.language_models.chat.BaseChatModel`.
A `Runnable` that takes same inputs as a
`langchain_core.language_models.chat.BaseChatModel`. If `include_raw` is
`False` and `schema` is a Pydantic class, `Runnable` outputs an instance
of `schema` (i.e., a Pydantic object). Otherwise, if `include_raw` is
`False` then `Runnable` outputs a `dict`.
If `include_raw` is False and `schema` is a Pydantic class, Runnable outputs
an instance of `schema` (i.e., a Pydantic object). Otherwise, if `include_raw` is False then Runnable outputs a dict.
If `include_raw` is `True`, then `Runnable` outputs a `dict` with keys:
If `include_raw` is True, then Runnable outputs a dict with keys:
- `'raw'`: BaseMessage
- `'parsed'`: None if there was a parsing error, otherwise the type depends on the `schema` as described above.
- `'parsing_error'`: BaseException | None
- `'raw'`: `BaseMessage`
- `'parsed'`: `None` if there was a parsing error, otherwise the type
depends on the `schema` as described above.
- `'parsing_error'`: `BaseException | None`
!!! warning "Behavior changed in 0.3.0"
`method` default changed from "function_calling" to "json_schema".

72
libs/partners/openai/langchain_openai/chat_models/base.py
View File

@@ -1744,9 +1744,11 @@ class BaseChatOpenAI(BaseChatModel):
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
validated by the Pydantic class. Otherwise the model output will be a
dict and will not be validated. See `langchain_core.utils.function_calling.convert_to_openai_tool`
for more on how to properly specify types and descriptions of
schema fields when specifying a Pydantic or `TypedDict` class.
dict and will not be validated.
See `langchain_core.utils.function_calling.convert_to_openai_tool` for
more on how to properly specify types and descriptions of schema fields
when specifying a Pydantic or `TypedDict` class.
method: The method for steering model generation, one of:
@@ -1765,8 +1767,10 @@ class BaseChatOpenAI(BaseChatModel):
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'`.
will be caught and returned as well.
The final output is always a `dict` with keys `'raw'`, `'parsed'`, and
`'parsing_error'`.
strict:
- `True`:
@@ -1827,25 +1831,25 @@ class BaseChatOpenAI(BaseChatModel):
kwargs: Additional keyword args are passed through to the model.
Returns:
A `Runnable` that takes same inputs as a `BaseChatModel`.
A `Runnable` that takes same inputs as a
`langchain_core.language_models.chat.BaseChatModel`. If `include_raw` is
`False` and `schema` is a Pydantic class, `Runnable` outputs an instance
of `schema` (i.e., a Pydantic object). Otherwise, if `include_raw` is
`False` then `Runnable` outputs a `dict`.
If `include_raw` is `False` and `schema` is a Pydantic class, `Runnable`
outputs an instance of `schema` (i.e., a Pydantic object). Otherwise, if
`include_raw` is `False` then `Runnable` outputs a `dict`.
If `include_raw` is `True`, then `Runnable` outputs a `dict` with keys:
If `include_raw` is `True`, then `Runnable` outputs a dict with keys:
- `'raw'`: `BaseMessage`
- `'parsed'`: `None` if there was a parsing error, otherwise the type depends
on the `schema` as described above.
- `'parsing_error'`: `BaseException` or `None`
- `'raw'`: `BaseMessage`
- `'parsed'`: `None` if there was a parsing error, otherwise the type
depends on the `schema` as described above.
- `'parsing_error'`: `BaseException | None`
!!! warning "Behavior changed in 0.3.12"
Support for `tools` added.
!!! warning "Behavior changed in 0.3.21"
Pass `kwargs` through to the model.
""" # noqa: E501
"""
if strict is not None and method == "json_mode":
msg = "Argument `strict` is not supported with `method`='json_mode'"
raise ValueError(msg)
@@ -2832,17 +2836,19 @@ class ChatOpenAI(BaseChatOpenAI): # type: ignore[override]
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.
- 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
validated by the Pydantic class. Otherwise the model output will be a
dict and will not be validated. See `langchain_core.utils.function_calling.convert_to_openai_tool`
for more on how to properly specify types and descriptions of
schema fields when specifying a Pydantic or `TypedDict` class.
dict and will not be validated.
See `langchain_core.utils.function_calling.convert_to_openai_tool` for
more on how to properly specify types and descriptions of schema fields
when specifying a Pydantic or `TypedDict` class.
method: The method for steering model generation, one of:
@@ -2864,8 +2870,10 @@ class ChatOpenAI(BaseChatOpenAI): # type: ignore[override]
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'`.
will be caught and returned as well.
The final output is always a `dict` with keys `'raw'`, `'parsed'`, and
`'parsing_error'`.
strict:
- `True`:
@@ -2931,16 +2939,18 @@ class ChatOpenAI(BaseChatOpenAI): # type: ignore[override]
kwargs: Additional keyword args are passed through to the model.
Returns:
A Runnable that takes same inputs as a `langchain_core.language_models.chat.BaseChatModel`.
A `Runnable` that takes same inputs as a
`langchain_core.language_models.chat.BaseChatModel`. If `include_raw` is
`False` and `schema` is a Pydantic class, `Runnable` outputs an instance
of `schema` (i.e., a Pydantic object). Otherwise, if `include_raw` is
`False` then `Runnable` outputs a `dict`.
If `include_raw` is `False` and `schema` is a Pydantic class, Runnable outputs
an instance of `schema` (i.e., a Pydantic object). Otherwise, if `include_raw` is `False` then `Runnable` outputs a `dict`.
If `include_raw` is `True`, then `Runnable` outputs a `dict` with keys:
If `include_raw` is `True`, then `Runnable` outputs a `dict` with keys:
- `'raw'`: `BaseMessage`
- `'parsed'`: `None` if there was a parsing error, otherwise the type depends on the `schema` as described above.
- `'parsing_error'`: `BaseException` or `None`
- `'raw'`: `BaseMessage`
- `'parsed'`: `None` if there was a parsing error, otherwise the type
depends on the `schema` as described above.
- `'parsing_error'`: `BaseException | None`
!!! warning "Behavior changed in 0.3.0"
`method` default changed from `"function_calling"` to `"json_schema"`.

13
libs/partners/openai/langchain_openai/embeddings/azure.py
View File

@@ -38,14 +38,11 @@ class AzureOpenAIEmbeddings(OpenAIEmbeddings): # type: ignore[override]
```
Key init args — completion params:
model: str
Name of AzureOpenAI model to use.
dimensions: int | None
Number of dimensions for the embeddings. Can be specified only
if the underlying model supports it.
Key init args — client params:
api_key: SecretStr | None
model:
Name of `AzureOpenAI` model to use.
dimensions:
Number of dimensions for the embeddings. Can be specified only if the
underlying model supports it.
See full list of supported init args and their descriptions in the params section.

12
libs/partners/openai/langchain_openai/embeddings/base.py
View File

@@ -90,21 +90,21 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
```
Key init args — embedding params:
model: str
model:
Name of OpenAI model to use.
dimensions: int | None = None
dimensions:
The number of dimensions the resulting output embeddings should have.
Only supported in `'text-embedding-3'` and later models.
Key init args — client params:
api_key: SecretStr | None = None
api_key:
OpenAI API key.
organization: str | None = None
organization:
OpenAI organization ID. If not passed in will be read
from env var `OPENAI_ORG_ID`.
max_retries: int = 2
max_retries:
Maximum number of retries to make when generating.
request_timeout: float | Tuple[float, float] | Any | None = None
request_timeout:
Timeout for requests to OpenAI completion API
See full list of supported init args and their descriptions in the params section.

56
libs/partners/openai/langchain_openai/llms/base.py
View File

@@ -62,46 +62,46 @@ class BaseOpenAI(BaseLLM):
```
Key init args — completion params:
model_name: str
model_name:
Name of OpenAI model to use.
temperature: float
temperature:
Sampling temperature.
max_tokens: int
max_tokens:
Max number of tokens to generate.
top_p: float
top_p:
Total probability mass of tokens to consider at each step.
frequency_penalty: float
frequency_penalty:
Penalizes repeated tokens according to frequency.
presence_penalty: float
presence_penalty:
Penalizes repeated tokens.
n: int
n:
How many completions to generate for each prompt.
best_of: int
best_of:
Generates best_of completions server-side and returns the "best".
logit_bias: dict[str, float] | None
logit_bias:
Adjust the probability of specific tokens being generated.
seed: int | None
seed:
Seed for generation.
logprobs: int | None
logprobs:
Include the log probabilities on the logprobs most likely output tokens.
streaming: bool
streaming:
Whether to stream the results or not.
Key init args — client params:
openai_api_key: SecretStr | None
openai_api_key:
OpenAI API key. If not passed in will be read from env var
`OPENAI_API_KEY`.
openai_api_base: str | None
openai_api_base:
Base URL path for API requests, leave blank if not using a proxy or
service emulator.
openai_organization: str | None
openai_organization:
OpenAI organization ID. If not passed in will be read from env
var `OPENAI_ORG_ID`.
request_timeout: Union[float, tuple[float, float], Any, None]
request_timeout:
Timeout for requests to OpenAI completion API.
max_retries: int
max_retries:
Maximum number of retries to make when generating.
batch_size: int
batch_size:
Batch size to use when passing multiple documents to generate.
See full list of supported init args and their descriptions in the params section.
@@ -707,29 +707,29 @@ class OpenAI(BaseOpenAI):
```
Key init args — completion params:
model: str
model:
Name of OpenAI model to use.
temperature: float
temperature:
Sampling temperature.
max_tokens: int | None
max_tokens:
Max number of tokens to generate.
logprobs: bool | None
logprobs:
Whether to return logprobs.
stream_options: Dict
stream_options:
Configure streaming outputs, like whether to return token usage when
streaming (`{"include_usage": True}`).
Key init args — client params:
timeout: Union[float, Tuple[float, float], Any, None]
timeout:
Timeout for requests.
max_retries: int
max_retries:
Max number of retries.
api_key: str | None
api_key:
OpenAI API key. If not passed in will be read from env var `OPENAI_API_KEY`.
base_url: str | None
base_url:
Base URL for API requests. Only specify if using a proxy or service
emulator.
organization: str | None
organization:
OpenAI organization ID. If not passed in will be read from env
var `OPENAI_ORG_ID`.