Skip to content

🌿 Fern Regeneration -- October 15, 2025 #702

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

🌿 Fern Regeneration -- October 15, 2025 #702

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
820 changes: 456 additions & 364 deletions poetry.lock
View file
Open in desktop

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ name = "cohere"

[tool.poetry]
name = "cohere"
version = "5.18.0"
version = "5.19.0"
description = ""
readme = "README.md"
authors = []
Expand Down
66 changes: 20 additions & 46 deletions src/cohere/base_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -268,9 +268,8 @@ def chat_stream(
Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

citation_quality : typing.Optional[ChatStreamRequestCitationQuality]
Defaults to `"accurate"`.

Dictates the approach taken to generating citations as part of the RAG flow by allowing the user to specify whether they want `"accurate"` results, `"fast"` results or no results.
Defaults to `"enabled"`.
Citations are enabled by default for models that support it, but can be turned off by setting `"type": "disabled"`.

Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

Expand Down Expand Up @@ -406,7 +405,8 @@ def chat_stream(
token="YOUR_TOKEN",
)
response = client.chat_stream(
message="hello world!",
model="command-a-03-2025",
message="hello!",
)
for chunk in response:
yield chunk
Expand Down Expand Up @@ -568,9 +568,8 @@ def chat(
Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

citation_quality : typing.Optional[ChatRequestCitationQuality]
Defaults to `"accurate"`.

Dictates the approach taken to generating citations as part of the RAG flow by allowing the user to specify whether they want `"accurate"` results, `"fast"` results or no results.
Defaults to `"enabled"`.
Citations are enabled by default for models that support it, but can be turned off by setting `"type": "disabled"`.

Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

Expand Down Expand Up @@ -699,27 +698,15 @@ def chat(

Examples
--------
from cohere import ChatbotMessage, ChatConnector, Client, UserMessage
from cohere import Client

client = Client(
client_name="YOUR_CLIENT_NAME",
token="YOUR_TOKEN",
)
client.chat(
chat_history=[
UserMessage(
message="Who discovered gravity?",
),
ChatbotMessage(
message="The man who is widely credited with discovering gravity is Sir Isaac Newton",
),
],
message="What year was he born?",
connectors=[
ChatConnector(
id="web-search",
)
],
model="command-a-03-2025",
message="Tell me about LLMs",
)
"""
_response = self._raw_client.chat(
Expand Down Expand Up @@ -1073,7 +1060,7 @@ def embed(
images : typing.Optional[typing.Sequence[str]]
An array of image data URIs for the model to embed. Maximum number of images per call is `1`.

The image must be a valid [data URI](https://developer.mozilla.org/en-US/docs/Web/URI/Schemes/data). The image must be in either `image/jpeg` or `image/png` format and has a maximum size of 5MB.
The image must be a valid [data URI](https://developer.mozilla.org/en-US/docs/Web/URI/Schemes/data). The image must be in either `image/jpeg`, `image/png`, `image/webp`, or `image/gif` format and has a maximum size of 5MB.

Images are only supported with Embed v3.0 and newer models.

Expand Down Expand Up @@ -1724,9 +1711,8 @@ async def chat_stream(
Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

citation_quality : typing.Optional[ChatStreamRequestCitationQuality]
Defaults to `"accurate"`.

Dictates the approach taken to generating citations as part of the RAG flow by allowing the user to specify whether they want `"accurate"` results, `"fast"` results or no results.
Defaults to `"enabled"`.
Citations are enabled by default for models that support it, but can be turned off by setting `"type": "disabled"`.

Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

Expand Down Expand Up @@ -1867,7 +1853,8 @@ async def chat_stream(

async def main() -> None:
response = await client.chat_stream(
message="hello world!",
model="command-a-03-2025",
message="hello!",
)
async for chunk in response:
yield chunk
Expand Down Expand Up @@ -2033,9 +2020,8 @@ async def chat(
Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

citation_quality : typing.Optional[ChatRequestCitationQuality]
Defaults to `"accurate"`.

Dictates the approach taken to generating citations as part of the RAG flow by allowing the user to specify whether they want `"accurate"` results, `"fast"` results or no results.
Defaults to `"enabled"`.
Citations are enabled by default for models that support it, but can be turned off by setting `"type": "disabled"`.

Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

Expand Down Expand Up @@ -2166,7 +2152,7 @@ async def chat(
--------
import asyncio

from cohere import AsyncClient, ChatbotMessage, ChatConnector, UserMessage
from cohere import AsyncClient

client = AsyncClient(
client_name="YOUR_CLIENT_NAME",
Expand All @@ -2176,20 +2162,8 @@ async def chat(

async def main() -> None:
await client.chat(
chat_history=[
UserMessage(
message="Who discovered gravity?",
),
ChatbotMessage(
message="The man who is widely credited with discovering gravity is Sir Isaac Newton",
),
],
message="What year was he born?",
connectors=[
ChatConnector(
id="web-search",
)
],
model="command-a-03-2025",
message="Tell me about LLMs",
)


Expand Down Expand Up @@ -2563,7 +2537,7 @@ async def embed(
images : typing.Optional[typing.Sequence[str]]
An array of image data URIs for the model to embed. Maximum number of images per call is `1`.

The image must be a valid [data URI](https://developer.mozilla.org/en-US/docs/Web/URI/Schemes/data). The image must be in either `image/jpeg` or `image/png` format and has a maximum size of 5MB.
The image must be a valid [data URI](https://developer.mozilla.org/en-US/docs/Web/URI/Schemes/data). The image must be in either `image/jpeg`, `image/png`, `image/webp`, or `image/gif` format and has a maximum size of 5MB.

Images are only supported with Embed v3.0 and newer models.

Expand Down
4 changes: 2 additions & 2 deletions src/cohere/core/client_wrapper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,10 +22,10 @@ def __init__(

def get_headers(self) -> typing.Dict[str, str]:
headers: typing.Dict[str, str] = {
"User-Agent": "cohere/5.18.0",
"User-Agent": "cohere/5.19.0",
"X-Fern-Language": "Python",
"X-Fern-SDK-Name": "cohere",
"X-Fern-SDK-Version": "5.18.0",
"X-Fern-SDK-Version": "5.19.0",
}
if self._client_name is not None:
headers["X-Client-Name"] = self._client_name
Expand Down
4 changes: 2 additions & 2 deletions src/cohere/datasets/client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,7 +120,7 @@ def create(
The name of the uploaded dataset.

type : DatasetType
The dataset type, which is used to validate the data. Valid types are `embed-input`, `reranker-finetune-input`, `single-label-classification-finetune-input`, `chat-finetune-input`, and `multi-label-classification-finetune-input`.
The dataset type, which is used to validate the data. The only valid type is `embed-input` used in conjunction with the Embed Jobs API.

data : core.File
See core.File for more documentation
Expand Down Expand Up @@ -384,7 +384,7 @@ async def create(
The name of the uploaded dataset.

type : DatasetType
The dataset type, which is used to validate the data. Valid types are `embed-input`, `reranker-finetune-input`, `single-label-classification-finetune-input`, `chat-finetune-input`, and `multi-label-classification-finetune-input`.
The dataset type, which is used to validate the data. The only valid type is `embed-input` used in conjunction with the Embed Jobs API.

data : core.File
See core.File for more documentation
Expand Down
4 changes: 2 additions & 2 deletions src/cohere/datasets/raw_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -265,7 +265,7 @@ def create(
The name of the uploaded dataset.

type : DatasetType
The dataset type, which is used to validate the data. Valid types are `embed-input`, `reranker-finetune-input`, `single-label-classification-finetune-input`, `chat-finetune-input`, and `multi-label-classification-finetune-input`.
The dataset type, which is used to validate the data. The only valid type is `embed-input` used in conjunction with the Embed Jobs API.

data : core.File
See core.File for more documentation
Expand Down Expand Up @@ -1207,7 +1207,7 @@ async def create(
The name of the uploaded dataset.

type : DatasetType
The dataset type, which is used to validate the data. Valid types are `embed-input`, `reranker-finetune-input`, `single-label-classification-finetune-input`, `chat-finetune-input`, and `multi-label-classification-finetune-input`.
The dataset type, which is used to validate the data. The only valid type is `embed-input` used in conjunction with the Embed Jobs API.

data : core.File
See core.File for more documentation
Expand Down
4 changes: 2 additions & 2 deletions src/cohere/models/client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@ def list(
request_options: typing.Optional[RequestOptions] = None,
) -> ListModelsResponse:
"""
Returns a list of models available for use. The list contains models from Cohere as well as your fine-tuned models.
Returns a list of models available for use.

Parameters
----------
Expand Down Expand Up @@ -175,7 +175,7 @@ async def list(
request_options: typing.Optional[RequestOptions] = None,
) -> ListModelsResponse:
"""
Returns a list of models available for use. The list contains models from Cohere as well as your fine-tuned models.
Returns a list of models available for use.

Parameters
----------
Expand Down
4 changes: 2 additions & 2 deletions src/cohere/models/raw_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,7 +210,7 @@ def list(
request_options: typing.Optional[RequestOptions] = None,
) -> HttpResponse[ListModelsResponse]:
"""
Returns a list of models available for use. The list contains models from Cohere as well as your fine-tuned models.
Returns a list of models available for use.

Parameters
----------
Expand Down Expand Up @@ -578,7 +578,7 @@ async def list(
request_options: typing.Optional[RequestOptions] = None,
) -> AsyncHttpResponse[ListModelsResponse]:
"""
Returns a list of models available for use. The list contains models from Cohere as well as your fine-tuned models.
Returns a list of models available for use.

Parameters
----------
Expand Down
24 changes: 10 additions & 14 deletions src/cohere/raw_base_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -196,9 +196,8 @@ def chat_stream(
Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

citation_quality : typing.Optional[ChatStreamRequestCitationQuality]
Defaults to `"accurate"`.

Dictates the approach taken to generating citations as part of the RAG flow by allowing the user to specify whether they want `"accurate"` results, `"fast"` results or no results.
Defaults to `"enabled"`.
Citations are enabled by default for models that support it, but can be turned off by setting `"type": "disabled"`.

Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

Expand Down Expand Up @@ -663,9 +662,8 @@ def chat(
Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

citation_quality : typing.Optional[ChatRequestCitationQuality]
Defaults to `"accurate"`.

Dictates the approach taken to generating citations as part of the RAG flow by allowing the user to specify whether they want `"accurate"` results, `"fast"` results or no results.
Defaults to `"enabled"`.
Citations are enabled by default for models that support it, but can be turned off by setting `"type": "disabled"`.

Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

Expand Down Expand Up @@ -1607,7 +1605,7 @@ def embed(
images : typing.Optional[typing.Sequence[str]]
An array of image data URIs for the model to embed. Maximum number of images per call is `1`.

The image must be a valid [data URI](https://developer.mozilla.org/en-US/docs/Web/URI/Schemes/data). The image must be in either `image/jpeg` or `image/png` format and has a maximum size of 5MB.
The image must be a valid [data URI](https://developer.mozilla.org/en-US/docs/Web/URI/Schemes/data). The image must be in either `image/jpeg`, `image/png`, `image/webp`, or `image/gif` format and has a maximum size of 5MB.

Images are only supported with Embed v3.0 and newer models.

Expand Down Expand Up @@ -3111,9 +3109,8 @@ async def chat_stream(
Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

citation_quality : typing.Optional[ChatStreamRequestCitationQuality]
Defaults to `"accurate"`.

Dictates the approach taken to generating citations as part of the RAG flow by allowing the user to specify whether they want `"accurate"` results, `"fast"` results or no results.
Defaults to `"enabled"`.
Citations are enabled by default for models that support it, but can be turned off by setting `"type": "disabled"`.

Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

Expand Down Expand Up @@ -3578,9 +3575,8 @@ async def chat(
Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

citation_quality : typing.Optional[ChatRequestCitationQuality]
Defaults to `"accurate"`.

Dictates the approach taken to generating citations as part of the RAG flow by allowing the user to specify whether they want `"accurate"` results, `"fast"` results or no results.
Defaults to `"enabled"`.
Citations are enabled by default for models that support it, but can be turned off by setting `"type": "disabled"`.

Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments

Expand Down Expand Up @@ -4522,7 +4518,7 @@ async def embed(
images : typing.Optional[typing.Sequence[str]]
An array of image data URIs for the model to embed. Maximum number of images per call is `1`.

The image must be a valid [data URI](https://developer.mozilla.org/en-US/docs/Web/URI/Schemes/data). The image must be in either `image/jpeg` or `image/png` format and has a maximum size of 5MB.
The image must be a valid [data URI](https://developer.mozilla.org/en-US/docs/Web/URI/Schemes/data). The image must be in either `image/jpeg`, `image/png`, `image/webp`, or `image/gif` format and has a maximum size of 5MB.

Images are only supported with Embed v3.0 and newer models.

Expand Down
5 changes: 5 additions & 0 deletions src/cohere/types/api_meta.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,11 @@ class ApiMeta(UncheckedBaseModel):
api_version: typing.Optional[ApiMetaApiVersion] = None
billed_units: typing.Optional[ApiMetaBilledUnits] = None
tokens: typing.Optional[ApiMetaTokens] = None
cached_tokens: typing.Optional[float] = pydantic.Field(default=None)
"""
The number of prompt tokens that hit the inference cache.
"""

warnings: typing.Optional[typing.List[str]] = None

if IS_PYDANTIC_V2:
Expand Down
2 changes: 1 addition & 1 deletion src/cohere/types/chat_request_citation_quality.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,4 +2,4 @@

import typing

ChatRequestCitationQuality = typing.Union[typing.Literal["fast", "accurate", "off"], typing.Any]
ChatRequestCitationQuality = typing.Union[typing.Literal["ENABLED", "DISABLED", "FAST", "ACCURATE", "OFF"], typing.Any]
4 changes: 3 additions & 1 deletion src/cohere/types/chat_stream_request_citation_quality.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,4 +2,6 @@

import typing

ChatStreamRequestCitationQuality = typing.Union[typing.Literal["fast", "accurate", "off"], typing.Any]
ChatStreamRequestCitationQuality = typing.Union[
typing.Literal["ENABLED", "DISABLED", "FAST", "ACCURATE", "OFF"], typing.Any
]
6 changes: 2 additions & 4 deletions src/cohere/types/citation_options.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,10 +15,8 @@ class CitationOptions(UncheckedBaseModel):

mode: typing.Optional[CitationOptionsMode] = pydantic.Field(default=None)
"""
Defaults to `"accurate"`.
Dictates the approach taken to generating citations as part of the RAG flow by allowing the user to specify whether they want `"accurate"` results, `"fast"` results or no results.

**Note**: `command-r7b-12-2024` and `command-a-03-2025` only support `"fast"` and `"off"` modes. The default is `"fast"`.
Defaults to `"enabled"`.
Citations are enabled by default for models that support it, but can be turned off by setting `"type": "disabled"`.
"""

if IS_PYDANTIC_V2:
Expand Down
2 changes: 1 addition & 1 deletion src/cohere/types/citation_options_mode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,4 +2,4 @@

import typing

CitationOptionsMode = typing.Union[typing.Literal["FAST", "ACCURATE", "OFF"], typing.Any]
CitationOptionsMode = typing.Union[typing.Literal["ENABLED", "DISABLED", "FAST", "ACCURATE", "OFF"], typing.Any]
4 changes: 4 additions & 0 deletions src/cohere/types/dataset_type.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,10 @@
"single-label-classification-finetune-input",
"chat-finetune-input",
"multi-label-classification-finetune-input",
"batch-chat-input",
"batch-openai-chat-input",
"batch-embed-v2-input",
"batch-chat-v2-input",
],
typing.Any,
]
5 changes: 0 additions & 5 deletions src/cohere/types/get_model_response.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,11 +43,6 @@ class GetModelResponse(UncheckedBaseModel):
Public URL to the tokenizer's configuration file.
"""

supports_vision: typing.Optional[bool] = pydantic.Field(default=None)
"""
Whether the model supports image inputs or not.
"""

default_endpoints: typing.Optional[typing.List[CompatibleEndpoint]] = pydantic.Field(default=None)
"""
The API endpoints that the model is default to.
Expand Down
8 changes: 4 additions & 4 deletions src/cohere/types/usage.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,13 +5,13 @@
import pydantic
from ..core.pydantic_utilities import IS_PYDANTIC_V2
from ..core.unchecked_base_model import UncheckedBaseModel
from .usage_billed_units import UsageBilledUnits
from .usage_tokens import UsageTokens


class Usage(UncheckedBaseModel):
billed_units: typing.Optional[UsageBilledUnits] = None
tokens: typing.Optional[UsageTokens] = None
cached_tokens: typing.Optional[float] = pydantic.Field(default=None)
"""
The number of prompt tokens that hit the inference cache.
"""

if IS_PYDANTIC_V2:
model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow") # type: ignore # Pydantic v2
Expand Down
Loading
Loading