SDK regeneration

.gitignore

@@ -3,4 +3,3 @@ dist/
 __pycache__/
 poetry.toml
 .ruff_cache/
-.venv/

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cohere"
-version = "5.11.4"
+version = "5.12.0"
 description = ""
 readme = "README.md"
 authors = []

reference.md

@@ -2365,6 +2365,7 @@ response = client.v2.chat_stream(
             ),
         )
     ],
+    strict_tools=True,
     documents=["string"],
     citation_options=CitationOptions(
         mode="FAST",
@@ -2381,6 +2382,7 @@ response = client.v2.chat_stream(
     p=1.1,
     return_prompt=True,
     logprobs=True,
+    stream=True,
 )
 for chunk in response:
     yield chunk
@@ -2422,6 +2424,19 @@ A list of available tools (functions) that the model may suggest invoking before
 When `tools` is passed (without `tool_results`), the `text` content in the response will be empty and the `tool_calls` field in the response will be populated with a list of tool calls that need to be made. If no calls need to be made, the `tool_calls` array will be empty.
 
 
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**strict_tools:** `typing.Optional[bool]` 
+
+When set to `true`, tool calls in the Assistant message will be forced to follow the tool definition strictly. Learn more in the [Strict Tools guide](https://docs.cohere.com/docs/structured-outputs-json#structured-outputs-tools).
+
+**Note**: The first few requests with a new set of tools will take longer to process.
+
+
 </dd>
 </dl>
 
@@ -2546,7 +2561,7 @@ Used to reduce repetitiveness of generated tokens. Similar to `frequency_penalty
 
 **k:** `typing.Optional[float]` 
 
-Ensures that only the top `k` most likely tokens are considered for generation at each step. When `k` is set to `0`, k-sampling is disabled. 
+Ensures that only the top `k` most likely tokens are considered for generation at each step. When `k` is set to `0`, k-sampling is disabled.
 Defaults to `0`, min value of `0`, max value of `500`.
 
 
@@ -2576,7 +2591,7 @@ Defaults to `0.75`. min value of `0.01`, max value of `0.99`.
 <dl>
 <dd>
 
-**logprobs:** `typing.Optional[bool]` — Whether to return the log probabilities of the generated tokens. Defaults to false.
+**logprobs:** `typing.Optional[bool]` — Defaults to `false`. When set to `true`, the log probabilities of the generated tokens will be included in the response.
 
 
 </dd>
@@ -2640,6 +2655,7 @@ client.v2.chat(
             content="messages",
         )
     ],
+    stream=False,
 )
 
 ```
@@ -2679,6 +2695,19 @@ A list of available tools (functions) that the model may suggest invoking before
 When `tools` is passed (without `tool_results`), the `text` content in the response will be empty and the `tool_calls` field in the response will be populated with a list of tool calls that need to be made. If no calls need to be made, the `tool_calls` array will be empty.
 
 
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**strict_tools:** `typing.Optional[bool]` 
+
+When set to `true`, tool calls in the Assistant message will be forced to follow the tool definition strictly. Learn more in the [Strict Tools guide](https://docs.cohere.com/docs/structured-outputs-json#structured-outputs-tools).
+
+**Note**: The first few requests with a new set of tools will take longer to process.
+
+
 </dd>
 </dl>
 
@@ -2803,7 +2832,7 @@ Used to reduce repetitiveness of generated tokens. Similar to `frequency_penalty
 
 **k:** `typing.Optional[float]` 
 
-Ensures that only the top `k` most likely tokens are considered for generation at each step. When `k` is set to `0`, k-sampling is disabled. 
+Ensures that only the top `k` most likely tokens are considered for generation at each step. When `k` is set to `0`, k-sampling is disabled.
 Defaults to `0`, min value of `0`, max value of `500`.
 
 
@@ -2833,7 +2862,7 @@ Defaults to `0.75`. min value of `0.01`, max value of `0.99`.
 <dl>
 <dd>
 
-**logprobs:** `typing.Optional[bool]` — Whether to return the log probabilities of the generated tokens. Defaults to false.
+**logprobs:** `typing.Optional[bool]` — Defaults to `false`. When set to `true`, the log probabilities of the generated tokens will be included in the response.
 
 
 </dd>
@@ -3057,7 +3086,15 @@ client.v2.rerank(
 <dl>
 <dd>
 
-**model:** `str` — The identifier of the model to use, one of : `rerank-english-v3.0`, `rerank-multilingual-v3.0`, `rerank-english-v2.0`, `rerank-multilingual-v2.0`
+**model:** `str` 
+
+The identifier of the model to use.
+
+Supported models:
+  - `rerank-english-v3.0`
+  - `rerank-multilingual-v3.0`
+  - `rerank-english-v2.0`
+  - `rerank-multilingual-v2.0`
 
 </dd>
 </dl>
@@ -3073,30 +3110,22 @@ client.v2.rerank(
 <dl>
 <dd>
 
-**documents:** `typing.Sequence[V2RerankRequestDocumentsItem]` 
-
-A list of document objects or strings to rerank.
-If a document is provided the text fields is required and all other fields will be preserved in the response.
-
-The total max chunks (length of documents * max_chunks_per_doc) must be less than 10000.
+**documents:** `typing.Sequence[str]` 
 
-We recommend a maximum of 1,000 documents for optimal endpoint performance.
-
-</dd>
-</dl>
+A list of texts that will be compared to the `query`.
+For optimal performance we recommend against sending more than 1,000 documents in a single request.
 
-<dl>
-<dd>
+**Note**: long documents will automatically be truncated to the value of `max_tokens_per_doc`.
 
-**top_n:** `typing.Optional[int]` — The number of most relevant documents or indices to return, defaults to the length of the documents
+**Note**: structured data should be formatted as YAML strings for best performance.  
 
 </dd>
 </dl>
 
 <dl>
 <dd>
 
-**rank_fields:** `typing.Optional[typing.Sequence[str]]` — If a JSON object is provided, you can specify which keys you would like to have considered for reranking. The model will rerank based on order of the fields passed in (i.e. rank_fields=['title','author','text'] will rerank using the values in title, author, text  sequentially. If the length of title, author, and text exceeds the context length of the model, the chunking will not re-consider earlier fields). If not provided, the model will use the default text field for ranking.
+**top_n:** `typing.Optional[int]` — Limits the number of returned rerank results to the specified value. If not passed, all the rerank results will be returned.
 
 </dd>
 </dl>
@@ -3115,7 +3144,7 @@ We recommend a maximum of 1,000 documents for optimal endpoint performance.
 <dl>
 <dd>
 
-**max_chunks_per_doc:** `typing.Optional[int]` — The maximum number of chunks to produce internally from a document
+**max_tokens_per_doc:** `typing.Optional[int]` — Defaults to `4096`. Long documents will be automatically truncated to the specified number of tokens.
 
 </dd>
 </dl>
@@ -5043,7 +5072,7 @@ client.finetuning.update_finetuned_model(
 <dl>
 <dd>
 
-**last_used:** `typing.Optional[dt.datetime]` — Timestamp for the latest request to this fine-tuned model.
+**last_used:** `typing.Optional[dt.datetime]` — Deprecated: Timestamp for the latest request to this fine-tuned model.
 
 </dd>
 </dl>

src/cohere/__init__.py

@@ -106,6 +106,7 @@
     DatasetType,
     DatasetValidationStatus,
     DebugStreamedChatResponse,
+    DebugStreamedChatResponseV2,
     DeleteConnectorResponse,
     DetokenizeResponse,
     Document,
@@ -263,7 +264,6 @@
     V2ChatStreamRequestDocumentsItem,
     V2ChatStreamRequestSafetyMode,
     V2EmbedRequestTruncate,
-    V2RerankRequestDocumentsItem,
     V2RerankResponse,
     V2RerankResponseResultsItem,
     V2RerankResponseResultsItemDocument,
@@ -391,6 +391,7 @@
     "DatasetsGetUsageResponse",
     "DatasetsListResponse",
     "DebugStreamedChatResponse",
+    "DebugStreamedChatResponseV2",
     "DeleteConnectorResponse",
     "DetokenizeResponse",
     "Document",
@@ -528,7 +529,6 @@
     "V2ChatStreamRequestDocumentsItem",
     "V2ChatStreamRequestSafetyMode",
     "V2EmbedRequestTruncate",
-    "V2RerankRequestDocumentsItem",
     "V2RerankResponse",
     "V2RerankResponseResultsItem",
     "V2RerankResponseResultsItemDocument",

src/cohere/core/client_wrapper.py

@@ -24,7 +24,7 @@ def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "cohere",
-            "X-Fern-SDK-Version": "5.11.4",
+            "X-Fern-SDK-Version": "5.12.0",
         }
         if self._client_name is not None:
             headers["X-Client-Name"] = self._client_name

src/cohere/finetuning/client.py

@@ -543,7 +543,7 @@ def update_finetuned_model(
             Timestamp for the completed fine-tuning.
 
         last_used : typing.Optional[dt.datetime]
-            Timestamp for the latest request to this fine-tuned model.
+            Deprecated: Timestamp for the latest request to this fine-tuned model.
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
@@ -1468,7 +1468,7 @@ async def update_finetuned_model(
             Timestamp for the completed fine-tuning.
 
         last_used : typing.Optional[dt.datetime]
-            Timestamp for the latest request to this fine-tuned model.
+            Deprecated: Timestamp for the latest request to this fine-tuned model.
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.

src/cohere/finetuning/finetuning/types/finetuned_model.py

@@ -61,7 +61,7 @@ class FinetunedModel(UncheckedBaseModel):
 
     last_used: typing.Optional[dt.datetime] = pydantic.Field(default=None)
     """
-    read-only. Timestamp for the latest request to this fine-tuned model.
+    read-only. Deprecated: Timestamp for the latest request to this fine-tuned model.
     """
 
     if IS_PYDANTIC_V2:

src/cohere/types/__init__.py

@@ -111,6 +111,7 @@
 from .detokenize_response import DetokenizeResponse
 from .document import Document
 from .document_content import DocumentContent
+from .document_source import DocumentSource
 from .embed_by_type_response import EmbedByTypeResponse
 from .embed_by_type_response_embeddings import EmbedByTypeResponseEmbeddings
 from .embed_floats_response import EmbedFloatsResponse
@@ -188,6 +189,7 @@
     ContentDeltaStreamedChatResponseV2,
     ContentEndStreamedChatResponseV2,
     ContentStartStreamedChatResponseV2,
+    DebugStreamedChatResponseV2,
     MessageEndStreamedChatResponseV2,
     MessageStartStreamedChatResponseV2,
     StreamedChatResponseV2,
@@ -200,8 +202,12 @@
 from .summarize_request_format import SummarizeRequestFormat
 from .summarize_request_length import SummarizeRequestLength
 from .summarize_response import SummarizeResponse
+from .system_message import SystemMessage
 from .system_message_content import SystemMessageContent
 from .system_message_content_item import SystemMessageContentItem, TextSystemMessageContentItem
+from .text_content import TextContent
+from .text_response_format import TextResponseFormat
+from .text_response_format_v2 import TextResponseFormatV2
 from .tokenize_response import TokenizeResponse
 from .too_many_requests_error_body import TooManyRequestsErrorBody
 from .tool import Tool
@@ -210,17 +216,20 @@
 from .tool_call_v2 import ToolCallV2
 from .tool_call_v2function import ToolCallV2Function
 from .tool_content import DocumentToolContent, TextToolContent, ToolContent
+from .tool_message import ToolMessage
 from .tool_message_v2 import ToolMessageV2
 from .tool_message_v2content import ToolMessageV2Content
 from .tool_parameter_definitions_value import ToolParameterDefinitionsValue
 from .tool_result import ToolResult
+from .tool_source import ToolSource
 from .tool_v2 import ToolV2
 from .tool_v2function import ToolV2Function
 from .unprocessable_entity_error_body import UnprocessableEntityErrorBody
 from .update_connector_response import UpdateConnectorResponse
 from .usage import Usage
 from .usage_billed_units import UsageBilledUnits
 from .usage_tokens import UsageTokens
+from .user_message import UserMessage
 from .user_message_content import UserMessageContent
 
 __all__ = [
@@ -329,6 +338,7 @@
     "DatasetType",
     "DatasetValidationStatus",
     "DebugStreamedChatResponse",
+    "DebugStreamedChatResponseV2",
     "DeleteConnectorResponse",
     "DetokenizeResponse",
     "Document",

src/cohere/types/streamed_chat_response_v2.py

@@ -213,6 +213,23 @@ class Config:
             extra = pydantic.Extra.allow
 
 
+class DebugStreamedChatResponseV2(UncheckedBaseModel):
+    """
+    StreamedChatResponse is returned in streaming mode (specified with `stream=True` in the request).
+    """
+
+    type: typing.Literal["debug"] = "debug"
+    prompt: typing.Optional[str] = None
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow")  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            smart_union = True
+            extra = pydantic.Extra.allow
+
+
 StreamedChatResponseV2 = typing_extensions.Annotated[
     typing.Union[
         MessageStartStreamedChatResponseV2,
@@ -226,6 +243,7 @@ class Config:
         CitationStartStreamedChatResponseV2,
         CitationEndStreamedChatResponseV2,
         MessageEndStreamedChatResponseV2,
+        DebugStreamedChatResponseV2,
     ],
     UnionMetadata(discriminant="type"),
 ]

src/cohere/v2/__init__.py

@@ -6,7 +6,6 @@
     V2ChatStreamRequestDocumentsItem,
     V2ChatStreamRequestSafetyMode,
     V2EmbedRequestTruncate,
-    V2RerankRequestDocumentsItem,
     V2RerankResponse,
     V2RerankResponseResultsItem,
     V2RerankResponseResultsItemDocument,
@@ -18,7 +17,6 @@
     "V2ChatStreamRequestDocumentsItem",
     "V2ChatStreamRequestSafetyMode",
     "V2EmbedRequestTruncate",
-    "V2RerankRequestDocumentsItem",
     "V2RerankResponse",
     "V2RerankResponseResultsItem",
     "V2RerankResponseResultsItemDocument",