mistralai 1.0.0rc2__tar.gz → 1.0.2__tar.gz

{mistralai-1.0.0rc2 → mistralai-1.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mistralai
-Version: 1.0.0rc2
+Version: 1.0.2
 Summary: Python Client SDK for the Mistral AI API.
 Author: Mistral
 Requires-Python: >=3.8,<4.0
@@ -20,15 +20,26 @@ Requires-Dist: requests (>=2.32.3,<3.0.0) ; extra == "gcp"
 Requires-Dist: typing-inspect (>=0.9.0,<0.10.0)
 Description-Content-Type: text/markdown
 
-# mistralai
-
-<div align="left">
-    <a href="https://speakeasyapi.dev/"><img src="https://custom-icon-badges.demolab.com/badge/-Built%20By%20Speakeasy-212015?style=for-the-badge&logoColor=FBE331&logo=speakeasy&labelColor=545454" /></a>
-</div>
+# Mistral Python Client
 
 ## Migration warning
  
-This documentation is for Mistralai SDK v1. You can find more details on how to migrate from v0 to v1 [here](MIGRATION.md)
+This documentation is for Mistral AI SDK v1. You can find more details on how to migrate from v0 to v1 [here](MIGRATION.md)
+
+## API Key Setup
+
+Before you begin, you will need a Mistral AI API key.
+
+1. Get your own Mistral API Key: <https://docs.mistral.ai/#api-access>
+2. Set your Mistral API Key as an environment variable. You only need to do this once.
+
+```bash
+# set Mistral API Key (using zsh for example)
+$ echo 'export MISTRAL_API_KEY=[your_key_here]' >> ~/.zshenv
+
+# reload the environment (or just quit and open a new terminal)
+$ source ~/.zshenv
+```
 
 <!-- Start SDK Installation [installation] -->
 ## SDK Installation
@@ -200,6 +211,12 @@ asyncio.run(main())
 ```
 <!-- End SDK Example Usage [usage] -->
 
+
+### More examples
+
+You can run the examples in the `examples/` directory using `poetry run` or by entering the virtual environment using `poetry shell`.
+
+
 ## Providers' SDKs Example Usage
 
 ### Azure AI
@@ -329,7 +346,7 @@ The documentation for the GCP SDK is available [here](packages/mistralai_gcp/REA
 
 ### [agents](docs/sdks/agents/README.md)
 
-* [complete](docs/sdks/agents/README.md#complete) - Chat Completion
+* [complete](docs/sdks/agents/README.md#complete) - Agents Completion
 * [stream](docs/sdks/agents/README.md#stream) - Stream Agents completion
 
 ### [embeddings](docs/sdks/embeddings/README.md)
@@ -634,7 +651,7 @@ This SDK supports the following security scheme globally:
 | -------------------- | -------------------- | -------------------- | -------------------- |
 | `api_key`            | http                 | HTTP Bearer          | `MISTRAL_API_KEY`    |
 
-To authenticate with the API the `null` parameter must be set when initializing the SDK client instance. For example:
+To authenticate with the API the `api_key` parameter must be set when initializing the SDK client instance. For example:
 ```python
 from mistralai import Mistral
 import os
@@ -656,8 +673,9 @@ if res is not None:
 <!-- Start Debugging [debug] -->
 ## Debugging
 
-To emit debug logs for SDK requests and responses you can pass a logger object directly into your SDK object.
+You can setup your SDK to emit debug logs for SDK requests and responses.
 
+You can pass your own logger class directly into your SDK.
 ```python
 from mistralai import Mistral
 import logging
@@ -665,22 +683,26 @@ import logging
 logging.basicConfig(level=logging.DEBUG)
 s = Mistral(debug_logger=logging.getLogger("mistralai"))
 ```
+
+You can also enable a default debug logger by setting an environment variable `MISTRAL_DEBUG` to true.
 <!-- End Debugging [debug] -->
 
-<!-- Placeholder for Future Speakeasy SDK Sections -->
+<!-- Start IDE Support [idesupport] -->
+## IDE Support
 
-# Development
+### PyCharm
 
-## Maturity
+Generally, the SDK will work well with most IDEs out of the box. However, when using PyCharm, you can enjoy much better integration with Pydantic by installing an additional plugin.
 
-This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage
-to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally
-looking for the latest version.
+- [PyCharm Pydantic Plugin](https://docs.pydantic.dev/latest/integrations/pycharm/)
+<!-- End IDE Support [idesupport] -->
+
+<!-- Placeholder for Future Speakeasy SDK Sections -->
+
+# Development
 
 ## Contributions
 
 While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation. 
 We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release. 
 
-### SDK Created by [Speakeasy](https://docs.speakeasyapi.dev/docs/using-speakeasy/client-sdks)
-

{mistralai-1.0.0rc2 → mistralai-1.0.2}/README.md

@@ -1,12 +1,23 @@
-# mistralai
-
-<div align="left">
-    <a href="https://speakeasyapi.dev/"><img src="https://custom-icon-badges.demolab.com/badge/-Built%20By%20Speakeasy-212015?style=for-the-badge&logoColor=FBE331&logo=speakeasy&labelColor=545454" /></a>
-</div>
+# Mistral Python Client
 
 ## Migration warning
  
-This documentation is for Mistralai SDK v1. You can find more details on how to migrate from v0 to v1 [here](MIGRATION.md)
+This documentation is for Mistral AI SDK v1. You can find more details on how to migrate from v0 to v1 [here](MIGRATION.md)
+
+## API Key Setup
+
+Before you begin, you will need a Mistral AI API key.
+
+1. Get your own Mistral API Key: <https://docs.mistral.ai/#api-access>
+2. Set your Mistral API Key as an environment variable. You only need to do this once.
+
+```bash
+# set Mistral API Key (using zsh for example)
+$ echo 'export MISTRAL_API_KEY=[your_key_here]' >> ~/.zshenv
+
+# reload the environment (or just quit and open a new terminal)
+$ source ~/.zshenv
+```
 
 <!-- Start SDK Installation [installation] -->
 ## SDK Installation
@@ -178,6 +189,12 @@ asyncio.run(main())
 ```
 <!-- End SDK Example Usage [usage] -->
 
+
+### More examples
+
+You can run the examples in the `examples/` directory using `poetry run` or by entering the virtual environment using `poetry shell`.
+
+
 ## Providers' SDKs Example Usage
 
 ### Azure AI
@@ -307,7 +324,7 @@ The documentation for the GCP SDK is available [here](packages/mistralai_gcp/REA
 
 ### [agents](docs/sdks/agents/README.md)
 
-* [complete](docs/sdks/agents/README.md#complete) - Chat Completion
+* [complete](docs/sdks/agents/README.md#complete) - Agents Completion
 * [stream](docs/sdks/agents/README.md#stream) - Stream Agents completion
 
 ### [embeddings](docs/sdks/embeddings/README.md)
@@ -612,7 +629,7 @@ This SDK supports the following security scheme globally:
 | -------------------- | -------------------- | -------------------- | -------------------- |
 | `api_key`            | http                 | HTTP Bearer          | `MISTRAL_API_KEY`    |
 
-To authenticate with the API the `null` parameter must be set when initializing the SDK client instance. For example:
+To authenticate with the API the `api_key` parameter must be set when initializing the SDK client instance. For example:
 ```python
 from mistralai import Mistral
 import os
@@ -634,8 +651,9 @@ if res is not None:
 <!-- Start Debugging [debug] -->
 ## Debugging
 
-To emit debug logs for SDK requests and responses you can pass a logger object directly into your SDK object.
+You can setup your SDK to emit debug logs for SDK requests and responses.
 
+You can pass your own logger class directly into your SDK.
 ```python
 from mistralai import Mistral
 import logging
@@ -643,21 +661,25 @@ import logging
 logging.basicConfig(level=logging.DEBUG)
 s = Mistral(debug_logger=logging.getLogger("mistralai"))
 ```
+
+You can also enable a default debug logger by setting an environment variable `MISTRAL_DEBUG` to true.
 <!-- End Debugging [debug] -->
 
-<!-- Placeholder for Future Speakeasy SDK Sections -->
+<!-- Start IDE Support [idesupport] -->
+## IDE Support
 
-# Development
+### PyCharm
 
-## Maturity
+Generally, the SDK will work well with most IDEs out of the box. However, when using PyCharm, you can enjoy much better integration with Pydantic by installing an additional plugin.
 
-This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage
-to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally
-looking for the latest version.
+- [PyCharm Pydantic Plugin](https://docs.pydantic.dev/latest/integrations/pycharm/)
+<!-- End IDE Support [idesupport] -->
+
+<!-- Placeholder for Future Speakeasy SDK Sections -->
+
+# Development
 
 ## Contributions
 
 While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation. 
 We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release. 
-
-### SDK Created by [Speakeasy](https://docs.speakeasyapi.dev/docs/using-speakeasy/client-sdks)

{mistralai-1.0.0rc2 → mistralai-1.0.2}/packages/mistralai_azure/src/mistralai_azure/models/__init__.py

@@ -11,18 +11,18 @@ from .completionresponsestreamchoice import CompletionResponseStreamChoice, Comp
 from .contentchunk import ContentChunk, ContentChunkTypedDict
 from .deltamessage import DeltaMessage, DeltaMessageTypedDict
 from .function import Function, FunctionTypedDict
-from .functioncall import FunctionCall, FunctionCallTypedDict
+from .functioncall import Arguments, ArgumentsTypedDict, FunctionCall, FunctionCallTypedDict
 from .httpvalidationerror import HTTPValidationError, HTTPValidationErrorData
 from .responseformat import ResponseFormat, ResponseFormatTypedDict, ResponseFormats
 from .sdkerror import SDKError
 from .security import Security, SecurityTypedDict
 from .systemmessage import Content, ContentTypedDict, Role, SystemMessage, SystemMessageTypedDict
 from .textchunk import TextChunk, TextChunkTypedDict
-from .tool import Tool, ToolTypedDict
-from .toolcall import ToolCall, ToolCallTypedDict
+from .tool import Tool, ToolToolTypes, ToolTypedDict
+from .toolcall import ToolCall, ToolCallTypedDict, ToolTypes
 from .toolmessage import ToolMessage, ToolMessageRole, ToolMessageTypedDict
 from .usageinfo import UsageInfo, UsageInfoTypedDict
 from .usermessage import UserMessage, UserMessageContent, UserMessageContentTypedDict, UserMessageRole, UserMessageTypedDict
 from .validationerror import Loc, LocTypedDict, ValidationError, ValidationErrorTypedDict
 
-__all__ = ["AssistantMessage", "AssistantMessageRole", "AssistantMessageTypedDict", "ChatCompletionChoice", "ChatCompletionChoiceFinishReason", "ChatCompletionChoiceTypedDict", "ChatCompletionRequest", "ChatCompletionRequestMessages", "ChatCompletionRequestMessagesTypedDict", "ChatCompletionRequestStop", "ChatCompletionRequestStopTypedDict", "ChatCompletionRequestToolChoice", "ChatCompletionRequestTypedDict", "ChatCompletionResponse", "ChatCompletionResponseTypedDict", "ChatCompletionStreamRequest", "ChatCompletionStreamRequestTypedDict", "CompletionChunk", "CompletionChunkTypedDict", "CompletionEvent", "CompletionEventTypedDict", "CompletionResponseStreamChoice", "CompletionResponseStreamChoiceTypedDict", "Content", "ContentChunk", "ContentChunkTypedDict", "ContentTypedDict", "DeltaMessage", "DeltaMessageTypedDict", "FinishReason", "Function", "FunctionCall", "FunctionCallTypedDict", "FunctionTypedDict", "HTTPValidationError", "HTTPValidationErrorData", "Loc", "LocTypedDict", "Messages", "MessagesTypedDict", "ResponseFormat", "ResponseFormatTypedDict", "ResponseFormats", "Role", "SDKError", "Security", "SecurityTypedDict", "Stop", "StopTypedDict", "SystemMessage", "SystemMessageTypedDict", "TextChunk", "TextChunkTypedDict", "Tool", "ToolCall", "ToolCallTypedDict", "ToolChoice", "ToolMessage", "ToolMessageRole", "ToolMessageTypedDict", "ToolTypedDict", "UsageInfo", "UsageInfoTypedDict", "UserMessage", "UserMessageContent", "UserMessageContentTypedDict", "UserMessageRole", "UserMessageTypedDict", "ValidationError", "ValidationErrorTypedDict"]
+__all__ = ["Arguments", "ArgumentsTypedDict", "AssistantMessage", "AssistantMessageRole", "AssistantMessageTypedDict", "ChatCompletionChoice", "ChatCompletionChoiceFinishReason", "ChatCompletionChoiceTypedDict", "ChatCompletionRequest", "ChatCompletionRequestMessages", "ChatCompletionRequestMessagesTypedDict", "ChatCompletionRequestStop", "ChatCompletionRequestStopTypedDict", "ChatCompletionRequestToolChoice", "ChatCompletionRequestTypedDict", "ChatCompletionResponse", "ChatCompletionResponseTypedDict", "ChatCompletionStreamRequest", "ChatCompletionStreamRequestTypedDict", "CompletionChunk", "CompletionChunkTypedDict", "CompletionEvent", "CompletionEventTypedDict", "CompletionResponseStreamChoice", "CompletionResponseStreamChoiceTypedDict", "Content", "ContentChunk", "ContentChunkTypedDict", "ContentTypedDict", "DeltaMessage", "DeltaMessageTypedDict", "FinishReason", "Function", "FunctionCall", "FunctionCallTypedDict", "FunctionTypedDict", "HTTPValidationError", "HTTPValidationErrorData", "Loc", "LocTypedDict", "Messages", "MessagesTypedDict", "ResponseFormat", "ResponseFormatTypedDict", "ResponseFormats", "Role", "SDKError", "Security", "SecurityTypedDict", "Stop", "StopTypedDict", "SystemMessage", "SystemMessageTypedDict", "TextChunk", "TextChunkTypedDict", "Tool", "ToolCall", "ToolCallTypedDict", "ToolChoice", "ToolMessage", "ToolMessageRole", "ToolMessageTypedDict", "ToolToolTypes", "ToolTypedDict", "ToolTypes", "UsageInfo", "UsageInfoTypedDict", "UserMessage", "UserMessageContent", "UserMessageContentTypedDict", "UserMessageRole", "UserMessageTypedDict", "ValidationError", "ValidationErrorTypedDict"]

{mistralai-1.0.0rc2 → mistralai-1.0.2}/packages/mistralai_azure/src/mistralai_azure/models/chatcompletionchoice.py

@@ -3,20 +3,19 @@
 from __future__ import annotations
 from .assistantmessage import AssistantMessage, AssistantMessageTypedDict
 from mistralai_azure.types import BaseModel
-from typing import Literal, Optional, TypedDict
-from typing_extensions import NotRequired
+from typing import Literal, TypedDict
 
 
 ChatCompletionChoiceFinishReason = Literal["stop", "length", "model_length", "error", "tool_calls"]
 
 class ChatCompletionChoiceTypedDict(TypedDict):
     index: int
+    message: AssistantMessageTypedDict
     finish_reason: ChatCompletionChoiceFinishReason
-    message: NotRequired[AssistantMessageTypedDict]
     
 
 class ChatCompletionChoice(BaseModel):
     index: int
+    message: AssistantMessage
     finish_reason: ChatCompletionChoiceFinishReason
-    message: Optional[AssistantMessage] = None
     

{mistralai-1.0.0rc2 → mistralai-1.0.2}/packages/mistralai_azure/src/mistralai_azure/models/deltamessage.py

@@ -4,25 +4,25 @@ from __future__ import annotations
 from .toolcall import ToolCall, ToolCallTypedDict
 from mistralai_azure.types import BaseModel, Nullable, OptionalNullable, UNSET, UNSET_SENTINEL
 from pydantic import model_serializer
-from typing import Optional, TypedDict
+from typing import List, Optional, TypedDict
 from typing_extensions import NotRequired
 
 
 class DeltaMessageTypedDict(TypedDict):
     role: NotRequired[str]
-    content: NotRequired[str]
-    tool_calls: NotRequired[Nullable[ToolCallTypedDict]]
+    content: NotRequired[Nullable[str]]
+    tool_calls: NotRequired[Nullable[List[ToolCallTypedDict]]]
     
 
 class DeltaMessage(BaseModel):
     role: Optional[str] = None
-    content: Optional[str] = None
-    tool_calls: OptionalNullable[ToolCall] = UNSET
+    content: OptionalNullable[str] = UNSET
+    tool_calls: OptionalNullable[List[ToolCall]] = UNSET
     
     @model_serializer(mode="wrap")
     def serialize_model(self, handler):
         optional_fields = ["role", "content", "tool_calls"]
-        nullable_fields = ["tool_calls"]
+        nullable_fields = ["content", "tool_calls"]
         null_default_fields = []
 
         serialized = handler(self)

{mistralai-1.0.0rc2 → mistralai-1.0.2}/packages/mistralai_azure/src/mistralai_azure/models/functioncall.py

@@ -2,15 +2,21 @@
 
 from __future__ import annotations
 from mistralai_azure.types import BaseModel
-from typing import TypedDict
+from typing import Any, Dict, TypedDict, Union
+
+
+ArgumentsTypedDict = Union[Dict[str, Any], str]
+
+
+Arguments = Union[Dict[str, Any], str]
 
 
 class FunctionCallTypedDict(TypedDict):
     name: str
-    arguments: str
+    arguments: ArgumentsTypedDict
     
 
 class FunctionCall(BaseModel):
     name: str
-    arguments: str
+    arguments: Arguments
     

mistralai-1.0.2/packages/mistralai_azure/src/mistralai_azure/models/tool.py

@@ -0,0 +1,22 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from __future__ import annotations
+from .function import Function, FunctionTypedDict
+from mistralai_azure.types import BaseModel, UnrecognizedStr
+from mistralai_azure.utils import validate_open_enum
+from pydantic.functional_validators import PlainValidator
+from typing import Literal, Optional, TypedDict, Union
+from typing_extensions import Annotated, NotRequired
+
+
+ToolToolTypes = Union[Literal["function"], UnrecognizedStr]
+
+class ToolTypedDict(TypedDict):
+    function: FunctionTypedDict
+    type: NotRequired[ToolToolTypes]
+    
+
+class Tool(BaseModel):
+    function: Function
+    type: Annotated[Optional[ToolToolTypes], PlainValidator(validate_open_enum(False))] = "function"
+    

{mistralai-1.0.0rc2 → mistralai-1.0.2}/packages/mistralai_azure/src/mistralai_azure/models/toolcall.py

@@ -2,19 +2,23 @@
 
 from __future__ import annotations
 from .functioncall import FunctionCall, FunctionCallTypedDict
-from mistralai_azure.types import BaseModel
-import pydantic
-from typing import Final, Optional, TypedDict
+from mistralai_azure.types import BaseModel, UnrecognizedStr
+from mistralai_azure.utils import validate_open_enum
+from pydantic.functional_validators import PlainValidator
+from typing import Literal, Optional, TypedDict, Union
 from typing_extensions import Annotated, NotRequired
 
 
+ToolTypes = Union[Literal["function"], UnrecognizedStr]
+
 class ToolCallTypedDict(TypedDict):
     function: FunctionCallTypedDict
     id: NotRequired[str]
+    type: NotRequired[ToolTypes]
     
 
 class ToolCall(BaseModel):
     function: FunctionCall
     id: Optional[str] = "null"
-    TYPE: Annotated[Final[Optional[str]], pydantic.Field(alias="type")] = "function" # type: ignore
+    type: Annotated[Optional[ToolTypes], PlainValidator(validate_open_enum(False))] = "function"
     

{mistralai-1.0.0rc2 → mistralai-1.0.2}/packages/mistralai_azure/src/mistralai_azure/sdkconfiguration.py

@@ -29,9 +29,9 @@ class SDKConfiguration:
     server: Optional[str] = ""
     language: str = "python"
     openapi_doc_version: str = "0.0.2"
-    sdk_version: str = "1.0.0-alpha.13"
-    gen_version: str = "2.386.0"
-    user_agent: str = "speakeasy-sdk/python 1.0.0-alpha.13 2.386.0 0.0.2 mistralai_azure"
+    sdk_version: str = "1.0.1"
+    gen_version: str = "2.399.0"
+    user_agent: str = "speakeasy-sdk/python 1.0.1 2.399.0 0.0.2 mistralai_azure"
     retry_config: OptionalNullable[RetryConfig] = Field(default_factory=lambda: UNSET)
     timeout_ms: Optional[int] = None
 

{mistralai-1.0.0rc2 → mistralai-1.0.2}/packages/mistralai_gcp/src/mistralai_gcp/chat.py

@@ -33,7 +33,7 @@ class Chat(BaseSDK):
 
         Mistral AI provides the ability to stream responses back to a client in order to allow partial results for certain requests. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON.
 
-        :param model: ID of the model to use. You can use the [List Available Models](/api#operation/listModels) API to see all of your available models, or see our [Model overview](/models) for model descriptions.
+        :param model: ID of the model to use. You can use the [List Available Models](/api/#tag/models/operation/list_models_v1_models_get) API to see all of your available models, or see our [Model overview](/models) for model descriptions.
         :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
         :param temperature: What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
         :param top_p: Nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
@@ -146,7 +146,7 @@ class Chat(BaseSDK):
 
         Mistral AI provides the ability to stream responses back to a client in order to allow partial results for certain requests. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON.
 
-        :param model: ID of the model to use. You can use the [List Available Models](/api#operation/listModels) API to see all of your available models, or see our [Model overview](/models) for model descriptions.
+        :param model: ID of the model to use. You can use the [List Available Models](/api/#tag/models/operation/list_models_v1_models_get) API to see all of your available models, or see our [Model overview](/models) for model descriptions.
         :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
         :param temperature: What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
         :param top_p: Nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
@@ -257,7 +257,7 @@ class Chat(BaseSDK):
     ) -> Optional[models.ChatCompletionResponse]:
         r"""Chat Completion
 
-        :param model: ID of the model to use. You can use the [List Available Models](/api#operation/listModels) API to see all of your available models, or see our [Model overview](/models) for model descriptions.
+        :param model: ID of the model to use. You can use the [List Available Models](/api/#tag/models/operation/list_models_v1_models_get) API to see all of your available models, or see our [Model overview](/models) for model descriptions.
         :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
         :param temperature: What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
         :param top_p: Nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.
@@ -367,7 +367,7 @@ class Chat(BaseSDK):
     ) -> Optional[models.ChatCompletionResponse]:
         r"""Chat Completion
 
-        :param model: ID of the model to use. You can use the [List Available Models](/api#operation/listModels) API to see all of your available models, or see our [Model overview](/models) for model descriptions.
+        :param model: ID of the model to use. You can use the [List Available Models](/api/#tag/models/operation/list_models_v1_models_get) API to see all of your available models, or see our [Model overview](/models) for model descriptions.
         :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
         :param temperature: What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both.
         :param top_p: Nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.

{mistralai-1.0.0rc2 → mistralai-1.0.2}/packages/mistralai_gcp/src/mistralai_gcp/models/__init__.py

@@ -14,18 +14,18 @@ from .fimcompletionrequest import FIMCompletionRequest, FIMCompletionRequestStop
 from .fimcompletionresponse import FIMCompletionResponse, FIMCompletionResponseTypedDict
 from .fimcompletionstreamrequest import FIMCompletionStreamRequest, FIMCompletionStreamRequestStop, FIMCompletionStreamRequestStopTypedDict, FIMCompletionStreamRequestTypedDict
 from .function import Function, FunctionTypedDict
-from .functioncall import FunctionCall, FunctionCallTypedDict
+from .functioncall import Arguments, ArgumentsTypedDict, FunctionCall, FunctionCallTypedDict
 from .httpvalidationerror import HTTPValidationError, HTTPValidationErrorData
 from .responseformat import ResponseFormat, ResponseFormatTypedDict, ResponseFormats
 from .sdkerror import SDKError
 from .security import Security, SecurityTypedDict
 from .systemmessage import Content, ContentTypedDict, Role, SystemMessage, SystemMessageTypedDict
 from .textchunk import TextChunk, TextChunkTypedDict
-from .tool import Tool, ToolTypedDict
-from .toolcall import ToolCall, ToolCallTypedDict
+from .tool import Tool, ToolToolTypes, ToolTypedDict
+from .toolcall import ToolCall, ToolCallTypedDict, ToolTypes
 from .toolmessage import ToolMessage, ToolMessageRole, ToolMessageTypedDict
 from .usageinfo import UsageInfo, UsageInfoTypedDict
 from .usermessage import UserMessage, UserMessageContent, UserMessageContentTypedDict, UserMessageRole, UserMessageTypedDict
 from .validationerror import Loc, LocTypedDict, ValidationError, ValidationErrorTypedDict
 
-__all__ = ["AssistantMessage", "AssistantMessageRole", "AssistantMessageTypedDict", "ChatCompletionChoice", "ChatCompletionChoiceFinishReason", "ChatCompletionChoiceTypedDict", "ChatCompletionRequest", "ChatCompletionRequestMessages", "ChatCompletionRequestMessagesTypedDict", "ChatCompletionRequestStop", "ChatCompletionRequestStopTypedDict", "ChatCompletionRequestToolChoice", "ChatCompletionRequestTypedDict", "ChatCompletionResponse", "ChatCompletionResponseTypedDict", "ChatCompletionStreamRequest", "ChatCompletionStreamRequestTypedDict", "CompletionChunk", "CompletionChunkTypedDict", "CompletionEvent", "CompletionEventTypedDict", "CompletionResponseStreamChoice", "CompletionResponseStreamChoiceTypedDict", "Content", "ContentChunk", "ContentChunkTypedDict", "ContentTypedDict", "DeltaMessage", "DeltaMessageTypedDict", "FIMCompletionRequest", "FIMCompletionRequestStop", "FIMCompletionRequestStopTypedDict", "FIMCompletionRequestTypedDict", "FIMCompletionResponse", "FIMCompletionResponseTypedDict", "FIMCompletionStreamRequest", "FIMCompletionStreamRequestStop", "FIMCompletionStreamRequestStopTypedDict", "FIMCompletionStreamRequestTypedDict", "FinishReason", "Function", "FunctionCall", "FunctionCallTypedDict", "FunctionTypedDict", "HTTPValidationError", "HTTPValidationErrorData", "Loc", "LocTypedDict", "Messages", "MessagesTypedDict", "ResponseFormat", "ResponseFormatTypedDict", "ResponseFormats", "Role", "SDKError", "Security", "SecurityTypedDict", "Stop", "StopTypedDict", "SystemMessage", "SystemMessageTypedDict", "TextChunk", "TextChunkTypedDict", "Tool", "ToolCall", "ToolCallTypedDict", "ToolChoice", "ToolMessage", "ToolMessageRole", "ToolMessageTypedDict", "ToolTypedDict", "UsageInfo", "UsageInfoTypedDict", "UserMessage", "UserMessageContent", "UserMessageContentTypedDict", "UserMessageRole", "UserMessageTypedDict", "ValidationError", "ValidationErrorTypedDict"]
+__all__ = ["Arguments", "ArgumentsTypedDict", "AssistantMessage", "AssistantMessageRole", "AssistantMessageTypedDict", "ChatCompletionChoice", "ChatCompletionChoiceFinishReason", "ChatCompletionChoiceTypedDict", "ChatCompletionRequest", "ChatCompletionRequestMessages", "ChatCompletionRequestMessagesTypedDict", "ChatCompletionRequestStop", "ChatCompletionRequestStopTypedDict", "ChatCompletionRequestToolChoice", "ChatCompletionRequestTypedDict", "ChatCompletionResponse", "ChatCompletionResponseTypedDict", "ChatCompletionStreamRequest", "ChatCompletionStreamRequestTypedDict", "CompletionChunk", "CompletionChunkTypedDict", "CompletionEvent", "CompletionEventTypedDict", "CompletionResponseStreamChoice", "CompletionResponseStreamChoiceTypedDict", "Content", "ContentChunk", "ContentChunkTypedDict", "ContentTypedDict", "DeltaMessage", "DeltaMessageTypedDict", "FIMCompletionRequest", "FIMCompletionRequestStop", "FIMCompletionRequestStopTypedDict", "FIMCompletionRequestTypedDict", "FIMCompletionResponse", "FIMCompletionResponseTypedDict", "FIMCompletionStreamRequest", "FIMCompletionStreamRequestStop", "FIMCompletionStreamRequestStopTypedDict", "FIMCompletionStreamRequestTypedDict", "FinishReason", "Function", "FunctionCall", "FunctionCallTypedDict", "FunctionTypedDict", "HTTPValidationError", "HTTPValidationErrorData", "Loc", "LocTypedDict", "Messages", "MessagesTypedDict", "ResponseFormat", "ResponseFormatTypedDict", "ResponseFormats", "Role", "SDKError", "Security", "SecurityTypedDict", "Stop", "StopTypedDict", "SystemMessage", "SystemMessageTypedDict", "TextChunk", "TextChunkTypedDict", "Tool", "ToolCall", "ToolCallTypedDict", "ToolChoice", "ToolMessage", "ToolMessageRole", "ToolMessageTypedDict", "ToolToolTypes", "ToolTypedDict", "ToolTypes", "UsageInfo", "UsageInfoTypedDict", "UserMessage", "UserMessageContent", "UserMessageContentTypedDict", "UserMessageRole", "UserMessageTypedDict", "ValidationError", "ValidationErrorTypedDict"]

{mistralai-1.0.0rc2 → mistralai-1.0.2}/packages/mistralai_gcp/src/mistralai_gcp/models/chatcompletionchoice.py

@@ -3,20 +3,19 @@
 from __future__ import annotations
 from .assistantmessage import AssistantMessage, AssistantMessageTypedDict
 from mistralai_gcp.types import BaseModel
-from typing import Literal, Optional, TypedDict
-from typing_extensions import NotRequired
+from typing import Literal, TypedDict
 
 
 ChatCompletionChoiceFinishReason = Literal["stop", "length", "model_length", "error", "tool_calls"]
 
 class ChatCompletionChoiceTypedDict(TypedDict):
     index: int
+    message: AssistantMessageTypedDict
     finish_reason: ChatCompletionChoiceFinishReason
-    message: NotRequired[AssistantMessageTypedDict]
     
 
 class ChatCompletionChoice(BaseModel):
     index: int
+    message: AssistantMessage
     finish_reason: ChatCompletionChoiceFinishReason
-    message: Optional[AssistantMessage] = None
     

{mistralai-1.0.0rc2 → mistralai-1.0.2}/packages/mistralai_gcp/src/mistralai_gcp/models/chatcompletionrequest.py

@@ -14,11 +14,25 @@ from typing import List, Literal, Optional, TypedDict, Union
 from typing_extensions import Annotated, NotRequired
 
 
+ChatCompletionRequestStopTypedDict = Union[str, List[str]]
+r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
+
+
+ChatCompletionRequestStop = Union[str, List[str]]
+r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
+
+
+ChatCompletionRequestMessagesTypedDict = Union[SystemMessageTypedDict, UserMessageTypedDict, AssistantMessageTypedDict, ToolMessageTypedDict]
+
+
+ChatCompletionRequestMessages = Annotated[Union[Annotated[AssistantMessage, Tag("assistant")], Annotated[SystemMessage, Tag("system")], Annotated[ToolMessage, Tag("tool")], Annotated[UserMessage, Tag("user")]], Discriminator(lambda m: get_discriminator(m, "role", "role"))]
+
+
 ChatCompletionRequestToolChoice = Literal["auto", "none", "any"]
 
 class ChatCompletionRequestTypedDict(TypedDict):
     model: Nullable[str]
-    r"""ID of the model to use. You can use the [List Available Models](/api#operation/listModels) API to see all of your available models, or see our [Model overview](/models) for model descriptions."""
+    r"""ID of the model to use. You can use the [List Available Models](/api/#tag/models/operation/list_models_v1_models_get) API to see all of your available models, or see our [Model overview](/models) for model descriptions."""
     messages: List[ChatCompletionRequestMessagesTypedDict]
     r"""The prompt(s) to generate completions for, encoded as a list of dict with role and content."""
     temperature: NotRequired[float]
@@ -42,7 +56,7 @@ class ChatCompletionRequestTypedDict(TypedDict):
 
 class ChatCompletionRequest(BaseModel):
     model: Nullable[str]
-    r"""ID of the model to use. You can use the [List Available Models](/api#operation/listModels) API to see all of your available models, or see our [Model overview](/models) for model descriptions."""
+    r"""ID of the model to use. You can use the [List Available Models](/api/#tag/models/operation/list_models_v1_models_get) API to see all of your available models, or see our [Model overview](/models) for model descriptions."""
     messages: List[ChatCompletionRequestMessages]
     r"""The prompt(s) to generate completions for, encoded as a list of dict with role and content."""
     temperature: Optional[float] = 0.7
@@ -89,17 +103,3 @@ class ChatCompletionRequest(BaseModel):
 
         return m
         
-
-ChatCompletionRequestStopTypedDict = Union[str, List[str]]
-r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
-
-
-ChatCompletionRequestStop = Union[str, List[str]]
-r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
-
-
-ChatCompletionRequestMessagesTypedDict = Union[SystemMessageTypedDict, UserMessageTypedDict, AssistantMessageTypedDict, ToolMessageTypedDict]
-
-
-ChatCompletionRequestMessages = Annotated[Union[Annotated[AssistantMessage, Tag("assistant")], Annotated[SystemMessage, Tag("system")], Annotated[ToolMessage, Tag("tool")], Annotated[UserMessage, Tag("user")]], Discriminator(lambda m: get_discriminator(m, "role", "role"))]
-

{mistralai-1.0.0rc2 → mistralai-1.0.2}/packages/mistralai_gcp/src/mistralai_gcp/models/chatcompletionstreamrequest.py

@@ -14,11 +14,25 @@ from typing import List, Literal, Optional, TypedDict, Union
 from typing_extensions import Annotated, NotRequired
 
 
+StopTypedDict = Union[str, List[str]]
+r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
+
+
+Stop = Union[str, List[str]]
+r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
+
+
+MessagesTypedDict = Union[SystemMessageTypedDict, UserMessageTypedDict, AssistantMessageTypedDict, ToolMessageTypedDict]
+
+
+Messages = Annotated[Union[Annotated[AssistantMessage, Tag("assistant")], Annotated[SystemMessage, Tag("system")], Annotated[ToolMessage, Tag("tool")], Annotated[UserMessage, Tag("user")]], Discriminator(lambda m: get_discriminator(m, "role", "role"))]
+
+
 ToolChoice = Literal["auto", "none", "any"]
 
 class ChatCompletionStreamRequestTypedDict(TypedDict):
     model: Nullable[str]
-    r"""ID of the model to use. You can use the [List Available Models](/api#operation/listModels) API to see all of your available models, or see our [Model overview](/models) for model descriptions."""
+    r"""ID of the model to use. You can use the [List Available Models](/api/#tag/models/operation/list_models_v1_models_get) API to see all of your available models, or see our [Model overview](/models) for model descriptions."""
     messages: List[MessagesTypedDict]
     r"""The prompt(s) to generate completions for, encoded as a list of dict with role and content."""
     temperature: NotRequired[float]
@@ -41,7 +55,7 @@ class ChatCompletionStreamRequestTypedDict(TypedDict):
 
 class ChatCompletionStreamRequest(BaseModel):
     model: Nullable[str]
-    r"""ID of the model to use. You can use the [List Available Models](/api#operation/listModels) API to see all of your available models, or see our [Model overview](/models) for model descriptions."""
+    r"""ID of the model to use. You can use the [List Available Models](/api/#tag/models/operation/list_models_v1_models_get) API to see all of your available models, or see our [Model overview](/models) for model descriptions."""
     messages: List[Messages]
     r"""The prompt(s) to generate completions for, encoded as a list of dict with role and content."""
     temperature: Optional[float] = 0.7
@@ -87,17 +101,3 @@ class ChatCompletionStreamRequest(BaseModel):
 
         return m
         
-
-StopTypedDict = Union[str, List[str]]
-r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
-
-
-Stop = Union[str, List[str]]
-r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
-
-
-MessagesTypedDict = Union[SystemMessageTypedDict, UserMessageTypedDict, AssistantMessageTypedDict, ToolMessageTypedDict]
-
-
-Messages = Annotated[Union[Annotated[AssistantMessage, Tag("assistant")], Annotated[SystemMessage, Tag("system")], Annotated[ToolMessage, Tag("tool")], Annotated[UserMessage, Tag("user")]], Discriminator(lambda m: get_discriminator(m, "role", "role"))]
-

{mistralai-1.0.0rc2 → mistralai-1.0.2}/packages/mistralai_gcp/src/mistralai_gcp/models/deltamessage.py

@@ -4,25 +4,25 @@ from __future__ import annotations
 from .toolcall import ToolCall, ToolCallTypedDict
 from mistralai_gcp.types import BaseModel, Nullable, OptionalNullable, UNSET, UNSET_SENTINEL
 from pydantic import model_serializer
-from typing import Optional, TypedDict
+from typing import List, Optional, TypedDict
 from typing_extensions import NotRequired
 
 
 class DeltaMessageTypedDict(TypedDict):
     role: NotRequired[str]
-    content: NotRequired[str]
-    tool_calls: NotRequired[Nullable[ToolCallTypedDict]]
+    content: NotRequired[Nullable[str]]
+    tool_calls: NotRequired[Nullable[List[ToolCallTypedDict]]]
     
 
 class DeltaMessage(BaseModel):
     role: Optional[str] = None
-    content: Optional[str] = None
-    tool_calls: OptionalNullable[ToolCall] = UNSET
+    content: OptionalNullable[str] = UNSET
+    tool_calls: OptionalNullable[List[ToolCall]] = UNSET
     
     @model_serializer(mode="wrap")
     def serialize_model(self, handler):
         optional_fields = ["role", "content", "tool_calls"]
-        nullable_fields = ["tool_calls"]
+        nullable_fields = ["content", "tool_calls"]
         null_default_fields = []
 
         serialized = handler(self)