mistralai 1.0.3__py3-none-any.whl → 1.2.0__py3-none-any.whl

mistralai_gcp/models/__init__.py

@@ -1,31 +1,199 @@
 """Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
 
-from .assistantmessage import AssistantMessage, AssistantMessageRole, AssistantMessageTypedDict
-from .chatcompletionchoice import ChatCompletionChoice, ChatCompletionChoiceFinishReason, ChatCompletionChoiceTypedDict
-from .chatcompletionrequest import ChatCompletionRequest, ChatCompletionRequestMessages, ChatCompletionRequestMessagesTypedDict, ChatCompletionRequestStop, ChatCompletionRequestStopTypedDict, ChatCompletionRequestToolChoice, ChatCompletionRequestTypedDict
-from .chatcompletionresponse import ChatCompletionResponse, ChatCompletionResponseTypedDict
-from .chatcompletionstreamrequest import ChatCompletionStreamRequest, ChatCompletionStreamRequestTypedDict, Messages, MessagesTypedDict, Stop, StopTypedDict, ToolChoice
+from .assistantmessage import (
+    AssistantMessage,
+    AssistantMessageContent,
+    AssistantMessageContentTypedDict,
+    AssistantMessageRole,
+    AssistantMessageTypedDict,
+)
+from .chatcompletionchoice import (
+    ChatCompletionChoice,
+    ChatCompletionChoiceFinishReason,
+    ChatCompletionChoiceTypedDict,
+)
+from .chatcompletionrequest import (
+    ChatCompletionRequest,
+    ChatCompletionRequestMessages,
+    ChatCompletionRequestMessagesTypedDict,
+    ChatCompletionRequestStop,
+    ChatCompletionRequestStopTypedDict,
+    ChatCompletionRequestToolChoice,
+    ChatCompletionRequestToolChoiceTypedDict,
+    ChatCompletionRequestTypedDict,
+)
+from .chatcompletionresponse import (
+    ChatCompletionResponse,
+    ChatCompletionResponseTypedDict,
+)
+from .chatcompletionstreamrequest import (
+    ChatCompletionStreamRequest,
+    ChatCompletionStreamRequestToolChoice,
+    ChatCompletionStreamRequestToolChoiceTypedDict,
+    ChatCompletionStreamRequestTypedDict,
+    Messages,
+    MessagesTypedDict,
+    Stop,
+    StopTypedDict,
+)
 from .completionchunk import CompletionChunk, CompletionChunkTypedDict
 from .completionevent import CompletionEvent, CompletionEventTypedDict
-from .completionresponsestreamchoice import CompletionResponseStreamChoice, CompletionResponseStreamChoiceTypedDict, FinishReason
+from .completionresponsestreamchoice import (
+    CompletionResponseStreamChoice,
+    CompletionResponseStreamChoiceTypedDict,
+    FinishReason,
+)
 from .contentchunk import ContentChunk, ContentChunkTypedDict
-from .deltamessage import DeltaMessage, DeltaMessageTypedDict
-from .fimcompletionrequest import FIMCompletionRequest, FIMCompletionRequestStop, FIMCompletionRequestStopTypedDict, FIMCompletionRequestTypedDict
+from .deltamessage import Content, ContentTypedDict, DeltaMessage, DeltaMessageTypedDict
+from .fimcompletionrequest import (
+    FIMCompletionRequest,
+    FIMCompletionRequestStop,
+    FIMCompletionRequestStopTypedDict,
+    FIMCompletionRequestTypedDict,
+)
 from .fimcompletionresponse import FIMCompletionResponse, FIMCompletionResponseTypedDict
-from .fimcompletionstreamrequest import FIMCompletionStreamRequest, FIMCompletionStreamRequestStop, FIMCompletionStreamRequestStopTypedDict, FIMCompletionStreamRequestTypedDict
+from .fimcompletionstreamrequest import (
+    FIMCompletionStreamRequest,
+    FIMCompletionStreamRequestStop,
+    FIMCompletionStreamRequestStopTypedDict,
+    FIMCompletionStreamRequestTypedDict,
+)
 from .function import Function, FunctionTypedDict
-from .functioncall import Arguments, ArgumentsTypedDict, FunctionCall, FunctionCallTypedDict
+from .functioncall import (
+    Arguments,
+    ArgumentsTypedDict,
+    FunctionCall,
+    FunctionCallTypedDict,
+)
+from .functionname import FunctionName, FunctionNameTypedDict
 from .httpvalidationerror import HTTPValidationError, HTTPValidationErrorData
-from .responseformat import ResponseFormat, ResponseFormatTypedDict, ResponseFormats
+from .responseformat import ResponseFormat, ResponseFormatTypedDict
+from .responseformats import 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, ToolToolTypes, ToolTypedDict
-from .toolcall import ToolCall, ToolCallTypedDict, ToolTypes
+from .systemmessage import (
+    Role,
+    SystemMessage,
+    SystemMessageContent,
+    SystemMessageContentTypedDict,
+    SystemMessageTypedDict,
+)
+from .textchunk import TextChunk, TextChunkTypedDict, Type
+from .tool import Tool, ToolTypedDict
+from .toolcall import ToolCall, ToolCallTypedDict
+from .toolchoice import ToolChoice, ToolChoiceTypedDict
+from .toolchoiceenum import ToolChoiceEnum
 from .toolmessage import ToolMessage, ToolMessageRole, ToolMessageTypedDict
+from .tooltypes import ToolTypes
 from .usageinfo import UsageInfo, UsageInfoTypedDict
-from .usermessage import UserMessage, UserMessageContent, UserMessageContentTypedDict, UserMessageRole, UserMessageTypedDict
-from .validationerror import Loc, LocTypedDict, ValidationError, ValidationErrorTypedDict
+from .usermessage import (
+    UserMessage,
+    UserMessageContent,
+    UserMessageContentTypedDict,
+    UserMessageRole,
+    UserMessageTypedDict,
+)
+from .validationerror import (
+    Loc,
+    LocTypedDict,
+    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"]
+__all__ = [
+    "Arguments",
+    "ArgumentsTypedDict",
+    "AssistantMessage",
+    "AssistantMessageContent",
+    "AssistantMessageContentTypedDict",
+    "AssistantMessageRole",
+    "AssistantMessageTypedDict",
+    "ChatCompletionChoice",
+    "ChatCompletionChoiceFinishReason",
+    "ChatCompletionChoiceTypedDict",
+    "ChatCompletionRequest",
+    "ChatCompletionRequestMessages",
+    "ChatCompletionRequestMessagesTypedDict",
+    "ChatCompletionRequestStop",
+    "ChatCompletionRequestStopTypedDict",
+    "ChatCompletionRequestToolChoice",
+    "ChatCompletionRequestToolChoiceTypedDict",
+    "ChatCompletionRequestTypedDict",
+    "ChatCompletionResponse",
+    "ChatCompletionResponseTypedDict",
+    "ChatCompletionStreamRequest",
+    "ChatCompletionStreamRequestToolChoice",
+    "ChatCompletionStreamRequestToolChoiceTypedDict",
+    "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",
+    "FunctionName",
+    "FunctionNameTypedDict",
+    "FunctionTypedDict",
+    "HTTPValidationError",
+    "HTTPValidationErrorData",
+    "Loc",
+    "LocTypedDict",
+    "Messages",
+    "MessagesTypedDict",
+    "ResponseFormat",
+    "ResponseFormatTypedDict",
+    "ResponseFormats",
+    "Role",
+    "SDKError",
+    "Security",
+    "SecurityTypedDict",
+    "Stop",
+    "StopTypedDict",
+    "SystemMessage",
+    "SystemMessageContent",
+    "SystemMessageContentTypedDict",
+    "SystemMessageTypedDict",
+    "TextChunk",
+    "TextChunkTypedDict",
+    "Tool",
+    "ToolCall",
+    "ToolCallTypedDict",
+    "ToolChoice",
+    "ToolChoiceEnum",
+    "ToolChoiceTypedDict",
+    "ToolMessage",
+    "ToolMessageRole",
+    "ToolMessageTypedDict",
+    "ToolTypedDict",
+    "ToolTypes",
+    "Type",
+    "UsageInfo",
+    "UsageInfoTypedDict",
+    "UserMessage",
+    "UserMessageContent",
+    "UserMessageContentTypedDict",
+    "UserMessageRole",
+    "UserMessageTypedDict",
+    "ValidationError",
+    "ValidationErrorTypedDict",
+]

mistralai_gcp/models/assistantmessage.py

@@ -1,30 +1,45 @@
 """Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
 
 from __future__ import annotations
+from .contentchunk import ContentChunk, ContentChunkTypedDict
 from .toolcall import ToolCall, ToolCallTypedDict
-from mistralai_gcp.types import BaseModel, Nullable, OptionalNullable, UNSET, UNSET_SENTINEL
+from mistralai_gcp.types import (
+    BaseModel,
+    Nullable,
+    OptionalNullable,
+    UNSET,
+    UNSET_SENTINEL,
+)
 from pydantic import model_serializer
-from typing import List, Literal, Optional, TypedDict
-from typing_extensions import NotRequired
+from typing import List, Literal, Optional, Union
+from typing_extensions import NotRequired, TypedDict
+
+
+AssistantMessageContentTypedDict = Union[str, List[ContentChunkTypedDict]]
+
+
+AssistantMessageContent = Union[str, List[ContentChunk]]
 
 
 AssistantMessageRole = Literal["assistant"]
 
+
 class AssistantMessageTypedDict(TypedDict):
-    content: NotRequired[Nullable[str]]
+    content: NotRequired[Nullable[AssistantMessageContentTypedDict]]
     tool_calls: NotRequired[Nullable[List[ToolCallTypedDict]]]
     prefix: NotRequired[bool]
-    r"""Set this to `true` when adding an assistant message as prefix to condition the model response. The role of the prefix message is to force the model to start its answer by the content of the message."""
     role: NotRequired[AssistantMessageRole]
-    
+
 
 class AssistantMessage(BaseModel):
-    content: OptionalNullable[str] = UNSET
+    content: OptionalNullable[AssistantMessageContent] = UNSET
+
     tool_calls: OptionalNullable[List[ToolCall]] = UNSET
+
     prefix: Optional[bool] = False
-    r"""Set this to `true` when adding an assistant message as prefix to condition the model response. The role of the prefix message is to force the model to start its answer by the content of the message."""
+
     role: Optional[AssistantMessageRole] = "assistant"
-    
+
     @model_serializer(mode="wrap")
     def serialize_model(self, handler):
         optional_fields = ["content", "tool_calls", "prefix", "role"]
@@ -38,9 +53,13 @@ class AssistantMessage(BaseModel):
         for n, f in self.model_fields.items():
             k = f.alias or n
             val = serialized.get(k)
+            serialized.pop(k, None)
 
             optional_nullable = k in optional_fields and k in nullable_fields
-            is_set = (self.__pydantic_fields_set__.intersection({n}) or k in null_default_fields) # pylint: disable=no-member
+            is_set = (
+                self.__pydantic_fields_set__.intersection({n})
+                or k in null_default_fields
+            )  # pylint: disable=no-member
 
             if val is not None and val != UNSET_SENTINEL:
                 m[k] = val
@@ -50,4 +69,3 @@ class AssistantMessage(BaseModel):
                 m[k] = val
 
         return m
-        

mistralai_gcp/models/chatcompletionchoice.py

@@ -2,20 +2,29 @@
 
 from __future__ import annotations
 from .assistantmessage import AssistantMessage, AssistantMessageTypedDict
-from mistralai_gcp.types import BaseModel
-from typing import Literal, TypedDict
+from mistralai_gcp.types import BaseModel, UnrecognizedStr
+from mistralai_gcp.utils import validate_open_enum
+from pydantic.functional_validators import PlainValidator
+from typing import Literal, Union
+from typing_extensions import Annotated, TypedDict
 
 
-ChatCompletionChoiceFinishReason = Literal["stop", "length", "model_length", "error", "tool_calls"]
+ChatCompletionChoiceFinishReason = Union[
+    Literal["stop", "length", "model_length", "error", "tool_calls"], UnrecognizedStr
+]
+
 
 class ChatCompletionChoiceTypedDict(TypedDict):
     index: int
     message: AssistantMessageTypedDict
     finish_reason: ChatCompletionChoiceFinishReason
-    
+
 
 class ChatCompletionChoice(BaseModel):
     index: int
+
     message: AssistantMessage
-    finish_reason: ChatCompletionChoiceFinishReason
-    
+
+    finish_reason: Annotated[
+        ChatCompletionChoiceFinishReason, PlainValidator(validate_open_enum(False))
+    ]

mistralai_gcp/models/chatcompletionrequest.py

@@ -5,13 +5,21 @@ from .assistantmessage import AssistantMessage, AssistantMessageTypedDict
 from .responseformat import ResponseFormat, ResponseFormatTypedDict
 from .systemmessage import SystemMessage, SystemMessageTypedDict
 from .tool import Tool, ToolTypedDict
+from .toolchoice import ToolChoice, ToolChoiceTypedDict
+from .toolchoiceenum import ToolChoiceEnum
 from .toolmessage import ToolMessage, ToolMessageTypedDict
 from .usermessage import UserMessage, UserMessageTypedDict
-from mistralai_gcp.types import BaseModel, Nullable, OptionalNullable, UNSET, UNSET_SENTINEL
+from mistralai_gcp.types import (
+    BaseModel,
+    Nullable,
+    OptionalNullable,
+    UNSET,
+    UNSET_SENTINEL,
+)
 from mistralai_gcp.utils import get_discriminator
 from pydantic import Discriminator, Tag, model_serializer
-from typing import List, Literal, Optional, TypedDict, Union
-from typing_extensions import Annotated, NotRequired
+from typing import List, Optional, Union
+from typing_extensions import Annotated, NotRequired, TypedDict
 
 
 ChatCompletionRequestStopTypedDict = Union[str, List[str]]
@@ -22,27 +30,42 @@ 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]
+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"))]
+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"]
+ChatCompletionRequestToolChoiceTypedDict = Union[ToolChoiceTypedDict, ToolChoiceEnum]
+
+
+ChatCompletionRequestToolChoice = Union[ToolChoice, ToolChoiceEnum]
+
 
 class ChatCompletionRequestTypedDict(TypedDict):
     model: Nullable[str]
     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]
-    r"""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."""
+    temperature: NotRequired[Nullable[float]]
+    r"""What sampling temperature to use, we recommend between 0.0 and 0.7. Higher values like 0.7 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. The default value varies depending on the model you are targeting. Call the `/models` endpoint to retrieve the appropriate value."""
     top_p: NotRequired[float]
     r"""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."""
     max_tokens: NotRequired[Nullable[int]]
     r"""The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length."""
-    min_tokens: NotRequired[Nullable[int]]
-    r"""The minimum number of tokens to generate in the completion."""
     stream: NotRequired[bool]
     r"""Whether to stream back partial progress. If set, tokens will be sent as data-only server-side 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."""
     stop: NotRequired[ChatCompletionRequestStopTypedDict]
@@ -51,36 +74,79 @@ class ChatCompletionRequestTypedDict(TypedDict):
     r"""The seed to use for random sampling. If set, different calls will generate deterministic results."""
     response_format: NotRequired[ResponseFormatTypedDict]
     tools: NotRequired[Nullable[List[ToolTypedDict]]]
-    tool_choice: NotRequired[ChatCompletionRequestToolChoice]
-    
+    tool_choice: NotRequired[ChatCompletionRequestToolChoiceTypedDict]
+    presence_penalty: NotRequired[float]
+    r"""presence_penalty determines how much the model penalizes the repetition of words or phrases. A higher presence penalty encourages the model to use a wider variety of words and phrases, making the output more diverse and creative."""
+    frequency_penalty: NotRequired[float]
+    r"""frequency_penalty penalizes the repetition of words based on their frequency in the generated text. A higher frequency penalty discourages the model from repeating words that have already appeared frequently in the output, promoting diversity and reducing repetition."""
+    n: NotRequired[Nullable[int]]
+    r"""Number of completions to return for each request, input tokens are only billed once."""
+
 
 class ChatCompletionRequest(BaseModel):
     model: Nullable[str]
     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
-    r"""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."""
+
+    temperature: OptionalNullable[float] = UNSET
+    r"""What sampling temperature to use, we recommend between 0.0 and 0.7. Higher values like 0.7 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. The default value varies depending on the model you are targeting. Call the `/models` endpoint to retrieve the appropriate value."""
+
     top_p: Optional[float] = 1
     r"""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."""
+
     max_tokens: OptionalNullable[int] = UNSET
     r"""The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length."""
-    min_tokens: OptionalNullable[int] = UNSET
-    r"""The minimum number of tokens to generate in the completion."""
+
     stream: Optional[bool] = False
     r"""Whether to stream back partial progress. If set, tokens will be sent as data-only server-side 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."""
+
     stop: Optional[ChatCompletionRequestStop] = None
     r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
+
     random_seed: OptionalNullable[int] = UNSET
     r"""The seed to use for random sampling. If set, different calls will generate deterministic results."""
+
     response_format: Optional[ResponseFormat] = None
+
     tools: OptionalNullable[List[Tool]] = UNSET
-    tool_choice: Optional[ChatCompletionRequestToolChoice] = "auto"
-    
+
+    tool_choice: Optional[ChatCompletionRequestToolChoice] = None
+
+    presence_penalty: Optional[float] = 0
+    r"""presence_penalty determines how much the model penalizes the repetition of words or phrases. A higher presence penalty encourages the model to use a wider variety of words and phrases, making the output more diverse and creative."""
+
+    frequency_penalty: Optional[float] = 0
+    r"""frequency_penalty penalizes the repetition of words based on their frequency in the generated text. A higher frequency penalty discourages the model from repeating words that have already appeared frequently in the output, promoting diversity and reducing repetition."""
+
+    n: OptionalNullable[int] = UNSET
+    r"""Number of completions to return for each request, input tokens are only billed once."""
+
     @model_serializer(mode="wrap")
     def serialize_model(self, handler):
-        optional_fields = ["temperature", "top_p", "max_tokens", "min_tokens", "stream", "stop", "random_seed", "response_format", "tools", "tool_choice"]
-        nullable_fields = ["model", "max_tokens", "min_tokens", "random_seed", "tools"]
+        optional_fields = [
+            "temperature",
+            "top_p",
+            "max_tokens",
+            "stream",
+            "stop",
+            "random_seed",
+            "response_format",
+            "tools",
+            "tool_choice",
+            "presence_penalty",
+            "frequency_penalty",
+            "n",
+        ]
+        nullable_fields = [
+            "model",
+            "temperature",
+            "max_tokens",
+            "random_seed",
+            "tools",
+            "n",
+        ]
         null_default_fields = []
 
         serialized = handler(self)
@@ -90,9 +156,13 @@ class ChatCompletionRequest(BaseModel):
         for n, f in self.model_fields.items():
             k = f.alias or n
             val = serialized.get(k)
+            serialized.pop(k, None)
 
             optional_nullable = k in optional_fields and k in nullable_fields
-            is_set = (self.__pydantic_fields_set__.intersection({n}) or k in null_default_fields) # pylint: disable=no-member
+            is_set = (
+                self.__pydantic_fields_set__.intersection({n})
+                or k in null_default_fields
+            )  # pylint: disable=no-member
 
             if val is not None and val != UNSET_SENTINEL:
                 m[k] = val
@@ -102,4 +172,3 @@ class ChatCompletionRequest(BaseModel):
                 m[k] = val
 
         return m
-        

mistralai_gcp/models/chatcompletionresponse.py

@@ -4,8 +4,8 @@ from __future__ import annotations
 from .chatcompletionchoice import ChatCompletionChoice, ChatCompletionChoiceTypedDict
 from .usageinfo import UsageInfo, UsageInfoTypedDict
 from mistralai_gcp.types import BaseModel
-from typing import List, Optional, TypedDict
-from typing_extensions import NotRequired
+from typing import List, Optional
+from typing_extensions import NotRequired, TypedDict
 
 
 class ChatCompletionResponseTypedDict(TypedDict):
@@ -15,13 +15,17 @@ class ChatCompletionResponseTypedDict(TypedDict):
     usage: UsageInfoTypedDict
     created: NotRequired[int]
     choices: NotRequired[List[ChatCompletionChoiceTypedDict]]
-    
+
 
 class ChatCompletionResponse(BaseModel):
     id: str
+
     object: str
+
     model: str
+
     usage: UsageInfo
+
     created: Optional[int] = None
+
     choices: Optional[List[ChatCompletionChoice]] = None
-