mistralai 0.4.2__py3-none-any.whl → 0.5.5a50__py3-none-any.whl

mistralai_gcp/models/chatcompletionrequest.py

@@ -0,0 +1,110 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from __future__ import annotations
+from .assistantmessage import AssistantMessage, AssistantMessageTypedDict
+from .responseformat import ResponseFormat, ResponseFormatTypedDict
+from .systemmessage import SystemMessage, SystemMessageTypedDict
+from .tool import Tool, ToolTypedDict
+from .toolmessage import ToolMessage, ToolMessageTypedDict
+from .usermessage import UserMessage, UserMessageTypedDict
+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
+
+
+ChatCompletionRequestToolChoice = Literal["auto", "none", "any"]
+
+class ChatCompletionRequestTypedDict(TypedDict):
+    messages: List[ChatCompletionRequestMessagesTypedDict]
+    r"""The prompt(s) to generate completions for, encoded as a list of dict with role and content."""
+    model: NotRequired[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."""
+    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."""
+    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]
+    r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
+    random_seed: NotRequired[Nullable[int]]
+    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]
+    
+
+class ChatCompletionRequest(BaseModel):
+    messages: List[ChatCompletionRequestMessages]
+    r"""The prompt(s) to generate completions for, encoded as a list of dict with role and content."""
+    model: OptionalNullable[str] = UNSET
+    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."""
+    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."""
+    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"
+    
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = ["model", "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"]
+        null_default_fields = []
+
+        serialized = handler(self)
+
+        m = {}
+
+        for n, f in self.model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val is not None and val != UNSET_SENTINEL:
+                m[k] = val
+            elif val != UNSET_SENTINEL and (
+                not k in optional_fields
+                or (
+                    k in optional_fields
+                    and k in nullable_fields
+                    and (
+                        self.__pydantic_fields_set__.intersection({n})
+                        or k in null_default_fields
+                    )  # pylint: disable=no-member
+                )
+            ):
+                m[k] = val
+
+        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_gcp/models/chatcompletionresponse.py

@@ -0,0 +1,27 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+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
+
+
+class ChatCompletionResponseTypedDict(TypedDict):
+    id: str
+    object: str
+    model: str
+    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
+    

mistralai_gcp/models/chatcompletionstreamrequest.py

@@ -0,0 +1,108 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from __future__ import annotations
+from .assistantmessage import AssistantMessage, AssistantMessageTypedDict
+from .responseformat import ResponseFormat, ResponseFormatTypedDict
+from .systemmessage import SystemMessage, SystemMessageTypedDict
+from .tool import Tool, ToolTypedDict
+from .toolmessage import ToolMessage, ToolMessageTypedDict
+from .usermessage import UserMessage, UserMessageTypedDict
+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
+
+
+ToolChoice = Literal["auto", "none", "any"]
+
+class ChatCompletionStreamRequestTypedDict(TypedDict):
+    messages: List[MessagesTypedDict]
+    r"""The prompt(s) to generate completions for, encoded as a list of dict with role and content."""
+    model: NotRequired[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."""
+    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."""
+    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]
+    stop: NotRequired[StopTypedDict]
+    r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
+    random_seed: NotRequired[Nullable[int]]
+    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[ToolChoice]
+    
+
+class ChatCompletionStreamRequest(BaseModel):
+    messages: List[Messages]
+    r"""The prompt(s) to generate completions for, encoded as a list of dict with role and content."""
+    model: OptionalNullable[str] = UNSET
+    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."""
+    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."""
+    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] = True
+    stop: Optional[Stop] = 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[ToolChoice] = "auto"
+    
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = ["model", "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"]
+        null_default_fields = []
+
+        serialized = handler(self)
+
+        m = {}
+
+        for n, f in self.model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val is not None and val != UNSET_SENTINEL:
+                m[k] = val
+            elif val != UNSET_SENTINEL and (
+                not k in optional_fields
+                or (
+                    k in optional_fields
+                    and k in nullable_fields
+                    and (
+                        self.__pydantic_fields_set__.intersection({n})
+                        or k in null_default_fields
+                    )  # pylint: disable=no-member
+                )
+            ):
+                m[k] = val
+
+        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_gcp/models/completionchunk.py

@@ -0,0 +1,27 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from __future__ import annotations
+from .completionresponsestreamchoice import CompletionResponseStreamChoice, CompletionResponseStreamChoiceTypedDict
+from .usageinfo import UsageInfo, UsageInfoTypedDict
+from mistralai_gcp.types import BaseModel
+from typing import List, Optional, TypedDict
+from typing_extensions import NotRequired
+
+
+class CompletionChunkTypedDict(TypedDict):
+    id: str
+    model: str
+    choices: List[CompletionResponseStreamChoiceTypedDict]
+    object: NotRequired[str]
+    created: NotRequired[int]
+    usage: NotRequired[UsageInfoTypedDict]
+    
+
+class CompletionChunk(BaseModel):
+    id: str
+    model: str
+    choices: List[CompletionResponseStreamChoice]
+    object: Optional[str] = None
+    created: Optional[int] = None
+    usage: Optional[UsageInfo] = None
+    

mistralai_gcp/models/completionevent.py

@@ -0,0 +1,15 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from __future__ import annotations
+from .completionchunk import CompletionChunk, CompletionChunkTypedDict
+from mistralai_gcp.types import BaseModel
+from typing import TypedDict
+
+
+class CompletionEventTypedDict(TypedDict):
+    data: CompletionChunkTypedDict
+    
+
+class CompletionEvent(BaseModel):
+    data: CompletionChunk
+    

mistralai_gcp/models/completionresponsestreamchoice.py

@@ -0,0 +1,53 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from __future__ import annotations
+from .deltamessage import DeltaMessage, DeltaMessageTypedDict
+from mistralai_gcp.types import BaseModel, Nullable, UNSET_SENTINEL
+from pydantic import model_serializer
+from typing import Literal, TypedDict
+
+
+FinishReason = Literal["stop", "length", "error", "tool_calls"]
+
+class CompletionResponseStreamChoiceTypedDict(TypedDict):
+    index: int
+    delta: DeltaMessageTypedDict
+    finish_reason: Nullable[FinishReason]
+    
+
+class CompletionResponseStreamChoice(BaseModel):
+    index: int
+    delta: DeltaMessage
+    finish_reason: Nullable[FinishReason]
+    
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = []
+        nullable_fields = ["finish_reason"]
+        null_default_fields = []
+
+        serialized = handler(self)
+
+        m = {}
+
+        for n, f in self.model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val is not None and val != UNSET_SENTINEL:
+                m[k] = val
+            elif val != UNSET_SENTINEL and (
+                not k in optional_fields
+                or (
+                    k in optional_fields
+                    and k in nullable_fields
+                    and (
+                        self.__pydantic_fields_set__.intersection({n})
+                        or k in null_default_fields
+                    )  # pylint: disable=no-member
+                )
+            ):
+                m[k] = val
+
+        return m
+        

mistralai_gcp/models/contentchunk.py

@@ -0,0 +1,17 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from __future__ import annotations
+from mistralai_gcp.types import BaseModel
+import pydantic
+from typing import Final, Optional, TypedDict
+from typing_extensions import Annotated
+
+
+class ContentChunkTypedDict(TypedDict):
+    text: str
+    
+
+class ContentChunk(BaseModel):
+    text: str
+    TYPE: Annotated[Final[Optional[str]], pydantic.Field(alias="type")] = "text" # type: ignore
+    

mistralai_gcp/models/deltamessage.py

@@ -0,0 +1,52 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+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_extensions import NotRequired
+
+
+class DeltaMessageTypedDict(TypedDict):
+    role: NotRequired[str]
+    content: NotRequired[str]
+    tool_calls: NotRequired[Nullable[ToolCallTypedDict]]
+    
+
+class DeltaMessage(BaseModel):
+    role: Optional[str] = None
+    content: Optional[str] = None
+    tool_calls: OptionalNullable[ToolCall] = UNSET
+    
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = ["role", "content", "tool_calls"]
+        nullable_fields = ["tool_calls"]
+        null_default_fields = []
+
+        serialized = handler(self)
+
+        m = {}
+
+        for n, f in self.model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val is not None and val != UNSET_SENTINEL:
+                m[k] = val
+            elif val != UNSET_SENTINEL and (
+                not k in optional_fields
+                or (
+                    k in optional_fields
+                    and k in nullable_fields
+                    and (
+                        self.__pydantic_fields_set__.intersection({n})
+                        or k in null_default_fields
+                    )  # pylint: disable=no-member
+                )
+            ):
+                m[k] = val
+
+        return m
+        

mistralai_gcp/models/fimcompletionrequest.py

@@ -0,0 +1,99 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from __future__ import annotations
+from mistralai_gcp.types import BaseModel, Nullable, OptionalNullable, UNSET, UNSET_SENTINEL
+from pydantic import model_serializer
+from typing import List, Optional, TypedDict, Union
+from typing_extensions import NotRequired
+
+
+class FIMCompletionRequestTypedDict(TypedDict):
+    prompt: str
+    r"""The text/code to complete."""
+    model: NotRequired[Nullable[str]]
+    r"""ID of the model to use. Only compatible for now with:
+    - `codestral-2405`
+    - `codestral-latest`
+    """
+    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."""
+    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[FIMCompletionRequestStopTypedDict]
+    r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
+    random_seed: NotRequired[Nullable[int]]
+    r"""The seed to use for random sampling. If set, different calls will generate deterministic results."""
+    suffix: NotRequired[Nullable[str]]
+    r"""Optional text/code that adds more context for the model. When given a `prompt` and a `suffix` the model will fill what is between them. When `suffix` is not provided, the model will simply execute completion starting with `prompt`."""
+    
+
+class FIMCompletionRequest(BaseModel):
+    prompt: str
+    r"""The text/code to complete."""
+    model: OptionalNullable[str] = UNSET
+    r"""ID of the model to use. Only compatible for now with:
+    - `codestral-2405`
+    - `codestral-latest`
+    """
+    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."""
+    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[FIMCompletionRequestStop] = 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."""
+    suffix: OptionalNullable[str] = UNSET
+    r"""Optional text/code that adds more context for the model. When given a `prompt` and a `suffix` the model will fill what is between them. When `suffix` is not provided, the model will simply execute completion starting with `prompt`."""
+    
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = ["model", "temperature", "top_p", "max_tokens", "min_tokens", "stream", "stop", "random_seed", "suffix"]
+        nullable_fields = ["model", "max_tokens", "min_tokens", "random_seed", "suffix"]
+        null_default_fields = []
+
+        serialized = handler(self)
+
+        m = {}
+
+        for n, f in self.model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val is not None and val != UNSET_SENTINEL:
+                m[k] = val
+            elif val != UNSET_SENTINEL and (
+                not k in optional_fields
+                or (
+                    k in optional_fields
+                    and k in nullable_fields
+                    and (
+                        self.__pydantic_fields_set__.intersection({n})
+                        or k in null_default_fields
+                    )  # pylint: disable=no-member
+                )
+            ):
+                m[k] = val
+
+        return m
+        
+
+FIMCompletionRequestStopTypedDict = Union[str, List[str]]
+r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
+
+
+FIMCompletionRequestStop = Union[str, List[str]]
+r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
+

mistralai_gcp/models/fimcompletionresponse.py

@@ -0,0 +1,27 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+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
+
+
+class FIMCompletionResponseTypedDict(TypedDict):
+    id: str
+    object: str
+    model: str
+    usage: UsageInfoTypedDict
+    created: NotRequired[int]
+    choices: NotRequired[List[ChatCompletionChoiceTypedDict]]
+    
+
+class FIMCompletionResponse(BaseModel):
+    id: str
+    object: str
+    model: str
+    usage: UsageInfo
+    created: Optional[int] = None
+    choices: Optional[List[ChatCompletionChoice]] = None
+    

mistralai_gcp/models/fimcompletionstreamrequest.py

@@ -0,0 +1,97 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from __future__ import annotations
+from mistralai_gcp.types import BaseModel, Nullable, OptionalNullable, UNSET, UNSET_SENTINEL
+from pydantic import model_serializer
+from typing import List, Optional, TypedDict, Union
+from typing_extensions import NotRequired
+
+
+class FIMCompletionStreamRequestTypedDict(TypedDict):
+    prompt: str
+    r"""The text/code to complete."""
+    model: NotRequired[Nullable[str]]
+    r"""ID of the model to use. Only compatible for now with:
+    - `codestral-2405`
+    - `codestral-latest`
+    """
+    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."""
+    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]
+    stop: NotRequired[FIMCompletionStreamRequestStopTypedDict]
+    r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
+    random_seed: NotRequired[Nullable[int]]
+    r"""The seed to use for random sampling. If set, different calls will generate deterministic results."""
+    suffix: NotRequired[Nullable[str]]
+    r"""Optional text/code that adds more context for the model. When given a `prompt` and a `suffix` the model will fill what is between them. When `suffix` is not provided, the model will simply execute completion starting with `prompt`."""
+    
+
+class FIMCompletionStreamRequest(BaseModel):
+    prompt: str
+    r"""The text/code to complete."""
+    model: OptionalNullable[str] = UNSET
+    r"""ID of the model to use. Only compatible for now with:
+    - `codestral-2405`
+    - `codestral-latest`
+    """
+    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."""
+    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] = True
+    stop: Optional[FIMCompletionStreamRequestStop] = 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."""
+    suffix: OptionalNullable[str] = UNSET
+    r"""Optional text/code that adds more context for the model. When given a `prompt` and a `suffix` the model will fill what is between them. When `suffix` is not provided, the model will simply execute completion starting with `prompt`."""
+    
+    @model_serializer(mode="wrap")
+    def serialize_model(self, handler):
+        optional_fields = ["model", "temperature", "top_p", "max_tokens", "min_tokens", "stream", "stop", "random_seed", "suffix"]
+        nullable_fields = ["model", "max_tokens", "min_tokens", "random_seed", "suffix"]
+        null_default_fields = []
+
+        serialized = handler(self)
+
+        m = {}
+
+        for n, f in self.model_fields.items():
+            k = f.alias or n
+            val = serialized.get(k)
+
+            if val is not None and val != UNSET_SENTINEL:
+                m[k] = val
+            elif val != UNSET_SENTINEL and (
+                not k in optional_fields
+                or (
+                    k in optional_fields
+                    and k in nullable_fields
+                    and (
+                        self.__pydantic_fields_set__.intersection({n})
+                        or k in null_default_fields
+                    )  # pylint: disable=no-member
+                )
+            ):
+                m[k] = val
+
+        return m
+        
+
+FIMCompletionStreamRequestStopTypedDict = Union[str, List[str]]
+r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
+
+
+FIMCompletionStreamRequestStop = Union[str, List[str]]
+r"""Stop generation if this token is detected. Or if one of these tokens is detected when providing an array"""
+