mistralai 0.4.2__py3-none-any.whl → 1.0.0__py3-none-any.whl

mistralai_azure/chat.py

@@ -0,0 +1,470 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+from .basesdk import BaseSDK
+from mistralai_azure import models, utils
+from mistralai_azure._hooks import HookContext
+from mistralai_azure.types import OptionalNullable, UNSET
+from mistralai_azure.utils import eventstreaming
+from typing import Any, AsyncGenerator, Generator, List, Optional, Union
+
+class Chat(BaseSDK):
+    r"""Chat Completion API."""
+    
+    
+    def stream(
+        self, *,
+        messages: Union[List[models.Messages], List[models.MessagesTypedDict]],
+        model: OptionalNullable[str] = "azureai",
+        temperature: Optional[float] = 0.7,
+        top_p: Optional[float] = 1,
+        max_tokens: OptionalNullable[int] = UNSET,
+        min_tokens: OptionalNullable[int] = UNSET,
+        stream: Optional[bool] = True,
+        stop: Optional[Union[models.Stop, models.StopTypedDict]] = None,
+        random_seed: OptionalNullable[int] = UNSET,
+        response_format: Optional[Union[models.ResponseFormat, models.ResponseFormatTypedDict]] = None,
+        tools: OptionalNullable[Union[List[models.Tool], List[models.ToolTypedDict]]] = UNSET,
+        tool_choice: Optional[models.ToolChoice] = "auto",
+        safe_prompt: Optional[bool] = False,
+        retries: OptionalNullable[utils.RetryConfig] = UNSET,
+        server_url: Optional[str] = None,
+        timeout_ms: Optional[int] = None,
+    ) -> Optional[Generator[models.CompletionEvent, None, None]]:
+        r"""Stream chat completion
+
+        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 messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
+        :param model: The ID of the model to use for this request.
+        :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.
+        :param max_tokens: 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.
+        :param min_tokens: The minimum number of tokens to generate in the completion.
+        :param stream: 
+        :param stop: Stop generation if this token is detected. Or if one of these tokens is detected when providing an array
+        :param random_seed: The seed to use for random sampling. If set, different calls will generate deterministic results.
+        :param response_format: 
+        :param tools: 
+        :param tool_choice: 
+        :param safe_prompt: Whether to inject a safety prompt before all conversations.
+        :param retries: Override the default retry configuration for this method
+        :param server_url: Override the default server URL for this method
+        :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        """
+        base_url = None
+        url_variables = None
+        if timeout_ms is None:
+            timeout_ms = self.sdk_configuration.timeout_ms
+        
+        if server_url is not None:
+            base_url = server_url
+        
+        request = models.ChatCompletionStreamRequest(
+            model=model,
+            temperature=temperature,
+            top_p=top_p,
+            max_tokens=max_tokens,
+            min_tokens=min_tokens,
+            stream=stream,
+            stop=stop,
+            random_seed=random_seed,
+            messages=utils.get_pydantic_model(messages, List[models.Messages]),
+            response_format=utils.get_pydantic_model(response_format, Optional[models.ResponseFormat]),
+            tools=utils.get_pydantic_model(tools, OptionalNullable[List[models.Tool]]),
+            tool_choice=tool_choice,
+            safe_prompt=safe_prompt,
+        )
+        
+        req = self.build_request(
+            method="POST",
+            path="/chat/completions#stream",
+            base_url=base_url,
+            url_variables=url_variables,
+            request=request,
+            request_body_required=True,
+            request_has_path_params=False,
+            request_has_query_params=True,
+            user_agent_header="user-agent",
+            accept_header_value="text/event-stream",
+            security=self.sdk_configuration.security,
+            get_serialized_body=lambda: utils.serialize_request_body(request, False, False, "json", models.ChatCompletionStreamRequest),
+            timeout_ms=timeout_ms,
+        )
+        
+        if retries == UNSET:
+            if self.sdk_configuration.retry_config is not UNSET:
+                retries = self.sdk_configuration.retry_config
+
+        retry_config = None
+        if isinstance(retries, utils.RetryConfig):
+            retry_config = (retries, [
+                "429",
+                "500",
+                "502",
+                "503",
+                "504"
+            ])                
+        
+        http_res = self.do_request(
+            hook_ctx=HookContext(operation_id="stream_chat", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            request=req,
+            error_status_codes=["422","4XX","5XX"],
+            stream=True,
+            retry_config=retry_config
+        )
+        
+        data: Any = None
+        if utils.match_response(http_res, "200", "text/event-stream"):
+            return eventstreaming.stream_events(http_res, lambda raw: utils.unmarshal_json(raw, models.CompletionEvent), sentinel="[DONE]")
+        if utils.match_response(http_res, "422", "application/json"):
+            data = utils.unmarshal_json(http_res.text, models.HTTPValidationErrorData)
+            raise models.HTTPValidationError(data=data)
+        if utils.match_response(http_res, ["4XX","5XX"], "*"):
+            raise models.SDKError("API error occurred", http_res.status_code, http_res.text, http_res)
+        
+        content_type = http_res.headers.get("Content-Type")
+        raise models.SDKError(f"Unexpected response received (code: {http_res.status_code}, type: {content_type})", http_res.status_code, http_res.text, http_res)
+
+    
+    
+    async def stream_async(
+        self, *,
+        messages: Union[List[models.Messages], List[models.MessagesTypedDict]],
+        model: OptionalNullable[str] = "azureai",
+        temperature: Optional[float] = 0.7,
+        top_p: Optional[float] = 1,
+        max_tokens: OptionalNullable[int] = UNSET,
+        min_tokens: OptionalNullable[int] = UNSET,
+        stream: Optional[bool] = True,
+        stop: Optional[Union[models.Stop, models.StopTypedDict]] = None,
+        random_seed: OptionalNullable[int] = UNSET,
+        response_format: Optional[Union[models.ResponseFormat, models.ResponseFormatTypedDict]] = None,
+        tools: OptionalNullable[Union[List[models.Tool], List[models.ToolTypedDict]]] = UNSET,
+        tool_choice: Optional[models.ToolChoice] = "auto",
+        safe_prompt: Optional[bool] = False,
+        retries: OptionalNullable[utils.RetryConfig] = UNSET,
+        server_url: Optional[str] = None,
+        timeout_ms: Optional[int] = None,
+    ) -> Optional[AsyncGenerator[models.CompletionEvent, None]]:
+        r"""Stream chat completion
+
+        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 messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
+        :param model: The ID of the model to use for this request.
+        :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.
+        :param max_tokens: 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.
+        :param min_tokens: The minimum number of tokens to generate in the completion.
+        :param stream: 
+        :param stop: Stop generation if this token is detected. Or if one of these tokens is detected when providing an array
+        :param random_seed: The seed to use for random sampling. If set, different calls will generate deterministic results.
+        :param response_format: 
+        :param tools: 
+        :param tool_choice: 
+        :param safe_prompt: Whether to inject a safety prompt before all conversations.
+        :param retries: Override the default retry configuration for this method
+        :param server_url: Override the default server URL for this method
+        :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        """
+        base_url = None
+        url_variables = None
+        if timeout_ms is None:
+            timeout_ms = self.sdk_configuration.timeout_ms
+        
+        if server_url is not None:
+            base_url = server_url
+        
+        request = models.ChatCompletionStreamRequest(
+            model=model,
+            temperature=temperature,
+            top_p=top_p,
+            max_tokens=max_tokens,
+            min_tokens=min_tokens,
+            stream=stream,
+            stop=stop,
+            random_seed=random_seed,
+            messages=utils.get_pydantic_model(messages, List[models.Messages]),
+            response_format=utils.get_pydantic_model(response_format, Optional[models.ResponseFormat]),
+            tools=utils.get_pydantic_model(tools, OptionalNullable[List[models.Tool]]),
+            tool_choice=tool_choice,
+            safe_prompt=safe_prompt,
+        )
+        
+        req = self.build_request(
+            method="POST",
+            path="/chat/completions#stream",
+            base_url=base_url,
+            url_variables=url_variables,
+            request=request,
+            request_body_required=True,
+            request_has_path_params=False,
+            request_has_query_params=True,
+            user_agent_header="user-agent",
+            accept_header_value="text/event-stream",
+            security=self.sdk_configuration.security,
+            get_serialized_body=lambda: utils.serialize_request_body(request, False, False, "json", models.ChatCompletionStreamRequest),
+            timeout_ms=timeout_ms,
+        )
+        
+        if retries == UNSET:
+            if self.sdk_configuration.retry_config is not UNSET:
+                retries = self.sdk_configuration.retry_config
+
+        retry_config = None
+        if isinstance(retries, utils.RetryConfig):
+            retry_config = (retries, [
+                "429",
+                "500",
+                "502",
+                "503",
+                "504"
+            ])                
+        
+        http_res = await self.do_request_async(
+            hook_ctx=HookContext(operation_id="stream_chat", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            request=req,
+            error_status_codes=["422","4XX","5XX"],
+            stream=True,
+            retry_config=retry_config
+        )
+        
+        data: Any = None
+        if utils.match_response(http_res, "200", "text/event-stream"):
+            return eventstreaming.stream_events_async(http_res, lambda raw: utils.unmarshal_json(raw, models.CompletionEvent), sentinel="[DONE]")
+        if utils.match_response(http_res, "422", "application/json"):
+            data = utils.unmarshal_json(http_res.text, models.HTTPValidationErrorData)
+            raise models.HTTPValidationError(data=data)
+        if utils.match_response(http_res, ["4XX","5XX"], "*"):
+            raise models.SDKError("API error occurred", http_res.status_code, http_res.text, http_res)
+        
+        content_type = http_res.headers.get("Content-Type")
+        raise models.SDKError(f"Unexpected response received (code: {http_res.status_code}, type: {content_type})", http_res.status_code, http_res.text, http_res)
+
+    
+    
+    def complete(
+        self, *,
+        messages: Union[List[models.ChatCompletionRequestMessages], List[models.ChatCompletionRequestMessagesTypedDict]],
+        model: OptionalNullable[str] = "azureai",
+        temperature: Optional[float] = 0.7,
+        top_p: Optional[float] = 1,
+        max_tokens: OptionalNullable[int] = UNSET,
+        min_tokens: OptionalNullable[int] = UNSET,
+        stream: Optional[bool] = False,
+        stop: Optional[Union[models.ChatCompletionRequestStop, models.ChatCompletionRequestStopTypedDict]] = None,
+        random_seed: OptionalNullable[int] = UNSET,
+        response_format: Optional[Union[models.ResponseFormat, models.ResponseFormatTypedDict]] = None,
+        tools: OptionalNullable[Union[List[models.Tool], List[models.ToolTypedDict]]] = UNSET,
+        tool_choice: Optional[models.ChatCompletionRequestToolChoice] = "auto",
+        safe_prompt: Optional[bool] = False,
+        retries: OptionalNullable[utils.RetryConfig] = UNSET,
+        server_url: Optional[str] = None,
+        timeout_ms: Optional[int] = None,
+    ) -> Optional[models.ChatCompletionResponse]:
+        r"""Chat Completion
+
+        :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
+        :param model: The ID of the model to use for this request.
+        :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.
+        :param max_tokens: 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.
+        :param min_tokens: The minimum number of tokens to generate in the completion.
+        :param stream: 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.
+        :param stop: Stop generation if this token is detected. Or if one of these tokens is detected when providing an array
+        :param random_seed: The seed to use for random sampling. If set, different calls will generate deterministic results.
+        :param response_format: 
+        :param tools: 
+        :param tool_choice: 
+        :param safe_prompt: Whether to inject a safety prompt before all conversations.
+        :param retries: Override the default retry configuration for this method
+        :param server_url: Override the default server URL for this method
+        :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        """
+        base_url = None
+        url_variables = None
+        if timeout_ms is None:
+            timeout_ms = self.sdk_configuration.timeout_ms
+        
+        if server_url is not None:
+            base_url = server_url
+        
+        request = models.ChatCompletionRequest(
+            model=model,
+            temperature=temperature,
+            top_p=top_p,
+            max_tokens=max_tokens,
+            min_tokens=min_tokens,
+            stream=stream,
+            stop=stop,
+            random_seed=random_seed,
+            messages=utils.get_pydantic_model(messages, List[models.ChatCompletionRequestMessages]),
+            response_format=utils.get_pydantic_model(response_format, Optional[models.ResponseFormat]),
+            tools=utils.get_pydantic_model(tools, OptionalNullable[List[models.Tool]]),
+            tool_choice=tool_choice,
+            safe_prompt=safe_prompt,
+        )
+        
+        req = self.build_request(
+            method="POST",
+            path="/chat/completions",
+            base_url=base_url,
+            url_variables=url_variables,
+            request=request,
+            request_body_required=True,
+            request_has_path_params=False,
+            request_has_query_params=True,
+            user_agent_header="user-agent",
+            accept_header_value="application/json",
+            security=self.sdk_configuration.security,
+            get_serialized_body=lambda: utils.serialize_request_body(request, False, False, "json", models.ChatCompletionRequest),
+            timeout_ms=timeout_ms,
+        )
+        
+        if retries == UNSET:
+            if self.sdk_configuration.retry_config is not UNSET:
+                retries = self.sdk_configuration.retry_config
+
+        retry_config = None
+        if isinstance(retries, utils.RetryConfig):
+            retry_config = (retries, [
+                "429",
+                "500",
+                "502",
+                "503",
+                "504"
+            ])                
+        
+        http_res = self.do_request(
+            hook_ctx=HookContext(operation_id="chat_completion_v1_chat_completions_post", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            request=req,
+            error_status_codes=["422","4XX","5XX"],
+            retry_config=retry_config
+        )
+        
+        data: Any = None
+        if utils.match_response(http_res, "200", "application/json"):
+            return utils.unmarshal_json(http_res.text, Optional[models.ChatCompletionResponse])
+        if utils.match_response(http_res, "422", "application/json"):
+            data = utils.unmarshal_json(http_res.text, models.HTTPValidationErrorData)
+            raise models.HTTPValidationError(data=data)
+        if utils.match_response(http_res, ["4XX","5XX"], "*"):
+            raise models.SDKError("API error occurred", http_res.status_code, http_res.text, http_res)
+        
+        content_type = http_res.headers.get("Content-Type")
+        raise models.SDKError(f"Unexpected response received (code: {http_res.status_code}, type: {content_type})", http_res.status_code, http_res.text, http_res)
+
+    
+    
+    async def complete_async(
+        self, *,
+        messages: Union[List[models.ChatCompletionRequestMessages], List[models.ChatCompletionRequestMessagesTypedDict]],
+        model: OptionalNullable[str] = "azureai",
+        temperature: Optional[float] = 0.7,
+        top_p: Optional[float] = 1,
+        max_tokens: OptionalNullable[int] = UNSET,
+        min_tokens: OptionalNullable[int] = UNSET,
+        stream: Optional[bool] = False,
+        stop: Optional[Union[models.ChatCompletionRequestStop, models.ChatCompletionRequestStopTypedDict]] = None,
+        random_seed: OptionalNullable[int] = UNSET,
+        response_format: Optional[Union[models.ResponseFormat, models.ResponseFormatTypedDict]] = None,
+        tools: OptionalNullable[Union[List[models.Tool], List[models.ToolTypedDict]]] = UNSET,
+        tool_choice: Optional[models.ChatCompletionRequestToolChoice] = "auto",
+        safe_prompt: Optional[bool] = False,
+        retries: OptionalNullable[utils.RetryConfig] = UNSET,
+        server_url: Optional[str] = None,
+        timeout_ms: Optional[int] = None,
+    ) -> Optional[models.ChatCompletionResponse]:
+        r"""Chat Completion
+
+        :param messages: The prompt(s) to generate completions for, encoded as a list of dict with role and content.
+        :param model: The ID of the model to use for this request.
+        :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.
+        :param max_tokens: 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.
+        :param min_tokens: The minimum number of tokens to generate in the completion.
+        :param stream: 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.
+        :param stop: Stop generation if this token is detected. Or if one of these tokens is detected when providing an array
+        :param random_seed: The seed to use for random sampling. If set, different calls will generate deterministic results.
+        :param response_format: 
+        :param tools: 
+        :param tool_choice: 
+        :param safe_prompt: Whether to inject a safety prompt before all conversations.
+        :param retries: Override the default retry configuration for this method
+        :param server_url: Override the default server URL for this method
+        :param timeout_ms: Override the default request timeout configuration for this method in milliseconds
+        """
+        base_url = None
+        url_variables = None
+        if timeout_ms is None:
+            timeout_ms = self.sdk_configuration.timeout_ms
+        
+        if server_url is not None:
+            base_url = server_url
+        
+        request = models.ChatCompletionRequest(
+            model=model,
+            temperature=temperature,
+            top_p=top_p,
+            max_tokens=max_tokens,
+            min_tokens=min_tokens,
+            stream=stream,
+            stop=stop,
+            random_seed=random_seed,
+            messages=utils.get_pydantic_model(messages, List[models.ChatCompletionRequestMessages]),
+            response_format=utils.get_pydantic_model(response_format, Optional[models.ResponseFormat]),
+            tools=utils.get_pydantic_model(tools, OptionalNullable[List[models.Tool]]),
+            tool_choice=tool_choice,
+            safe_prompt=safe_prompt,
+        )
+        
+        req = self.build_request(
+            method="POST",
+            path="/chat/completions",
+            base_url=base_url,
+            url_variables=url_variables,
+            request=request,
+            request_body_required=True,
+            request_has_path_params=False,
+            request_has_query_params=True,
+            user_agent_header="user-agent",
+            accept_header_value="application/json",
+            security=self.sdk_configuration.security,
+            get_serialized_body=lambda: utils.serialize_request_body(request, False, False, "json", models.ChatCompletionRequest),
+            timeout_ms=timeout_ms,
+        )
+        
+        if retries == UNSET:
+            if self.sdk_configuration.retry_config is not UNSET:
+                retries = self.sdk_configuration.retry_config
+
+        retry_config = None
+        if isinstance(retries, utils.RetryConfig):
+            retry_config = (retries, [
+                "429",
+                "500",
+                "502",
+                "503",
+                "504"
+            ])                
+        
+        http_res = await self.do_request_async(
+            hook_ctx=HookContext(operation_id="chat_completion_v1_chat_completions_post", oauth2_scopes=[], security_source=self.sdk_configuration.security),
+            request=req,
+            error_status_codes=["422","4XX","5XX"],
+            retry_config=retry_config
+        )
+        
+        data: Any = None
+        if utils.match_response(http_res, "200", "application/json"):
+            return utils.unmarshal_json(http_res.text, Optional[models.ChatCompletionResponse])
+        if utils.match_response(http_res, "422", "application/json"):
+            data = utils.unmarshal_json(http_res.text, models.HTTPValidationErrorData)
+            raise models.HTTPValidationError(data=data)
+        if utils.match_response(http_res, ["4XX","5XX"], "*"):
+            raise models.SDKError("API error occurred", http_res.status_code, http_res.text, http_res)
+        
+        content_type = http_res.headers.get("Content-Type")
+        raise models.SDKError(f"Unexpected response received (code: {http_res.status_code}, type: {content_type})", http_res.status_code, http_res.text, http_res)
+
+    

mistralai_azure/httpclient.py

@@ -0,0 +1,78 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+# pyright: reportReturnType = false
+from typing_extensions import Protocol, runtime_checkable
+import httpx
+from typing import Any, Optional, Union
+
+
+@runtime_checkable
+class HttpClient(Protocol):
+    def send(
+        self,
+        request: httpx.Request,
+        *,
+        stream: bool = False,
+        auth: Union[
+            httpx._types.AuthTypes, httpx._client.UseClientDefault, None
+        ] = httpx.USE_CLIENT_DEFAULT,
+        follow_redirects: Union[
+            bool, httpx._client.UseClientDefault
+        ] = httpx.USE_CLIENT_DEFAULT,
+    ) -> httpx.Response:
+        pass
+
+    def build_request(
+        self,
+        method: str,
+        url: httpx._types.URLTypes,
+        *,
+        content: Optional[httpx._types.RequestContent] = None,
+        data: Optional[httpx._types.RequestData] = None,
+        files: Optional[httpx._types.RequestFiles] = None,
+        json: Optional[Any] = None,
+        params: Optional[httpx._types.QueryParamTypes] = None,
+        headers: Optional[httpx._types.HeaderTypes] = None,
+        cookies: Optional[httpx._types.CookieTypes] = None,
+        timeout: Union[
+            httpx._types.TimeoutTypes, httpx._client.UseClientDefault
+        ] = httpx.USE_CLIENT_DEFAULT,
+        extensions: Optional[httpx._types.RequestExtensions] = None,
+    ) -> httpx.Request:
+        pass
+
+
+@runtime_checkable
+class AsyncHttpClient(Protocol):
+    async def send(
+        self,
+        request: httpx.Request,
+        *,
+        stream: bool = False,
+        auth: Union[
+            httpx._types.AuthTypes, httpx._client.UseClientDefault, None
+        ] = httpx.USE_CLIENT_DEFAULT,
+        follow_redirects: Union[
+            bool, httpx._client.UseClientDefault
+        ] = httpx.USE_CLIENT_DEFAULT,
+    ) -> httpx.Response:
+        pass
+
+    def build_request(
+        self,
+        method: str,
+        url: httpx._types.URLTypes,
+        *,
+        content: Optional[httpx._types.RequestContent] = None,
+        data: Optional[httpx._types.RequestData] = None,
+        files: Optional[httpx._types.RequestFiles] = None,
+        json: Optional[Any] = None,
+        params: Optional[httpx._types.QueryParamTypes] = None,
+        headers: Optional[httpx._types.HeaderTypes] = None,
+        cookies: Optional[httpx._types.CookieTypes] = None,
+        timeout: Union[
+            httpx._types.TimeoutTypes, httpx._client.UseClientDefault
+        ] = httpx.USE_CLIENT_DEFAULT,
+        extensions: Optional[httpx._types.RequestExtensions] = None,
+    ) -> httpx.Request:
+        pass

mistralai_azure/models/__init__.py

@@ -0,0 +1,28 @@
+"""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 .completionchunk import CompletionChunk, CompletionChunkTypedDict
+from .completionevent import CompletionEvent, CompletionEventTypedDict
+from .completionresponsestreamchoice import CompletionResponseStreamChoice, CompletionResponseStreamChoiceTypedDict, FinishReason
+from .contentchunk import ContentChunk, ContentChunkTypedDict
+from .deltamessage import DeltaMessage, DeltaMessageTypedDict
+from .function import Function, FunctionTypedDict
+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 .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__ = ["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", "ToolTypedDict", "UsageInfo", "UsageInfoTypedDict", "UserMessage", "UserMessageContent", "UserMessageContentTypedDict", "UserMessageRole", "UserMessageTypedDict", "ValidationError", "ValidationErrorTypedDict"]

mistralai_azure/models/assistantmessage.py

@@ -0,0 +1,53 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+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 List, Literal, Optional, TypedDict
+from typing_extensions import NotRequired
+
+
+AssistantMessageRole = Literal["assistant"]
+
+class AssistantMessageTypedDict(TypedDict):
+    content: NotRequired[Nullable[str]]
+    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
+    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"]
+        nullable_fields = ["content", "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)
+
+            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
+
+            if val is not None and val != UNSET_SENTINEL:
+                m[k] = val
+            elif val != UNSET_SENTINEL and (
+                not k in optional_fields or (optional_nullable and is_set)
+            ):
+                m[k] = val
+
+        return m
+        

mistralai_azure/models/chatcompletionchoice.py

@@ -0,0 +1,22 @@
+"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
+
+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
+
+
+ChatCompletionChoiceFinishReason = Literal["stop", "length", "model_length", "error", "tool_calls"]
+
+class ChatCompletionChoiceTypedDict(TypedDict):
+    index: int
+    finish_reason: ChatCompletionChoiceFinishReason
+    message: NotRequired[AssistantMessageTypedDict]
+    
+
+class ChatCompletionChoice(BaseModel):
+    index: int
+    finish_reason: ChatCompletionChoiceFinishReason
+    message: Optional[AssistantMessage] = None
+