mistralai 1.4.0__py3-none-any.whl → 1.5.1__py3-none-any.whl

mistralai/_version.py

@@ -3,10 +3,10 @@
 import importlib.metadata
 
 __title__: str = "mistralai"
-__version__: str = "1.4.0"
+__version__: str = "1.5.1"
 __openapi_doc_version__: str = "0.0.2"
-__gen_version__: str = "2.493.32"
-__user_agent__: str = "speakeasy-sdk/python 1.4.0 2.493.32 0.0.2 mistralai"
+__gen_version__: str = "2.497.0"
+__user_agent__: str = "speakeasy-sdk/python 1.5.1 2.497.0 0.0.2 mistralai"
 
 try:
     if __package__ is not None:

mistralai/chat.py

@@ -3,18 +3,100 @@
 from .basesdk import BaseSDK
 from mistralai import models, utils
 from mistralai._hooks import HookContext
-from mistralai.types import Nullable, OptionalNullable, UNSET
+from mistralai.types import OptionalNullable, UNSET
 from mistralai.utils import eventstreaming, get_security_from_env
 from typing import Any, List, Mapping, Optional, Union
 
+# region imports
+from typing import Type
+from mistralai.extra import (
+    convert_to_parsed_chat_completion_response,
+    response_format_from_pydantic_model,
+    CustomPydanticModel,
+    ParsedChatCompletionResponse,
+)
+# endregion imports
+
 
 class Chat(BaseSDK):
     r"""Chat Completion API."""
 
+    # region sdk-class-body
+    # Custom .parse methods for the Structure Outputs Feature.
+
+    def parse(
+        self, response_format: Type[CustomPydanticModel], **kwargs: Any
+    ) -> ParsedChatCompletionResponse[CustomPydanticModel]:
+        """
+        Parse the response using the provided response format.
+        :param Type[CustomPydanticModel] response_format: The Pydantic model to parse the response into
+        :param Any **kwargs Additional keyword arguments to pass to the .complete method
+        :return: The parsed response
+        """
+        # Convert the input Pydantic Model to a strict JSON ready to be passed to chat.complete
+        json_response_format = response_format_from_pydantic_model(response_format)
+        # Run the inference
+        response = self.complete(**kwargs, response_format=json_response_format)
+        # Parse response back to the input pydantic model
+        parsed_response = convert_to_parsed_chat_completion_response(
+            response, response_format
+        )
+        return parsed_response
+
+    async def parse_async(
+        self, response_format: Type[CustomPydanticModel], **kwargs
+    ) -> ParsedChatCompletionResponse[CustomPydanticModel]:
+        """
+        Asynchronously parse the response using the provided response format.
+        :param Type[CustomPydanticModel] response_format: The Pydantic model to parse the response into
+        :param Any **kwargs Additional keyword arguments to pass to the .complete method
+        :return: The parsed response
+        """
+        json_response_format = response_format_from_pydantic_model(response_format)
+        response = await self.complete_async(  # pylint: disable=E1125
+            **kwargs, response_format=json_response_format
+        )
+        parsed_response = convert_to_parsed_chat_completion_response(
+            response, response_format
+        )
+        return parsed_response
+
+    def parse_stream(
+        self, response_format: Type[CustomPydanticModel], **kwargs
+    ) -> eventstreaming.EventStream[models.CompletionEvent]:
+        """
+        Parse the response using the provided response format.
+        For now the response will be in JSON format not in the input Pydantic model.
+        :param Type[CustomPydanticModel] response_format: The Pydantic model to parse the response into
+        :param Any **kwargs Additional keyword arguments to pass to the .stream method
+        :return: The JSON parsed response
+        """
+        json_response_format = response_format_from_pydantic_model(response_format)
+        response = self.stream(**kwargs, response_format=json_response_format)
+        return response
+
+    async def parse_stream_async(
+        self, response_format: Type[CustomPydanticModel], **kwargs
+    ) -> eventstreaming.EventStreamAsync[models.CompletionEvent]:
+        """
+        Asynchronously parse the response using the provided response format.
+        For now the response will be in JSON format not in the input Pydantic model.
+        :param Type[CustomPydanticModel] response_format: The Pydantic model to parse the response into
+        :param Any **kwargs Additional keyword arguments to pass to the .stream method
+        :return: The JSON parsed response
+        """
+        json_response_format = response_format_from_pydantic_model(response_format)
+        response = await self.stream_async(  # pylint: disable=E1125
+            **kwargs, response_format=json_response_format
+        )
+        return response
+
+    # endregion sdk-class-body
+
     def complete(
         self,
         *,
-        model: Nullable[str],
+        model: str,
         messages: Union[List[models.Messages], List[models.MessagesTypedDict]],
         temperature: OptionalNullable[float] = UNSET,
         top_p: Optional[float] = None,
@@ -171,7 +253,7 @@ class Chat(BaseSDK):
     async def complete_async(
         self,
         *,
-        model: Nullable[str],
+        model: str,
         messages: Union[List[models.Messages], List[models.MessagesTypedDict]],
         temperature: OptionalNullable[float] = UNSET,
         top_p: Optional[float] = None,
@@ -328,7 +410,7 @@ class Chat(BaseSDK):
     def stream(
         self,
         *,
-        model: Nullable[str],
+        model: str,
         messages: Union[
             List[models.ChatCompletionStreamRequestMessages],
             List[models.ChatCompletionStreamRequestMessagesTypedDict],
@@ -503,7 +585,7 @@ class Chat(BaseSDK):
     async def stream_async(
         self,
         *,
-        model: Nullable[str],
+        model: str,
         messages: Union[
             List[models.ChatCompletionStreamRequestMessages],
             List[models.ChatCompletionStreamRequestMessagesTypedDict],

mistralai/classifiers.py

@@ -3,7 +3,7 @@
 from .basesdk import BaseSDK
 from mistralai import models, utils
 from mistralai._hooks import HookContext
-from mistralai.types import Nullable, OptionalNullable, UNSET
+from mistralai.types import OptionalNullable, UNSET
 from mistralai.utils import get_security_from_env
 from typing import Any, Mapping, Optional, Union
 
@@ -14,11 +14,11 @@ class Classifiers(BaseSDK):
     def moderate(
         self,
         *,
+        model: str,
         inputs: Union[
             models.ClassificationRequestInputs,
             models.ClassificationRequestInputsTypedDict,
         ],
-        model: OptionalNullable[str] = UNSET,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
@@ -26,8 +26,8 @@ class Classifiers(BaseSDK):
     ) -> models.ClassificationResponse:
         r"""Moderations
 
+        :param model: ID of the model to use.
         :param inputs: Text to classify.
-        :param model:
         :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
@@ -42,8 +42,8 @@ class Classifiers(BaseSDK):
             base_url = server_url
 
         request = models.ClassificationRequest(
-            inputs=inputs,
             model=model,
+            inputs=inputs,
         )
 
         req = self._build_request(
@@ -115,11 +115,11 @@ class Classifiers(BaseSDK):
     async def moderate_async(
         self,
         *,
+        model: str,
         inputs: Union[
             models.ClassificationRequestInputs,
             models.ClassificationRequestInputsTypedDict,
         ],
-        model: OptionalNullable[str] = UNSET,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
@@ -127,8 +127,8 @@ class Classifiers(BaseSDK):
     ) -> models.ClassificationResponse:
         r"""Moderations
 
+        :param model: ID of the model to use.
         :param inputs: Text to classify.
-        :param model:
         :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
@@ -143,8 +143,8 @@ class Classifiers(BaseSDK):
             base_url = server_url
 
         request = models.ClassificationRequest(
-            inputs=inputs,
             model=model,
+            inputs=inputs,
         )
 
         req = self._build_request_async(
@@ -216,11 +216,12 @@ class Classifiers(BaseSDK):
     def moderate_chat(
         self,
         *,
+        model: str,
         inputs: Union[
-            models.ChatClassificationRequestInputs,
-            models.ChatClassificationRequestInputsTypedDict,
+            models.ChatModerationRequestInputs,
+            models.ChatModerationRequestInputsTypedDict,
         ],
-        model: Nullable[str],
+        truncate_for_context_length: Optional[bool] = False,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
@@ -228,8 +229,9 @@ class Classifiers(BaseSDK):
     ) -> models.ClassificationResponse:
         r"""Moderations Chat
 
-        :param inputs: Chat to classify
         :param model:
+        :param inputs: Chat to classify
+        :param truncate_for_context_length:
         :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
@@ -243,11 +245,10 @@ class Classifiers(BaseSDK):
         if server_url is not None:
             base_url = server_url
 
-        request = models.ChatClassificationRequest(
-            inputs=utils.get_pydantic_model(
-                inputs, models.ChatClassificationRequestInputs
-            ),
+        request = models.ChatModerationRequest(
             model=model,
+            inputs=utils.get_pydantic_model(inputs, models.ChatModerationRequestInputs),
+            truncate_for_context_length=truncate_for_context_length,
         )
 
         req = self._build_request(
@@ -264,7 +265,7 @@ class Classifiers(BaseSDK):
             http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
-                request, False, False, "json", models.ChatClassificationRequest
+                request, False, False, "json", models.ChatModerationRequest
             ),
             timeout_ms=timeout_ms,
         )
@@ -319,11 +320,12 @@ class Classifiers(BaseSDK):
     async def moderate_chat_async(
         self,
         *,
+        model: str,
         inputs: Union[
-            models.ChatClassificationRequestInputs,
-            models.ChatClassificationRequestInputsTypedDict,
+            models.ChatModerationRequestInputs,
+            models.ChatModerationRequestInputsTypedDict,
         ],
-        model: Nullable[str],
+        truncate_for_context_length: Optional[bool] = False,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
@@ -331,8 +333,9 @@ class Classifiers(BaseSDK):
     ) -> models.ClassificationResponse:
         r"""Moderations Chat
 
-        :param inputs: Chat to classify
         :param model:
+        :param inputs: Chat to classify
+        :param truncate_for_context_length:
         :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
@@ -346,11 +349,10 @@ class Classifiers(BaseSDK):
         if server_url is not None:
             base_url = server_url
 
-        request = models.ChatClassificationRequest(
-            inputs=utils.get_pydantic_model(
-                inputs, models.ChatClassificationRequestInputs
-            ),
+        request = models.ChatModerationRequest(
             model=model,
+            inputs=utils.get_pydantic_model(inputs, models.ChatModerationRequestInputs),
+            truncate_for_context_length=truncate_for_context_length,
         )
 
         req = self._build_request_async(
@@ -367,7 +369,7 @@ class Classifiers(BaseSDK):
             http_headers=http_headers,
             security=self.sdk_configuration.security,
             get_serialized_body=lambda: utils.serialize_request_body(
-                request, False, False, "json", models.ChatClassificationRequest
+                request, False, False, "json", models.ChatModerationRequest
             ),
             timeout_ms=timeout_ms,
         )

mistralai/embeddings.py

@@ -16,7 +16,6 @@ class Embeddings(BaseSDK):
         *,
         inputs: Union[models.Inputs, models.InputsTypedDict],
         model: Optional[str] = "mistral-embed",
-        encoding_format: OptionalNullable[str] = UNSET,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
@@ -28,7 +27,6 @@ class Embeddings(BaseSDK):
 
         :param inputs: Text to embed.
         :param model: ID of the model to use.
-        :param encoding_format: The format to return the embeddings in.
         :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
@@ -43,9 +41,8 @@ class Embeddings(BaseSDK):
             base_url = server_url
 
         request = models.EmbeddingRequest(
-            inputs=inputs,
             model=model,
-            encoding_format=encoding_format,
+            inputs=inputs,
         )
 
         req = self._build_request(
@@ -119,7 +116,6 @@ class Embeddings(BaseSDK):
         *,
         inputs: Union[models.Inputs, models.InputsTypedDict],
         model: Optional[str] = "mistral-embed",
-        encoding_format: OptionalNullable[str] = UNSET,
         retries: OptionalNullable[utils.RetryConfig] = UNSET,
         server_url: Optional[str] = None,
         timeout_ms: Optional[int] = None,
@@ -131,7 +127,6 @@ class Embeddings(BaseSDK):
 
         :param inputs: Text to embed.
         :param model: ID of the model to use.
-        :param encoding_format: The format to return the embeddings in.
         :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
@@ -146,9 +141,8 @@ class Embeddings(BaseSDK):
             base_url = server_url
 
         request = models.EmbeddingRequest(
-            inputs=inputs,
             model=model,
-            encoding_format=encoding_format,
+            inputs=inputs,
         )
 
         req = self._build_request_async(

mistralai/extra/README.md

@@ -0,0 +1,56 @@
+## Context
+
+The extra package contains the custom logic which is too complex to be generated by Speakeasy from the OpenAPI specs. It was introduced to add the Structured Outputs feature.
+
+## Development / Contributing
+
+To add custom code in the SDK, you need to use [Speakeasy custom code regions](https://www.speakeasy.com/docs/customize/code/code-regions/overview) as below.
+
+### Runbook of SDK customization
+
+1. Add the code you want to import in the `src/mistralai/extra/` package. To have it importable from the SDK, you need to add it in the `__init__.py` file:
+```python
+from .my_custom_file import my_custom_function
+
+__all__ = ["my_custom_function"]
+```
+
+2. Add a new custom code region in the SDK files, e.g in `src/mistralai/chat.py`:
+```python
+# region imports
+from typing import Type
+from mistralai.extra import my_custom_function
+# endregion imports
+
+class Chat(BaseSDK):
+    r"""Chat Completion API."""
+
+    # region sdk-class-body
+    def my_custom_method(self, param: str) -> Type[some_type]:
+        output = my_custom_function(param1)
+        return output
+    # endregion sdk-class-body
+```
+
+3. Now build the SDK with the custom code:
+```bash
+rm -rf dist; poetry build; python3 -m pip install ~/client-python/dist/mistralai-1.4.1-py3-none-any.whl --force-reinstall
+```
+
+4. And now you should be able to call the custom method:
+```python
+import os
+from mistralai import Mistral
+
+api_key = os.environ["MISTRAL_API_KEY"]
+client = Mistral(api_key=api_key)
+
+client.chat.my_custom_method(param="test")
+```
+
+### Run the unit tests
+
+To run the unit tests for the `extra` package, you can run the following command from the root of the repository:
+```bash
+python3.12 -m unittest discover -s src/mistralai/extra/tests -t src
+```

mistralai/extra/__init__.py

@@ -0,0 +1,5 @@
+from .struct_chat import ParsedChatCompletionResponse, convert_to_parsed_chat_completion_response
+from .utils import response_format_from_pydantic_model
+from .utils.response_format import CustomPydanticModel
+
+__all__ = ["convert_to_parsed_chat_completion_response", "response_format_from_pydantic_model", "CustomPydanticModel", "ParsedChatCompletionResponse"]

mistralai/extra/struct_chat.py

@@ -0,0 +1,41 @@
+from ..models import ChatCompletionResponse, ChatCompletionChoice, AssistantMessage
+from .utils.response_format import  CustomPydanticModel, pydantic_model_from_json
+from typing import List, Optional, Type, Generic
+from pydantic import BaseModel
+import json
+
+class ParsedAssistantMessage(AssistantMessage, Generic[CustomPydanticModel]):
+    parsed: Optional[CustomPydanticModel]
+
+class ParsedChatCompletionChoice(ChatCompletionChoice, Generic[CustomPydanticModel]):
+    message: Optional[ParsedAssistantMessage[CustomPydanticModel]]  # type: ignore
+
+class ParsedChatCompletionResponse(ChatCompletionResponse, Generic[CustomPydanticModel]):
+    choices: Optional[List[ParsedChatCompletionChoice[CustomPydanticModel]]] # type: ignore
+
+def convert_to_parsed_chat_completion_response(response: ChatCompletionResponse, response_format: Type[BaseModel]) -> ParsedChatCompletionResponse:
+    parsed_choices = []
+
+    if response.choices:
+        for choice in response.choices:
+            if choice.message:
+                parsed_message: ParsedAssistantMessage = ParsedAssistantMessage(
+                    **choice.message.model_dump(),
+                    parsed=None
+                )
+                if isinstance(parsed_message.content, str):
+                    parsed_message.parsed = pydantic_model_from_json(json.loads(parsed_message.content), response_format)
+                elif parsed_message.content is None:
+                    parsed_message.parsed = None
+                else:
+                    raise TypeError(f"Unexpected type for message.content: {type(parsed_message.content)}")
+                choice_dict = choice.model_dump()
+                choice_dict["message"] = parsed_message
+                parsed_choice: ParsedChatCompletionChoice = ParsedChatCompletionChoice(**choice_dict)
+                parsed_choices.append(parsed_choice)
+            else:
+                parsed_choice = ParsedChatCompletionChoice(**choice.model_dump())
+                parsed_choices.append(parsed_choice)
+    response_dict = response.model_dump()
+    response_dict["choices"] = parsed_choices
+    return ParsedChatCompletionResponse(**response_dict)

mistralai/extra/tests/test_struct_chat.py

@@ -0,0 +1,103 @@
+import unittest
+from ..struct_chat import (
+    convert_to_parsed_chat_completion_response,
+    ParsedChatCompletionResponse,
+    ParsedChatCompletionChoice,
+    ParsedAssistantMessage,
+)
+from ...models import (
+    ChatCompletionResponse,
+    UsageInfo,
+    ChatCompletionChoice,
+    AssistantMessage,
+)
+from pydantic import BaseModel
+
+
+class Explanation(BaseModel):
+    explanation: str
+    output: str
+
+
+class MathDemonstration(BaseModel):
+    steps: list[Explanation]
+    final_answer: str
+
+
+mock_cc_response = ChatCompletionResponse(
+    id="c0271b2098954c6094231703875ca0bc",
+    object="chat.completion",
+    model="mistral-large-latest",
+    usage=UsageInfo(prompt_tokens=75, completion_tokens=220, total_tokens=295),
+    created=1737727558,
+    choices=[
+        ChatCompletionChoice(
+            index=0,
+            message=AssistantMessage(
+                content='{\n  "final_answer": "x = -4",\n  "steps": [\n    {\n      "explanation": "Start with the given equation.",\n      "output": "8x + 7 = -23"\n    },\n    {\n      "explanation": "Subtract 7 from both sides to isolate the term with x.",\n      "output": "8x = -23 - 7"\n    },\n    {\n      "explanation": "Simplify the right side of the equation.",\n      "output": "8x = -30"\n    },\n    {\n      "explanation": "Divide both sides by 8 to solve for x.",\n      "output": "x = -30 / 8"\n    },\n    {\n      "explanation": "Simplify the fraction to get the final answer.",\n      "output": "x = -4"\n    }\n  ]\n}',
+                tool_calls=None,
+                prefix=False,
+                role="assistant",
+            ),
+            finish_reason="stop",
+        )
+    ],
+)
+
+
+expected_response = ParsedChatCompletionResponse(
+    choices=[
+        ParsedChatCompletionChoice(
+            index=0,
+            message=ParsedAssistantMessage(
+                content='{\n  "final_answer": "x = -4",\n  "steps": [\n    {\n      "explanation": "Start with the given equation.",\n      "output": "8x + 7 = -23"\n    },\n    {\n      "explanation": "Subtract 7 from both sides to isolate the term with x.",\n      "output": "8x = -23 - 7"\n    },\n    {\n      "explanation": "Simplify the right side of the equation.",\n      "output": "8x = -30"\n    },\n    {\n      "explanation": "Divide both sides by 8 to solve for x.",\n      "output": "x = -30 / 8"\n    },\n    {\n      "explanation": "Simplify the fraction to get the final answer.",\n      "output": "x = -4"\n    }\n  ]\n}',
+                tool_calls=None,
+                prefix=False,
+                role="assistant",
+                parsed=MathDemonstration(
+                    steps=[
+                        Explanation(
+                            explanation="Start with the given equation.",
+                            output="8x + 7 = -23",
+                        ),
+                        Explanation(
+                            explanation="Subtract 7 from both sides to isolate the term with x.",
+                            output="8x = -23 - 7",
+                        ),
+                        Explanation(
+                            explanation="Simplify the right side of the equation.",
+                            output="8x = -30",
+                        ),
+                        Explanation(
+                            explanation="Divide both sides by 8 to solve for x.",
+                            output="x = -30 / 8",
+                        ),
+                        Explanation(
+                            explanation="Simplify the fraction to get the final answer.",
+                            output="x = -4",
+                        ),
+                    ],
+                    final_answer="x = -4",
+                ),
+            ),
+            finish_reason="stop",
+        )
+    ],
+    created=1737727558,
+    id="c0271b2098954c6094231703875ca0bc",
+    model="mistral-large-latest",
+    object="chat.completion",
+    usage=UsageInfo(prompt_tokens=75, completion_tokens=220, total_tokens=295),
+)
+
+
+class TestConvertToParsedChatCompletionResponse(unittest.TestCase):
+    def test_convert_to_parsed_chat_completion_response(self):
+        output = convert_to_parsed_chat_completion_response(
+            mock_cc_response, MathDemonstration
+        )
+        self.assertEqual(output, expected_response)
+
+
+if __name__ == "__main__":
+    unittest.main()