mistralai 0.2.0__tar.gz → 0.3.0__tar.gz

{mistralai-0.2.0 → mistralai-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mistralai
-Version: 0.2.0
+Version: 0.3.0
 Summary: 
 Author: Bam4d
 Author-email: bam4d@mistral.ai

{mistralai-0.2.0 → mistralai-0.3.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "mistralai"
-version = "0.2.0"
+version = "0.3.0"
 description = ""
 authors = ["Bam4d <bam4d@mistral.ai>"]
 readme = "README.md"

{mistralai-0.2.0 → mistralai-0.3.0}/src/mistralai/async_client.py

@@ -92,7 +92,7 @@ class MistralAsyncClient(ClientBase):
     async def _request(
         self,
         method: str,
-        json: Dict[str, Any],
+        json: Optional[Dict[str, Any]],
         path: str,
         stream: bool = False,
         attempt: int = 1,
@@ -291,3 +291,74 @@ class MistralAsyncClient(ClientBase):
             return ModelList(**response)
 
         raise MistralException("No response received")
+
+    async def completion(
+        self,
+        model: str,
+        prompt: str,
+        suffix: Optional[str] = None,
+        temperature: Optional[float] = None,
+        max_tokens: Optional[int] = None,
+        top_p: Optional[float] = None,
+        random_seed: Optional[int] = None,
+        stop: Optional[List[str]] = None,
+    ) -> ChatCompletionResponse:
+        """An asynchronous completion endpoint that returns a single response.
+
+        Args:
+            model (str): model the name of the model to get completions with, e.g. codestral-latest
+            prompt (str): the prompt to complete
+            suffix (Optional[str]): the suffix to append to the prompt for fill-in-the-middle completion
+            temperature (Optional[float], optional): temperature the temperature to use for sampling, e.g. 0.5.
+            max_tokens (Optional[int], optional): the maximum number of tokens to generate, e.g. 100. Defaults to None.
+            top_p (Optional[float], optional): the cumulative probability of tokens to generate, e.g. 0.9.
+            Defaults to None.
+            random_seed (Optional[int], optional): the random seed to use for sampling, e.g. 42. Defaults to None.
+            stop (Optional[List[str]], optional): a list of tokens to stop generation at, e.g. ['/n/n']
+        Returns:
+            Dict[str, Any]: a response object containing the generated text.
+        """
+        request = self._make_completion_request(
+            prompt, model, suffix, temperature, max_tokens, top_p, random_seed, stop
+        )
+        single_response = self._request("post", request, "v1/fim/completions")
+
+        async for response in single_response:
+            return ChatCompletionResponse(**response)
+
+        raise MistralException("No response received")
+
+    async def completion_stream(
+        self,
+        model: str,
+        prompt: str,
+        suffix: Optional[str] = None,
+        temperature: Optional[float] = None,
+        max_tokens: Optional[int] = None,
+        top_p: Optional[float] = None,
+        random_seed: Optional[int] = None,
+        stop: Optional[List[str]] = None,
+    ) -> AsyncGenerator[ChatCompletionStreamResponse, None]:
+        """An asynchronous completion endpoint that returns a streaming response.
+
+        Args:
+            model (str): model the name of the model to get completions with, e.g. codestral-latest
+            prompt (str): the prompt to complete
+            suffix (Optional[str]): the suffix to append to the prompt for fill-in-the-middle completion
+            temperature (Optional[float], optional): temperature the temperature to use for sampling, e.g. 0.5.
+            max_tokens (Optional[int], optional): the maximum number of tokens to generate, e.g. 100. Defaults to None.
+            top_p (Optional[float], optional): the cumulative probability of tokens to generate, e.g. 0.9.
+            Defaults to None.
+            random_seed (Optional[int], optional): the random seed to use for sampling, e.g. 42. Defaults to None.
+            stop (Optional[List[str]], optional): a list of tokens to stop generation at, e.g. ['/n/n']
+
+        Returns:
+            Dict[str, Any]: a response object containing the generated text.
+        """
+        request = self._make_completion_request(
+            prompt, model, suffix, temperature, max_tokens, top_p, random_seed, stop, stream=True
+        )
+        async_response = self._request("post", request, "v1/fim/completions", stream=True)
+
+        async for json_response in async_response:
+            yield ChatCompletionStreamResponse(**json_response)

{mistralai-0.2.0 → mistralai-0.3.0}/src/mistralai/client.py

@@ -85,7 +85,7 @@ class MistralClient(ClientBase):
     def _request(
         self,
         method: str,
-        json: Dict[str, Any],
+        json: Optional[Dict[str, Any]],
         path: str,
         stream: bool = False,
         attempt: int = 1,
@@ -285,3 +285,77 @@ class MistralClient(ClientBase):
             return ModelList(**response)
 
         raise MistralException("No response received")
+
+    def completion(
+        self,
+        model: str,
+        prompt: str,
+        suffix: Optional[str] = None,
+        temperature: Optional[float] = None,
+        max_tokens: Optional[int] = None,
+        top_p: Optional[float] = None,
+        random_seed: Optional[int] = None,
+        stop: Optional[List[str]] = None,
+    ) -> ChatCompletionResponse:
+        """A completion endpoint that returns a single response.
+
+        Args:
+            model (str): model the name of the model to get completion with, e.g. codestral-latest
+            prompt (str): the prompt to complete
+            suffix (Optional[str]): the suffix to append to the prompt for fill-in-the-middle completion
+            temperature (Optional[float], optional): temperature the temperature to use for sampling, e.g. 0.5.
+            max_tokens (Optional[int], optional): the maximum number of tokens to generate, e.g. 100. Defaults to None.
+            top_p (Optional[float], optional): the cumulative probability of tokens to generate, e.g. 0.9.
+            Defaults to None.
+            random_seed (Optional[int], optional): the random seed to use for sampling, e.g. 42. Defaults to None.
+            stop (Optional[List[str]], optional): a list of tokens to stop generation at, e.g. ['/n/n']
+
+        Returns:
+            Dict[str, Any]: a response object containing the generated text.
+        """
+        request = self._make_completion_request(
+            prompt, model, suffix, temperature, max_tokens, top_p, random_seed, stop
+        )
+
+        single_response = self._request("post", request, "v1/fim/completions", stream=False)
+
+        for response in single_response:
+            return ChatCompletionResponse(**response)
+
+        raise MistralException("No response received")
+
+    def completion_stream(
+        self,
+        model: str,
+        prompt: str,
+        suffix: Optional[str] = None,
+        temperature: Optional[float] = None,
+        max_tokens: Optional[int] = None,
+        top_p: Optional[float] = None,
+        random_seed: Optional[int] = None,
+        stop: Optional[List[str]] = None,
+    ) -> Iterable[ChatCompletionStreamResponse]:
+        """An asynchronous completion endpoint that streams responses.
+
+        Args:
+            model (str): model the name of the model to get completions with, e.g. codestral-latest
+            prompt (str): the prompt to complete
+            suffix (Optional[str]): the suffix to append to the prompt for fill-in-the-middle completion
+            temperature (Optional[float], optional): temperature the temperature to use for sampling, e.g. 0.5.
+            max_tokens (Optional[int], optional): the maximum number of tokens to generate, e.g. 100. Defaults to None.
+            top_p (Optional[float], optional): the cumulative probability of tokens to generate, e.g. 0.9.
+            Defaults to None.
+            random_seed (Optional[int], optional): the random seed to use for sampling, e.g. 42. Defaults to None.
+            stop (Optional[List[str]], optional): a list of tokens to stop generation at, e.g. ['/n/n']
+
+        Returns:
+            Iterable[Dict[str, Any]]: a generator that yields response objects containing the generated text.
+        """
+        request = self._make_completion_request(
+            prompt, model, suffix, temperature, max_tokens, top_p, random_seed, stop, stream=True
+        )
+
+        response = self._request("post", request, "v1/fim/completions", stream=True)
+
+        for json_streamed_response in response:
+            yield ChatCompletionStreamResponse(**json_streamed_response)

{mistralai-0.2.0 → mistralai-0.3.0}/src/mistralai/client_base.py

@@ -73,6 +73,63 @@ class ClientBase(ABC):
 
         return parsed_messages
 
+    def _make_completion_request(
+        self,
+        prompt: str,
+        model: Optional[str] = None,
+        suffix: Optional[str] = None,
+        temperature: Optional[float] = None,
+        max_tokens: Optional[int] = None,
+        top_p: Optional[float] = None,
+        random_seed: Optional[int] = None,
+        stop: Optional[List[str]] = None,
+        stream: Optional[bool] = False,
+    ) -> Dict[str, Any]:
+        request_data: Dict[str, Any] = {
+            "prompt": prompt,
+            "suffix": suffix,
+            "model": model,
+            "stream": stream,
+        }
+
+        if stop is not None:
+            request_data["stop"] = stop
+
+        if model is not None:
+            request_data["model"] = model
+        else:
+            if self._default_model is None:
+                raise MistralException(message="model must be provided")
+            request_data["model"] = self._default_model
+
+        request_data.update(
+            self._build_sampling_params(
+                temperature=temperature, max_tokens=max_tokens, top_p=top_p, random_seed=random_seed
+            )
+        )
+
+        self._logger.debug(f"Completion request: {request_data}")
+
+        return request_data
+
+    def _build_sampling_params(
+        self,
+        max_tokens: Optional[int],
+        random_seed: Optional[int],
+        temperature: Optional[float],
+        top_p: Optional[float],
+    ) -> Dict[str, Any]:
+        params = {}
+        if temperature is not None:
+            params["temperature"] = temperature
+        if max_tokens is not None:
+            params["max_tokens"] = max_tokens
+        if top_p is not None:
+            params["top_p"] = top_p
+        if random_seed is not None:
+            params["random_seed"] = random_seed
+        return params
+
     def _make_chat_request(
         self,
         messages: List[Any],
@@ -99,16 +156,14 @@ class ClientBase(ABC):
                 raise MistralException(message="model must be provided")
             request_data["model"] = self._default_model
 
+        request_data.update(
+            self._build_sampling_params(
+                temperature=temperature, max_tokens=max_tokens, top_p=top_p, random_seed=random_seed
+            )
+        )
+
         if tools is not None:
             request_data["tools"] = self._parse_tools(tools)
-        if temperature is not None:
-            request_data["temperature"] = temperature
-        if max_tokens is not None:
-            request_data["max_tokens"] = max_tokens
-        if top_p is not None:
-            request_data["top_p"] = top_p
-        if random_seed is not None:
-            request_data["random_seed"] = random_seed
         if stream is not None:
             request_data["stream"] = stream