mirascope 1.22.4__py3-none-any.whl → 2.1.1__py3-none-any.whl

mirascope/core/mistral/dynamic_config.py

@@ -1,33 +0,0 @@
-"""This module defines the function return type for functions as LLM calls."""
-
-from mistralai import Mistral
-from mistralai.models import (
-    AssistantMessage,
-    SystemMessage,
-    ToolMessage,
-    UserMessage,
-)
-
-from ..base import BaseDynamicConfig, BaseMessageParam
-from .call_params import MistralCallParams
-
-MistralDynamicConfig = BaseDynamicConfig[
-    AssistantMessage | SystemMessage | ToolMessage | UserMessage | BaseMessageParam,
-    MistralCallParams,
-    Mistral,
-]
-"""The function return type for functions wrapped with the `mistral_call` decorator.
-
-Example:
-
-```python
-from mirascope.core import prompt_template
-from mirascope.core.mistral import MistralDynamicConfig, mistral_call
-
-
-@mistral_call("mistral-large-latest")
-@prompt_template("Recommend a {capitalized_genre} book")
-def recommend_book(genre: str) -> MistralDynamicConfig:
-    return {"computed_fields": {"capitalized_genre": genre.capitalize()}}
-```
-"""

mirascope/core/mistral/stream.py

@@ -1,120 +0,0 @@
-"""The `MistralStream` class for convenience around streaming LLM calls.
-
-usage docs: learn/streams.md
-"""
-
-from typing import Any, cast
-
-from mistralai.models import (
-    AssistantMessage,
-    ChatCompletionChoice,
-    ChatCompletionResponse,
-    FinishReason,
-    SystemMessage,
-    ToolMessage,
-    UsageInfo,
-    UserMessage,
-)
-
-from ..base.stream import BaseStream
-from ..base.types import CostMetadata
-from .call_params import MistralCallParams
-from .call_response import MistralCallResponse
-from .call_response_chunk import MistralCallResponseChunk
-from .dynamic_config import MistralDynamicConfig
-from .tool import MistralTool
-
-
-class MistralStream(
-    BaseStream[
-        MistralCallResponse,
-        MistralCallResponseChunk,
-        UserMessage,
-        AssistantMessage,
-        ToolMessage,
-        AssistantMessage | SystemMessage | ToolMessage | UserMessage,
-        MistralTool,
-        dict[str, Any],
-        MistralDynamicConfig,
-        MistralCallParams,
-        FinishReason,
-    ]
-):
-    """A class for convenience around streaming Mistral LLM calls.
-
-    Example:
-
-    ```python
-    from mirascope.core import prompt_template
-    from mirascope.core.mistral import mistral_call
-
-
-    @mistral_call("mistral-large-latest", stream=True)
-    def recommend_book(genre: str) -> str:
-        return f"Recommend a {genre} book"
-
-
-    stream = recommend_book("fantasy")  # returns `MistralStream` instance
-    for chunk, _ in stream:
-        print(chunk.content, end="", flush=True)
-    ```
-    """
-
-    _provider = "mistral"
-
-    def _construct_message_param(
-        self, tool_calls: list | None = None, content: str | None = None
-    ) -> AssistantMessage:
-        message_param = AssistantMessage(
-            content=content if content else "", tool_calls=tool_calls
-        )
-        return message_param
-
-    def construct_call_response(self) -> MistralCallResponse:
-        """Constructs the call response from a consumed MistralStream.
-
-        Raises:
-            ValueError: if the stream has not yet been consumed.
-        """
-        if not hasattr(self, "message_param"):
-            raise ValueError(
-                "No stream response, check if the stream has been consumed."
-            )
-        usage = UsageInfo(
-            prompt_tokens=int(self.input_tokens or 0),
-            completion_tokens=int(self.output_tokens or 0),
-            total_tokens=int(self.input_tokens or 0) + int(self.output_tokens or 0),
-        )
-        finish_reason = cast(FinishReason, (self.finish_reasons or [])[0])
-        completion = ChatCompletionResponse(
-            id=self.id if self.id else "",
-            choices=[
-                ChatCompletionChoice(
-                    finish_reason=finish_reason,
-                    index=0,
-                    message=self.message_param,
-                )
-            ],
-            created=0,
-            model=self.model,
-            object="",
-            usage=usage,
-        )
-        return MistralCallResponse(
-            metadata=self.metadata,
-            response=completion,
-            tool_types=self.tool_types,
-            prompt_template=self.prompt_template,
-            fn_args=self.fn_args if self.fn_args else {},
-            dynamic_config=self.dynamic_config,
-            messages=self.messages,
-            call_params=self.call_params,
-            call_kwargs=self.call_kwargs,
-            user_message_param=self.user_message_param,
-            start_time=self.start_time,
-            end_time=self.end_time,
-        )
-
-    @property
-    def cost_metadata(self) -> CostMetadata:
-        return super().cost_metadata

mirascope/core/mistral/tool.py

@@ -1,80 +0,0 @@
-"""The `MistralTool` class for easy tool usage with Mistral LLM calls.
-
-usage docs: learn/tools.md
-"""
-
-from __future__ import annotations
-
-from typing import Any
-
-import jiter
-from mistralai.models import ToolCall
-from pydantic.json_schema import SkipJsonSchema
-
-from ..base import BaseTool
-
-
-class MistralTool(BaseTool):
-    """A class for defining tools for Mistral LLM calls.
-
-    Example:
-
-    ```python
-    from mirascope.core import prompt_template
-    from mirascope.core.mistral import mistral_call
-
-
-    def format_book(title: str, author: str) -> str:
-        return f"{title} by {author}"
-
-
-    @mistral_call("mistral-large-latest", tools=[format_book])
-    def recommend_book(genre: str) -> str:
-        return f"Recommend a {genre} book"
-
-    response = recommend_book("fantasy")
-    if tool := response.tool:  # returns a `MistralTool` instance
-        print(tool.call())
-    ```
-    """
-
-    __provider__ = "mistral"
-
-    tool_call: SkipJsonSchema[ToolCall]
-
-    @classmethod
-    def tool_schema(cls) -> dict[str, Any]:
-        """Constructs a JSON Schema tool schema from the `BaseModel` schema defined.
-
-        Example:
-        ```python
-        from mirascope.core.mistral import MistralTool
-
-
-        def format_book(title: str, author: str) -> str:
-            return f"{title} by {author}"
-
-
-        tool_type = MistralTool.type_from_fn(format_book)
-        print(tool_type.tool_schema())  # prints the Mistral-specific tool schema
-        ```
-        """
-        fn: dict[str, Any] = {"name": cls._name(), "description": cls._description()}
-        model_schema = cls.model_json_schema()
-        if model_schema["properties"]:
-            fn["parameters"] = model_schema
-        return {"function": fn, "type": "function"}
-
-    @classmethod
-    def from_tool_call(cls, tool_call: ToolCall) -> MistralTool:
-        """Constructs an `MistralTool` instance from a `tool_call`.
-
-        Args:
-            tool_call: The Mistral tool call from which to construct this tool instance.
-        """
-        model_json = {"tool_call": tool_call}
-        if args := tool_call.function.arguments:
-            model_json |= (
-                jiter.from_json(args.encode()) if isinstance(args, str) else args
-            )
-        return cls.model_validate(model_json)

mirascope/core/openai/__init__.py

@@ -1,31 +0,0 @@
-"""The Mirascope OpenAI Module."""
-
-from typing import TypeAlias
-
-from openai.types.chat import ChatCompletionMessageParam
-
-from ..base import BaseMessageParam
-from ._call import openai_call
-from ._call import openai_call as call
-from .call_params import OpenAICallParams
-from .call_response import OpenAICallResponse
-from .call_response_chunk import OpenAICallResponseChunk
-from .dynamic_config import AsyncOpenAIDynamicConfig, OpenAIDynamicConfig
-from .stream import OpenAIStream
-from .tool import OpenAITool, OpenAIToolConfig
-
-OpenAIMessageParam: TypeAlias = ChatCompletionMessageParam | BaseMessageParam
-
-__all__ = [
-    "AsyncOpenAIDynamicConfig",
-    "OpenAICallParams",
-    "OpenAICallResponse",
-    "OpenAICallResponseChunk",
-    "OpenAIDynamicConfig",
-    "OpenAIMessageParam",
-    "OpenAIStream",
-    "OpenAITool",
-    "OpenAIToolConfig",
-    "call",
-    "openai_call",
-]

mirascope/core/openai/_call.py

@@ -1,67 +0,0 @@
-"""The `openai_call` decorator for functions as LLM calls."""
-
-from ..base import call_factory
-from ._utils import (
-    get_json_output,
-    handle_stream,
-    handle_stream_async,
-    setup_call,
-)
-from .call_params import OpenAICallParams
-from .call_response import OpenAICallResponse
-from .call_response_chunk import OpenAICallResponseChunk
-from .stream import OpenAIStream
-from .tool import OpenAITool
-
-openai_call = call_factory(
-    TCallResponse=OpenAICallResponse,
-    TCallResponseChunk=OpenAICallResponseChunk,
-    TToolType=OpenAITool,
-    TStream=OpenAIStream,
-    default_call_params=OpenAICallParams(),
-    setup_call=setup_call,
-    get_json_output=get_json_output,
-    handle_stream=handle_stream,
-    handle_stream_async=handle_stream_async,
-)
-"""A decorator for calling the OpenAI API with a typed function.
-
-usage docs: learn/calls.md
-
-This decorator is used to wrap a typed function that calls the OpenAI API. It parses
-the prompt template of the wrapped function as the messages array and templates the input
-arguments for the function into each message's template.
-
-Example:
-
-```python
-from mirascope.core import prompt_template
-from mirascope.core.openai import openai_call
-
-
-@openai_call("gpt-4o-mini")
-def recommend_book(genre: str) -> str:
-    return f"Recommend a {genre} book"
-
-response = recommend_book("fantasy")
-print(response.content)
-```
-
-Args:
-    model (str): The OpenAI model to use in the API call.
-    stream (bool): Whether to stream the response from the API call.
-    tools (list[BaseTool | Callable]): The tools to use in the OpenAI API call.
-    response_model (BaseModel | BaseType): The response model into which the response
-        should be structured.
-    output_parser (Callable[[OpenAICallResponse | ResponseModelT], Any]): A function for 
-        parsing the call response whose value will be returned in place of the original
-        call response.
-    json_mode (bool): Whether to use JSON Mode.
-    client (object): An optional custom client to use in place of the default client.
-    call_params (OpenAICallParams): The `OpenAICallParams` call parameters to use in the
-        API call.
-
-Returns:
-    decorator (Callable): The decorator for turning a typed function into an OpenAI API
-        call.
-"""

mirascope/core/openai/_call_kwargs.py

@@ -1,13 +0,0 @@
-"""This module contains the type definition for the OpenAI call keyword arguments."""
-
-from collections.abc import Sequence
-
-from openai.types.chat import ChatCompletionMessageParam, ChatCompletionToolParam
-
-from ..base import BaseCallKwargs
-from .call_params import OpenAICallParams
-
-
-class OpenAICallKwargs(OpenAICallParams, BaseCallKwargs[ChatCompletionToolParam]):
-    model: str
-    messages: Sequence[ChatCompletionMessageParam]

mirascope/core/openai/_utils/__init__.py

@@ -1,14 +0,0 @@
-"""OpenAI utilities for decorator factories."""
-
-from ._convert_message_params import convert_message_params
-from ._get_json_output import get_json_output
-from ._handle_stream import handle_stream, handle_stream_async
-from ._setup_call import setup_call
-
-__all__ = [
-    "convert_message_params",
-    "get_json_output",
-    "handle_stream",
-    "handle_stream_async",
-    "setup_call",
-]

mirascope/core/openai/_utils/_convert_common_call_params.py

@@ -1,26 +0,0 @@
-from typing import cast
-
-from ...base.call_params import CommonCallParams
-from ..call_params import OpenAICallParams
-
-OPENAI_PARAM_MAPPING = {
-    "temperature": "temperature",
-    "max_tokens": "max_tokens",
-    "top_p": "top_p",
-    "frequency_penalty": "frequency_penalty",
-    "presence_penalty": "presence_penalty",
-    "seed": "seed",
-    "stop": "stop",
-}
-
-
-def convert_common_call_params(common_params: CommonCallParams) -> OpenAICallParams:
-    """Convert CommonCallParams to OpenAI parameters."""
-    return cast(
-        OpenAICallParams,
-        {
-            OPENAI_PARAM_MAPPING[key]: value
-            for key, value in common_params.items()
-            if key in OPENAI_PARAM_MAPPING and value is not None
-        },
-    )

mirascope/core/openai/_utils/_convert_message_params.py

@@ -1,146 +0,0 @@
-"""Utility for converting `BaseMessageParam` to `ChatCompletionMessageParam`."""
-
-import base64
-import json
-
-from openai.types.chat import ChatCompletionMessageParam
-
-from ...base import BaseMessageParam
-from ...base._utils import get_audio_type
-from ...base._utils._parse_content_template import _load_media
-
-
-def convert_message_params(
-    message_params: list[BaseMessageParam | ChatCompletionMessageParam],
-) -> list[ChatCompletionMessageParam]:
-    converted_message_params = []
-    for message_param in message_params:
-        if not isinstance(message_param, BaseMessageParam):
-            converted_message_params.append(message_param)
-        elif isinstance((content := message_param.content), str):
-            converted_message_params.append(message_param.model_dump())
-        else:
-            converted_content = []
-
-            for part in content:
-                if part.type == "text":
-                    converted_content.append(part.model_dump())
-                elif part.type == "image":
-                    if part.media_type not in [
-                        "image/jpeg",
-                        "image/png",
-                        "image/gif",
-                        "image/webp",
-                    ]:
-                        raise ValueError(
-                            f"Unsupported image media type: {part.media_type}. OpenAI"
-                            " currently only supports JPEG, PNG, GIF, and WebP images."
-                        )
-                    data = base64.b64encode(part.image).decode("utf-8")
-                    converted_content.append(
-                        {
-                            "type": "image_url",
-                            "image_url": {
-                                "url": f"data:{part.media_type};base64,{data}",
-                                "detail": part.detail if part.detail else "auto",
-                            },
-                        }
-                    )
-                elif part.type == "image_url":
-                    converted_content.append(
-                        {
-                            "type": "image_url",
-                            "image_url": {
-                                "url": part.url,
-                                "detail": part.detail if part.detail else "auto",
-                            },
-                        }
-                    )
-                elif part.type == "audio":
-                    if part.media_type not in [
-                        "audio/wav",
-                        "audio/mp3",
-                    ]:
-                        raise ValueError(
-                            f"Unsupported audio media type: {part.media_type}. "
-                            "OpenAI currently only supports WAV and MP3 audio file types."
-                        )
-                    data = (
-                        part.audio
-                        if isinstance(part.audio, str)
-                        else base64.b64encode(part.audio).decode("utf-8")
-                    )
-                    converted_content.append(
-                        {
-                            "input_audio": {
-                                "format": part.media_type.split("/")[-1],
-                                "data": data,
-                            },
-                            "type": "input_audio",
-                        }
-                    )
-                elif part.type == "audio_url":
-                    audio = _load_media(part.url)
-                    audio_type = get_audio_type(audio)
-                    if audio_type not in [
-                        "wav",
-                        "mp3",
-                    ]:
-                        raise ValueError(
-                            f"Unsupported audio media type: audio/{audio_type}. "
-                            "OpenAI currently only supports WAV and MP3 audio file types."
-                        )
-                    converted_content.append(
-                        {
-                            "input_audio": {
-                                "format": audio_type,
-                                "data": base64.b64encode(audio).decode("utf-8"),
-                            },
-                            "type": "input_audio",
-                        }
-                    )
-                elif part.type == "tool_call":
-                    converted_message_param = {
-                        "role": "assistant",
-                        "name": part.name,
-                        "tool_calls": [
-                            {
-                                "function": {
-                                    "name": part.name,
-                                    "arguments": json.dumps(part.args),
-                                },
-                                "type": "function",
-                                "id": part.id,
-                            }
-                        ],
-                    }
-
-                    if converted_content:
-                        converted_message_param["content"] = converted_content
-                        converted_content = []
-                    converted_message_params.append(converted_message_param)
-                elif part.type == "tool_result":
-                    if converted_content:
-                        converted_message_params.append(
-                            {"role": message_param.role, "content": converted_content}
-                        )
-                        converted_content = []
-
-                    converted_message_params.append(
-                        {
-                            "role": "tool",
-                            "tool_call_id": part.id,
-                            "content": part.content,
-                        }
-                    )
-                else:
-                    raise ValueError(
-                        "OpenAI currently only supports text, image and audio parts. "
-                        f"Part provided: {part.type}"
-                    )
-            if converted_content:
-                converted_message_params.append(
-                    {"role": message_param.role, "content": converted_content}
-                )
-    # print(converted_message_params)
-    return converted_message_params

mirascope/core/openai/_utils/_get_json_output.py

@@ -1,31 +0,0 @@
-"""Get the JSON output from a completion response."""
-
-from ..call_response import OpenAICallResponse
-from ..call_response_chunk import OpenAICallResponseChunk
-
-
-def get_json_output(
-    response: OpenAICallResponse | OpenAICallResponseChunk, json_mode: bool
-) -> str:
-    """Get the JSON output from a completion response."""
-    if isinstance(response, OpenAICallResponse):
-        if hasattr(response.response.choices[0].message, "refusal") and (
-            refusal := response.response.choices[0].message.refusal
-        ):
-            raise ValueError(refusal)
-        elif json_mode and response.content:
-            return response.content
-        elif tool_calls := response.response.choices[0].message.tool_calls:
-            return tool_calls[0].function.arguments
-        raise ValueError("No tool call or JSON object found in response.")
-    else:
-        if json_mode:
-            return response.content
-        elif (
-            (choices := response.chunk.choices)
-            and (tool_calls := choices[0].delta.tool_calls)
-            and (function := tool_calls[0].function)
-            and (arguments := function.arguments) is not None
-        ):
-            return arguments
-        return ""