mirascope 1.0.5__py3-none-any.whl → 2.1.1__py3-none-any.whl

mirascope/core/openai/call_response.py

@@ -1,162 +0,0 @@
-"""This module contains the `OpenAICallResponse` class.
-
-usage docs: learn/calls.md#handling-responses
-"""
-
-from openai.types.chat import (
-    ChatCompletion,
-    ChatCompletionAssistantMessageParam,
-    ChatCompletionMessageParam,
-    ChatCompletionToolMessageParam,
-    ChatCompletionUserMessageParam,
-)
-from openai.types.completion_usage import CompletionUsage
-from pydantic import SerializeAsAny, SkipValidation, computed_field
-
-from ..base import BaseCallResponse
-from ._utils import calculate_cost
-from .call_params import OpenAICallParams
-from .dynamic_config import OpenAIDynamicConfig
-from .tool import OpenAITool
-
-
-class OpenAICallResponse(
-    BaseCallResponse[
-        ChatCompletion,
-        OpenAITool,
-        OpenAIDynamicConfig,
-        ChatCompletionMessageParam,
-        OpenAICallParams,
-        ChatCompletionUserMessageParam,
-    ]
-):
-    """A convenience wrapper around the OpenAI `ChatCompletion` response.
-
-    When calling the OpenAI API using a function decorated with `openai_call`, the
-    response will be an `OpenAICallResponse` instance with properties that allow for
-    more convenience access to commonly used attributes.
-
-    Example:
-
-    ```python
-    from mirascope.core import prompt_template
-    from mirascope.core.openai import openai_call
-
-
-    @openai_call("gpt-4o")
-    @prompt_template("Recommend a {genre} book")
-    def recommend_book(genre: str):
-        ...
-
-
-    response = recommend_book("fantasy")  # response is an `OpenAICallResponse` instance
-    print(response.content)
-    ```
-    """
-
-    response: SkipValidation[ChatCompletion]
-
-    _provider = "openai"
-
-    @property
-    def content(self) -> str:
-        """Returns the content of the chat completion for the 0th choice."""
-        message = self.response.choices[0].message
-        return message.content if message.content is not None else ""
-
-    @property
-    def finish_reasons(self) -> list[str]:
-        """Returns the finish reasons of the response."""
-        return [str(choice.finish_reason) for choice in self.response.choices]
-
-    @property
-    def model(self) -> str:
-        """Returns the name of the response model."""
-        return self.response.model
-
-    @property
-    def id(self) -> str:
-        """Returns the id of the response."""
-        return self.response.id
-
-    @property
-    def usage(self) -> CompletionUsage | None:
-        """Returns the usage of the chat completion."""
-        return self.response.usage
-
-    @property
-    def input_tokens(self) -> int | None:
-        """Returns the number of input tokens."""
-        return self.usage.prompt_tokens if self.usage else None
-
-    @property
-    def output_tokens(self) -> int | None:
-        """Returns the number of output tokens."""
-        return self.usage.completion_tokens if self.usage else None
-
-    @property
-    def cost(self) -> float | None:
-        """Returns the cost of the call."""
-        return calculate_cost(self.input_tokens, self.output_tokens, self.model)
-
-    @computed_field
-    @property
-    def message_param(self) -> SerializeAsAny[ChatCompletionAssistantMessageParam]:
-        """Returns the assistants's response as a message parameter."""
-        return self.response.choices[0].message.model_dump(exclude={"function_call"})  # type: ignore
-
-    @computed_field
-    @property
-    def tools(self) -> list[OpenAITool] | None:
-        """Returns any available tool calls as their `OpenAITool` definition.
-
-        Raises:
-            ValidationError: if a tool call doesn't match the tool's schema.
-        """
-        tool_calls = self.response.choices[0].message.tool_calls
-        if not self.tool_types or not tool_calls:
-            return None
-
-        extracted_tools = []
-        for tool_call in tool_calls:
-            for tool_type in self.tool_types:
-                if tool_call.function.name == tool_type._name():
-                    extracted_tools.append(tool_type.from_tool_call(tool_call))
-                    break
-
-        return extracted_tools
-
-    @computed_field
-    @property
-    def tool(self) -> OpenAITool | None:
-        """Returns the 0th tool for the 0th choice message.
-
-        Raises:
-            ValidationError: if the tool call doesn't match the tool's schema.
-        """
-        if tools := self.tools:
-            return tools[0]
-        return None
-
-    @classmethod
-    def tool_message_params(
-        cls, tools_and_outputs: list[tuple[OpenAITool, str]]
-    ) -> list[ChatCompletionToolMessageParam]:
-        """Returns the tool message parameters for tool call results.
-
-        Args:
-            tools_and_outputs: The list of tools and their outputs from which the tool
-                message parameters should be constructed.
-
-        Returns:
-            The list of constructed `ChatCompletionToolMessageParam` parameters.
-        """
-        return [
-            ChatCompletionToolMessageParam(
-                role="tool",
-                content=output,
-                tool_call_id=tool.tool_call.id,
-                name=tool._name(),  # type: ignore
-            )
-            for tool, output in tools_and_outputs
-        ]

mirascope/core/openai/call_response_chunk.py

@@ -1,90 +0,0 @@
-"""This module contains the `OpenAICallResponseChunk` class.
-
-usage docs: learn/streams.md#handling-streamed-responses
-"""
-
-from openai.types.chat import ChatCompletionChunk
-from openai.types.chat.chat_completion_chunk import Choice
-from openai.types.completion_usage import CompletionUsage
-from pydantic import SkipValidation
-
-from ..base import BaseCallResponseChunk
-
-FinishReason = Choice.__annotations__["finish_reason"]
-
-
-class OpenAICallResponseChunk(BaseCallResponseChunk[ChatCompletionChunk, FinishReason]):
-    """A convenience wrapper around the OpenAI `ChatCompletionChunk` streamed chunks.
-
-    When calling the OpenAI API using a function decorated with `openai_call` and
-    `stream` set to `True`, the stream will contain `OpenAIResponseChunk` instances with
-    properties that allow for more convenient access to commonly used attributes.
-
-    Example:
-
-    ```python
-    from mirascope.core import prompt_template
-    from mirascope.core.openai import openai_call
-
-
-    @openai_call("gpt-4o-mini", stream=True)
-    @prompt_template("Recommend a {genre} book")
-    def recommend_book(genre: str):
-        ...
-
-
-    stream = recommend_book("fantasy")  # response is an `OpenAIStream`
-    for chunk, _ in stream:
-        print(chunk.content, end="", flush=True)
-    ```
-    """
-
-    chunk: SkipValidation[ChatCompletionChunk]
-
-    @property
-    def content(self) -> str:
-        """Returns the content for the 0th choice delta."""
-        delta = None
-        if self.chunk.choices:
-            delta = self.chunk.choices[0].delta
-        return delta.content if delta is not None and delta.content else ""
-
-    @property
-    def finish_reasons(self) -> list[FinishReason]:
-        """Returns the finish reasons of the response."""
-        return [
-            choice.finish_reason
-            for choice in self.chunk.choices
-            if choice.finish_reason
-        ]
-
-    @property
-    def model(self) -> str:
-        """Returns the name of the response model."""
-        return self.chunk.model
-
-    @property
-    def id(self) -> str:
-        """Returns the id of the response."""
-        return self.chunk.id
-
-    @property
-    def usage(self) -> CompletionUsage | None:
-        """Returns the usage of the chat completion."""
-        if hasattr(self.chunk, "usage") and self.chunk.usage:
-            return self.chunk.usage
-        return None
-
-    @property
-    def input_tokens(self) -> int | None:
-        """Returns the number of input tokens."""
-        if self.usage:
-            return self.usage.prompt_tokens
-        return None
-
-    @property
-    def output_tokens(self) -> int | None:
-        """Returns the number of output tokens."""
-        if self.usage:
-            return self.usage.completion_tokens
-        return None

mirascope/core/openai/dynamic_config.py

@@ -1,26 +0,0 @@
-"""This module defines the function return type for functions as LLM calls.
-
-usage docs: learn/dynamic_configuration.md#dynamic-configuration-options
-"""
-
-from openai.types.chat import ChatCompletionMessageParam
-
-from ..base import BaseDynamicConfig
-from .call_params import OpenAICallParams
-
-OpenAIDynamicConfig = BaseDynamicConfig[ChatCompletionMessageParam, OpenAICallParams]
-"""The function return type for functions wrapped with the `openai_call` decorator.
-
-Example:
-
-```python
-from mirascope.core import prompt_template
-from mirascope.core.openai import OpenAIDynamicConfig, openai_call
-
-
-@openai_call("gpt-4o-mini")
-@prompt_template("Recommend a {capitalized_genre} book")
-def recommend_book(genre: str) -> OpenAIDynamicConfig:
-    return {"computed_fields": {"capitalized_genre": genre.capitalize()}}
-```
-"""

mirascope/core/openai/stream.py

@@ -1,148 +0,0 @@
-"""The `OpenAIStream` class for convenience around streaming LLM calls.
-
-usage docs: learn/streams.md
-"""
-
-from openai.types.chat import (
-    ChatCompletion,
-    ChatCompletionAssistantMessageParam,
-    ChatCompletionMessage,
-    ChatCompletionMessageParam,
-    ChatCompletionMessageToolCall,
-    ChatCompletionMessageToolCallParam,
-    ChatCompletionToolMessageParam,
-    ChatCompletionUserMessageParam,
-)
-from openai.types.chat.chat_completion import Choice
-from openai.types.chat.chat_completion_message_tool_call_param import Function
-from openai.types.completion_usage import CompletionUsage
-
-from ..base.stream import BaseStream
-from ._utils import calculate_cost
-from .call_params import OpenAICallParams
-from .call_response import OpenAICallResponse
-from .call_response_chunk import OpenAICallResponseChunk
-from .dynamic_config import OpenAIDynamicConfig
-from .tool import OpenAITool
-
-FinishReason = Choice.__annotations__["finish_reason"]
-
-
-class OpenAIStream(
-    BaseStream[
-        OpenAICallResponse,
-        OpenAICallResponseChunk,
-        ChatCompletionUserMessageParam,
-        ChatCompletionAssistantMessageParam,
-        ChatCompletionToolMessageParam,
-        ChatCompletionMessageParam,
-        OpenAITool,
-        OpenAIDynamicConfig,
-        OpenAICallParams,
-        FinishReason,
-    ]
-):
-    """A class for convenience around streaming OpenAI LLM calls.
-
-    Example:
-
-    ```python
-    from mirascope.core import prompt_template
-    from mirascope.core.openai import openai_call
-
-
-    @openai_call("gpt-4o-mini", stream=True)
-    @prompt_template("Recommend a {genre} book")
-    def recommend_book(genre: str):
-        ...
-
-
-    stream = recommend_book("fantasy")  # returns `OpenAIStream` instance
-    for chunk, _ in stream:
-        print(chunk.content, end="", flush=True)
-    ```
-    """
-
-    _provider = "openai"
-
-    @property
-    def cost(self) -> float | None:
-        """Returns the cost of the call."""
-        return calculate_cost(self.input_tokens, self.output_tokens, self.model)
-
-    def _construct_message_param(
-        self,
-        tool_calls: list[ChatCompletionMessageToolCall] | None = None,
-        content: str | None = None,
-    ) -> ChatCompletionAssistantMessageParam:
-        """Constructs the message parameter for the assistant."""
-        message_param = ChatCompletionAssistantMessageParam(
-            role="assistant", content=content
-        )
-        if tool_calls:
-            message_param["tool_calls"] = [
-                ChatCompletionMessageToolCallParam(
-                    type="function",
-                    function=Function(
-                        arguments=tool_call.function.arguments,
-                        name=tool_call.function.name,
-                    ),
-                    id=tool_call.id,
-                )
-                for tool_call in tool_calls
-            ]
-        return message_param
-
-    def construct_call_response(self) -> OpenAICallResponse:
-        """Constructs the call response from a consumed OpenAIStream.
-
-        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."
-            )
-        message = {
-            "role": self.message_param["role"],
-            "content": self.message_param.get("content", ""),
-            "tool_calls": self.message_param.get("tool_calls", []),
-        }
-        if not self.input_tokens and not self.output_tokens:
-            usage = None
-        else:
-            usage = CompletionUsage(
-                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),
-            )
-        completion = ChatCompletion(
-            id=self.id if self.id else "",
-            model=self.model,
-            choices=[
-                Choice(
-                    finish_reason=self.finish_reasons[0]
-                    if self.finish_reasons
-                    else "stop",
-                    index=0,
-                    message=ChatCompletionMessage.model_validate(message),
-                )
-            ],
-            created=0,
-            object="chat.completion",
-            usage=usage,
-        )
-        return OpenAICallResponse(
-            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,
-        )

mirascope/core/openai/tool.py

@@ -1,79 +0,0 @@
-"""The `OpenAITool` class for easy tool usage with OpenAI LLM calls.
-
-usage docs: learn/tools.md#using-tools-with-standard-calls
-"""
-
-from __future__ import annotations
-
-import jiter
-from openai.types.chat import (
-    ChatCompletionMessageToolCall,
-    ChatCompletionToolParam,
-)
-from openai.types.shared_params import FunctionDefinition
-from pydantic.json_schema import SkipJsonSchema
-
-from ..base import BaseTool
-
-
-class OpenAITool(BaseTool):
-    """A class for defining tools for OpenAI LLM calls.
-
-    Example:
-
-    ```python
-    from mirascope.core import prompt_template
-    from mirascope.core.openai import openai_call
-
-
-    def format_book(title: str, author: str) -> str:
-        return f"{title} by {author}"
-
-
-    @openai_call("gpt-4o-mini", tools=[format_book])
-    @prompt_template("Recommend a {genre} book")
-    def recommend_book(genre: str):
-        ...
-
-
-    response = recommend_book("fantasy")
-    if tool := response.tool:  # returns an `OpenAITool` instance
-        print(tool.call())
-    ```
-    """
-
-    tool_call: SkipJsonSchema[ChatCompletionMessageToolCall]
-
-    @classmethod
-    def tool_schema(cls) -> ChatCompletionToolParam:
-        """Constructs a JSON Schema tool schema from the `BaseModel` schema defined.
-
-        Example:
-        ```python
-        from mirascope.core.openai import OpenAITool
-
-
-        def format_book(title: str, author: str) -> str:
-            return f"{title} by {author}"
-
-
-        tool_type = OpenAITool.type_from_fn(format_book)
-        print(tool_type.tool_schema())  # prints the OpenAI-specific tool schema
-        ```
-        """
-        fn = FunctionDefinition(name=cls._name(), description=cls._description())
-        model_schema = cls.model_tool_schema()
-        if model_schema["properties"]:
-            fn["parameters"] = model_schema
-        return ChatCompletionToolParam(function=fn, type="function")
-
-    @classmethod
-    def from_tool_call(cls, tool_call: ChatCompletionMessageToolCall) -> OpenAITool:
-        """Constructs an `OpenAITool` instance from a `tool_call`.
-
-        Args:
-            tool_call: The OpenAI tool call from which to construct this tool instance.
-        """
-        model_json = jiter.from_json(tool_call.function.arguments.encode())
-        model_json["tool_call"] = tool_call.model_dump()
-        return cls.model_validate(model_json)

mirascope/integrations/__init__.py

@@ -1,20 +0,0 @@
-"""Integrations with third party libraries."""
-
-from contextlib import suppress
-
-from ._middleware_factory import middleware_factory
-
-with suppress(ImportError):
-    from . import logfire as logfire
-
-with suppress(ImportError):
-    from . import langfuse as langfuse
-
-with suppress(ImportError):
-    from . import otel as otel
-
-with suppress(ImportError):
-    from . import tenacity as tenacity
-
-
-__all__ = ["langfuse", "logfire", "middleware_factory", "otel", "tenacity"]