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

mirascope/core/groq/call_response_chunk.py

@@ -1,104 +0,0 @@
-"""This module contains the `GroqCallResponseChunk` class.
-
-usage docs: learn/streams.md#handling-streamed-responses
-"""
-
-from typing import cast
-
-from groq.types.chat import ChatCompletionChunk
-from groq.types.chat.chat_completion import Choice
-from groq.types.completion_usage import CompletionUsage
-
-from ..base import BaseCallResponseChunk
-from ..base.types import CostMetadata
-
-FinishReason = Choice.__annotations__["finish_reason"]
-
-
-class GroqCallResponseChunk(BaseCallResponseChunk[ChatCompletionChunk, FinishReason]):
-    """A convenience wrapper around the Groq `ChatCompletionChunk` streamed chunks.
-
-    When calling the Groq API using a function decorated with `groq_call` and
-    `stream` set to `True`, the stream will contain `GroqResponseChunk` instances with
-    properties that allow for more convenient access to commonly used attributes.
-
-    Example:
-
-    ```python
-    from mirascope.core import prompt_template
-    from mirascope.core.groq import groq_call
-
-
-    @groq_call("llama-3.1-8b-instant", stream=True)
-    def recommend_book(genre: str) -> str:
-        return f"Recommend a {genre} book"
-
-    stream = recommend_book("fantasy")  # response is an `GroqStream`
-    for chunk, _ in stream:
-        print(chunk.content, end="", flush=True)
-    ```
-    """
-
-    @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 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 cached_tokens(self) -> int | None:
-        """Returns the number of cached tokens."""
-        return 0
-
-    @property
-    def output_tokens(self) -> int | None:
-        """Returns the number of output tokens."""
-        if self.usage:
-            return self.usage.completion_tokens
-        return None
-
-    @property
-    def cost_metadata(self) -> CostMetadata:
-        """Returns the cost metadata."""
-        return super().cost_metadata
-
-    @property
-    def common_finish_reasons(self) -> list[FinishReason] | None:
-        return cast(list[FinishReason], self.finish_reasons)

mirascope/core/groq/dynamic_config.py

@@ -1,29 +0,0 @@
-"""This module defines the function return type for functions as LLM calls."""
-
-from groq import AsyncGroq, Groq
-from groq.types.chat import ChatCompletionMessageParam
-
-from ..base import BaseDynamicConfig, BaseMessageParam
-from .call_params import GroqCallParams
-
-AsyncGroqDynamicConfig = BaseDynamicConfig[
-    ChatCompletionMessageParam | BaseMessageParam, GroqCallParams, AsyncGroq
-]
-GroqDynamicConfig = BaseDynamicConfig[
-    ChatCompletionMessageParam | BaseMessageParam, GroqCallParams, Groq
-]
-"""The function return type for functions wrapped with the `groq_call` decorator.
-
-Example:
-
-```python
-from mirascope.core import prompt_template
-from mirascope.core.groq import GroqDynamicConfig, groq_call
-
-
-@groq_call("llama-3.1-8b-instant")
-@prompt_template("Recommend a {capitalized_genre} book")
-def recommend_book(genre: str) -> GroqDynamicConfig:
-    return {"computed_fields": {"capitalized_genre": genre.capitalize()}}
-```
-"""

mirascope/core/groq/stream.py

@@ -1,135 +0,0 @@
-"""The `GroqStream` class for convenience around streaming LLM calls.
-
-usage docs: learn/streams.md
-"""
-
-from groq.types.chat import (
-    ChatCompletion,
-    ChatCompletionAssistantMessageParam,
-    ChatCompletionMessageParam,
-    ChatCompletionMessageToolCallParam,
-    ChatCompletionToolMessageParam,
-    ChatCompletionToolParam,
-    ChatCompletionUserMessageParam,
-)
-from groq.types.chat.chat_completion import Choice
-from groq.types.chat.chat_completion_message import ChatCompletionMessage
-from groq.types.completion_usage import CompletionUsage
-
-from ..base.stream import BaseStream
-from ..base.types import CostMetadata
-from .call_params import GroqCallParams
-from .call_response import GroqCallResponse
-from .call_response_chunk import GroqCallResponseChunk
-from .dynamic_config import AsyncGroqDynamicConfig, GroqDynamicConfig
-from .tool import GroqTool
-
-FinishReason = Choice.__annotations__["finish_reason"]
-
-
-class GroqStream(
-    BaseStream[
-        GroqCallResponse,
-        GroqCallResponseChunk,
-        ChatCompletionUserMessageParam,
-        ChatCompletionAssistantMessageParam,
-        ChatCompletionToolMessageParam,
-        ChatCompletionMessageParam,
-        GroqTool,
-        ChatCompletionToolParam,
-        AsyncGroqDynamicConfig | GroqDynamicConfig,
-        GroqCallParams,
-        FinishReason,
-    ]
-):
-    """A class for convenience around streaming Groq LLM calls.
-
-    Example:
-
-    ```python
-    from mirascope.core import prompt_template
-    from mirascope.core.groq import groq_call
-
-
-    @groq_call("llama-3.1-8b-instant", stream=True)
-    def recommend_book(genre: str) -> str:
-        return f"Recommend a {genre} book"
-
-    stream = recommend_book("fantasy")  # returns `GroqStream` instance
-    for chunk, _ in stream:
-        print(chunk.content, end="", flush=True)
-    ```
-    """
-
-    _provider = "groq"
-
-    def _construct_message_param(
-        self,
-        tool_calls: list[ChatCompletionMessageToolCallParam] | None = None,
-        content: str | None = None,
-    ) -> ChatCompletionAssistantMessageParam:
-        message_param = ChatCompletionAssistantMessageParam(
-            role="assistant",
-            content=content,
-        )
-        if tool_calls:
-            message_param["tool_calls"] = tool_calls
-        return message_param
-
-    def construct_call_response(self) -> GroqCallResponse:
-        """Constructs the call response from a consumed GroqStream.
-
-        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 and self.finish_reasons[0]
-                    else "stop",
-                    index=0,
-                    message=ChatCompletionMessage.model_validate(message),
-                )
-            ],
-            created=0,
-            object="chat.completion",
-            usage=usage,
-        )
-        return GroqCallResponse(
-            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/groq/tool.py

@@ -1,80 +0,0 @@
-"""The `GroqTool` class for easy tool usage with Groq LLM calls.
-
-usage docs: learn/tools.md
-"""
-
-from __future__ import annotations
-
-import jiter
-from groq.types.chat import (
-    ChatCompletionMessageToolCall,
-    ChatCompletionToolParam,
-)
-from groq.types.shared_params import FunctionDefinition
-from pydantic.json_schema import SkipJsonSchema
-
-from ..base import BaseTool
-
-
-class GroqTool(BaseTool):
-    """A class for defining tools for Groq LLM calls.
-
-    Example:
-
-    ```python
-    from mirascope.core import prompt_template
-    from mirascope.core.groq import groq_call
-
-
-    def format_book(title: str, author: str) -> str:
-        return f"{title} by {author}"
-
-
-    @groq_call("llama-3.1-8b-instant", tools=[format_book])
-    def recommend_book(genre: str) -> str:
-        return f"Recommend a {genre} book"
-
-    response = recommend_book("fantasy")
-    if tool := response.tool:  # returns an `GroqTool` instance
-        print(tool.call())
-    ```
-    """
-
-    __provider__ = "groq"
-
-    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.groq import GroqTool
-
-
-        def format_book(title: str, author: str) -> str:
-            return f"{title} by {author}"
-
-
-        tool_type = GroqTool.type_from_fn(format_book)
-        print(tool_type.tool_schema())  # prints the Groq-specific tool schema
-        ```
-        """
-        fn = FunctionDefinition(name=cls._name(), description=cls._description())
-        model_schema = cls.model_json_schema()
-        if model_schema["properties"]:
-            fn["parameters"] = model_schema
-        return ChatCompletionToolParam(function=fn, type="function")
-
-    @classmethod
-    def from_tool_call(cls, tool_call: ChatCompletionMessageToolCall) -> GroqTool:
-        """Constructs an `GroqTool` instance from a `tool_call`.
-
-        Args:
-            tool_call: The Groq 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())
-        return cls.model_validate(model_json)

mirascope/core/litellm/__init__.py

@@ -1,28 +0,0 @@
-"""The Mirascope LiteLLM Module."""
-
-from typing import TypeAlias
-
-from ..openai import OpenAIMessageParam
-from ._call import litellm_call
-from ._call import litellm_call as call
-from .call_params import LiteLLMCallParams
-from .call_response import LiteLLMCallResponse
-from .call_response_chunk import LiteLLMCallResponseChunk
-from .dynamic_config import AsyncLiteLLMDynamicConfig, LiteLLMDynamicConfig
-from .stream import LiteLLMStream
-from .tool import LiteLLMTool
-
-LiteLLMMessageParam: TypeAlias = OpenAIMessageParam
-
-__all__ = [
-    "AsyncLiteLLMDynamicConfig",
-    "LiteLLMCallParams",
-    "LiteLLMCallResponse",
-    "LiteLLMCallResponseChunk",
-    "LiteLLMDynamicConfig",
-    "LiteLLMMessageParam",
-    "LiteLLMStream",
-    "LiteLLMTool",
-    "call",
-    "litellm_call",
-]

mirascope/core/litellm/_call.py

@@ -1,67 +0,0 @@
-"""The `litellm_call` decorator for functions as LLM calls."""
-
-from ..base import call_factory
-from ..openai._utils import (
-    get_json_output,
-    handle_stream,
-    handle_stream_async,
-)
-from ._utils import setup_call
-from .call_params import LiteLLMCallParams
-from .call_response import LiteLLMCallResponse
-from .call_response_chunk import LiteLLMCallResponseChunk
-from .stream import LiteLLMStream
-from .tool import LiteLLMTool
-
-litellm_call = call_factory(
-    TCallResponse=LiteLLMCallResponse,
-    TCallResponseChunk=LiteLLMCallResponseChunk,
-    TToolType=LiteLLMTool,
-    TStream=LiteLLMStream,
-    default_call_params=LiteLLMCallParams(),
-    setup_call=setup_call,  # pyright: ignore [reportArgumentType]
-    get_json_output=get_json_output,
-    handle_stream=handle_stream,  # pyright: ignore [reportArgumentType]
-    handle_stream_async=handle_stream_async,  # pyright: ignore [reportArgumentType]
-)
-"""A decorator for calling the LiteLLM API with a typed function.
-
-usage docs: learn/calls.md
-
-This decorator is used to wrap a typed function that calls the LiteLLM 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.litellm import litellm_call
-
-
-@litellm_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 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 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 (None): LiteLLM does not support a custom 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 a LiteLLM
-        routed LLM API call.
-"""

mirascope/core/litellm/_utils/__init__.py

@@ -1,5 +0,0 @@
-"""LiteLLM utilities for decorator factories."""
-
-from ._setup_call import setup_call
-
-__all__ = ["setup_call"]

mirascope/core/litellm/_utils/_setup_call.py

@@ -1,109 +0,0 @@
-"""This module contains the setup_call function for OpenAI tools."""
-
-from collections.abc import Awaitable, Callable
-from typing import Any, TypeAlias, cast, overload
-
-from litellm import acompletion, completion
-from openai import OpenAI
-from openai.types.chat import ChatCompletion, ChatCompletionMessageParam
-from pydantic import BaseModel
-
-from ...base import BaseTool
-from ...base._utils import AsyncCreateFn, CreateFn, fn_is_async
-from ...base.call_params import CommonCallParams
-from ...base.stream_config import StreamConfig
-from ...openai import (
-    AsyncOpenAIDynamicConfig,
-    OpenAICallParams,
-    OpenAIDynamicConfig,
-    OpenAITool,
-)
-from ...openai._call_kwargs import OpenAICallKwargs
-from ...openai._utils import setup_call as setup_call_openai
-
-# Note: MyPy doesn't like `client: ...` so we use these aliases instead.
-_AsyncLiteLLMClient: TypeAlias = Any
-_SyncLiteLLMClient: TypeAlias = Any
-
-
-@overload
-def setup_call(
-    *,
-    model: str,
-    client: _AsyncLiteLLMClient | None,
-    fn: Callable[..., Awaitable[AsyncOpenAIDynamicConfig]],
-    fn_args: dict[str, Any],
-    dynamic_config: AsyncOpenAIDynamicConfig,
-    tools: list[type[BaseTool] | Callable] | None,
-    json_mode: bool,
-    call_params: OpenAICallParams | CommonCallParams,
-    response_model: type[BaseModel] | None,
-    stream: bool | StreamConfig,
-) -> tuple[
-    AsyncCreateFn[ChatCompletion, ChatCompletion],
-    str | None,
-    list[ChatCompletionMessageParam],
-    list[type[OpenAITool]] | None,
-    OpenAICallKwargs,
-]: ...
-
-
-@overload
-def setup_call(
-    *,
-    model: str,
-    client: _SyncLiteLLMClient | None,
-    fn: Callable[..., OpenAIDynamicConfig],
-    fn_args: dict[str, Any],
-    dynamic_config: OpenAIDynamicConfig,
-    tools: list[type[BaseTool] | Callable] | None,
-    json_mode: bool,
-    call_params: OpenAICallParams | CommonCallParams,
-    response_model: type[BaseModel] | None,
-    stream: bool | StreamConfig,
-) -> tuple[
-    CreateFn[ChatCompletion, ChatCompletion],
-    str | None,
-    list[ChatCompletionMessageParam],
-    list[type[OpenAITool]] | None,
-    OpenAICallKwargs,
-]: ...
-
-
-def setup_call(
-    *,
-    model: str,
-    client: None,
-    fn: Callable[..., OpenAIDynamicConfig | Awaitable[AsyncOpenAIDynamicConfig]],
-    fn_args: dict[str, Any],
-    dynamic_config: OpenAIDynamicConfig | AsyncOpenAIDynamicConfig,
-    tools: list[type[BaseTool] | Callable] | None,
-    json_mode: bool,
-    call_params: OpenAICallParams | CommonCallParams,
-    response_model: type[BaseModel] | None,
-    stream: bool | StreamConfig,
-) -> tuple[
-    CreateFn[ChatCompletion, ChatCompletion]
-    | AsyncCreateFn[ChatCompletion, ChatCompletion],
-    str | None,
-    list[ChatCompletionMessageParam],
-    list[type[OpenAITool]] | None,
-    OpenAICallKwargs,
-]:
-    _, prompt_template, messages, tool_types, call_kwargs = setup_call_openai(
-        model=model,  # pyright: ignore [reportCallIssue]
-        client=OpenAI(api_key="NOT_USED"),
-        fn=fn,  # pyright: ignore [reportArgumentType]
-        fn_args=fn_args,  # pyright: ignore [reportArgumentType]
-        dynamic_config=dynamic_config,
-        tools=tools,
-        json_mode=json_mode,
-        call_params=call_params,
-        response_model=response_model,
-        stream=stream,
-    )
-    create = cast(
-        Callable[..., ChatCompletion] | Callable[..., Awaitable[ChatCompletion]],
-        acompletion if fn_is_async(fn) else completion,
-    )
-    return create, prompt_template, messages, tool_types, call_kwargs

mirascope/core/litellm/call_params.py

@@ -1,10 +0,0 @@
-"""usage docs: learn/calls.md#provider-specific-parameters"""
-
-from ..openai import OpenAICallParams
-
-
-class LiteLLMCallParams(OpenAICallParams):
-    """A simple wrapper around `OpenAICallParams.`
-
-    Since LiteLLM uses the OpenAI spec, we change nothing here.
-    """

mirascope/core/litellm/call_response.py

@@ -1,24 +0,0 @@
-"""This module contains the `LiteLLMCallResponse` class.
-
-usage docs: learn/calls.md#handling-responses
-"""
-
-from pydantic import computed_field
-
-from ..base.types import CostMetadata
-from ..openai import OpenAICallResponse
-
-
-class LiteLLMCallResponse(OpenAICallResponse):
-    """A simpler wrapper around `OpenAICallResponse`.
-
-    Everything is the same except the `cost` property, which has been updated to use
-    LiteLLM's cost calculations so that cost tracking works for non-OpenAI models.
-    """
-
-    _provider = "litellm"
-
-    @computed_field
-    @property
-    def cost_metadata(self) -> CostMetadata:
-        return CostMetadata(cost=self.response._hidden_params["response_cost"])  # pyright: ignore [reportAttributeAccessIssue]

mirascope/core/litellm/call_response_chunk.py

@@ -1,14 +0,0 @@
-"""This module contains the `LiteLLMCallResponseChunk` class.
-
-usage docs: learn/streams.md#handling-streamed-responses
-"""
-
-from ..openai import OpenAICallResponseChunk
-
-
-class LiteLLMCallResponseChunk(OpenAICallResponseChunk):
-    """A simpler wrapper around `OpenAICallResponse`.
-
-    Everything is the same except the `cost` property, which has been updated to use
-    LiteLLM's cost calculations so that cost tracking works for non-OpenAI models.
-    """

mirascope/core/litellm/dynamic_config.py

@@ -1,8 +0,0 @@
-"""This module defines the function return type for functions as LLM calls."""
-
-from typing import TypeAlias
-
-from ..openai import AsyncOpenAIDynamicConfig, OpenAIDynamicConfig
-
-AsyncLiteLLMDynamicConfig: TypeAlias = AsyncOpenAIDynamicConfig
-LiteLLMDynamicConfig: TypeAlias = OpenAIDynamicConfig