Skip to content

mirascope.core.anthropic.tool

The OpenAITool class for easy tool usage with OpenAI LLM calls.

Usage Documentation

Tools

AnthropicToolConfig

Bases: ToolConfig

A tool configuration for Anthropic-specific features.

AnthropicTool

Bases: BaseTool[ToolParam]

A class for defining tools for Anthropic LLM calls.

Example:

from mirascope.core import prompt_template
from mirascope.core.anthropic import anthropic_call


def format_book(title: str, author: str) -> str:
    return f"{title} by {author}"


@anthropic_call("claude-3-5-sonnet-20240620", tools=[format_book])
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str):
    ...


response = recommend_book("fantasy")
if tool := response.tool:  # returns an `AnthropicTool` instance
    print(tool.call())

tool_schema classmethod 

tool_schema() -> ToolParam

Constructs a ToolParam tool schema from the BaseModel schema defined.

Example: 

from mirascope.core.anthropic import AnthropicTool


def format_book(title: str, author: str) -> str:
    return f"{title} by {author}"


tool_type = AnthropicTool.type_from_fn(format_book)
print(tool_type.tool_schema())  # prints the Anthropic-specific tool schema

Source code in mirascope/core/anthropic/tool.py 
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
@classmethod
def tool_schema(cls) -> ToolParam:
    """Constructs a `ToolParam` tool schema from the `BaseModel` schema defined.

    Example:
    ```python
    from mirascope.core.anthropic import AnthropicTool


    def format_book(title: str, author: str) -> str:
        return f"{title} by {author}"


    tool_type = AnthropicTool.type_from_fn(format_book)
    print(tool_type.tool_schema())  # prints the Anthropic-specific tool schema
    ```
    """
    kwargs = {
        "input_schema": cls.model_json_schema(),
        "name": cls._name(),
        "description": cls._description(),
    }
    if "cache_control" in cls.tool_config:
        kwargs["cache_control"] = cls.tool_config["cache_control"]
    return ToolParam(**kwargs)

from_tool_call classmethod 

from_tool_call(tool_call: ToolUseBlock) -> AnthropicTool

Constructs an AnthropicTool instance from a tool_call.

Parameters:

Name Type Description Default
tool_call ToolUseBlock

The Anthropic tool call from which to construct this tool instance.

 required
Source code in mirascope/core/anthropic/tool.py 
84
85
86
87
88
89
90
91
92
93
94
@classmethod
def from_tool_call(cls, tool_call: ToolUseBlock) -> AnthropicTool:
    """Constructs an `AnthropicTool` instance from a `tool_call`.

    Args:
        tool_call: The Anthropic tool call from which to construct this tool
            instance.
    """
    model_json = copy.deepcopy(tool_call.input)
    model_json["tool_call"] = tool_call.model_dump()  # pyright: ignore [reportIndexIssue]
    return cls.model_validate(model_json)