This is a small utility to generate JSON schemas for python functions. With power of type annotations, it is possible to generate a schema for a function without describing it twice.

At this moment, extracting schema from a function is useful for OpenAI Assistant Tool Calling, OpenAI API function-call, and Anthropic Claude Tool calling feature. And it can be used for other purposes for example to generate documentation in the future.

pip install function-schema

See the examples directory for comprehensive usage examples with different AI platforms:

• Basic Usage - Core features and function definition patterns
• OpenAI Integration - Assistant API and Chat Completion examples
• Claude Integration - Anthropic Claude tool calling examples
• MCP Integration - Model Context Protocol examples
• CLI Usage - Command-line interface examples

from typing import Annotated
from function_schema import Doc, get_function_schema

def get_weather(city: Annotated[str, Doc("The city to get the weather for")]) -> str:
    """Returns the weather for the given city."""
    return f"Weather for {city} is 20°C"

# Generate schema
schema = get_function_schema(get_weather)

• Type Annotations: Use typing.Annotated with Doc metadata for parameter descriptions
• Multiple Formats: Support for OpenAI ("openai") and Claude ("claude") schema formats
• Enum Support: Use enum.Enum or typing.Literal for parameter constraints
• CLI Tool: Generate schemas from command line using function_schema

For detailed examples and advanced usage patterns, see the examples directory.

For detailed OpenAI integration examples including Assistant API and Chat Completion, see examples/openai_example.py.

For Claude tool calling examples and multi-turn conversations, see examples/claude_example.py.

For MCP server and tool integration examples, see examples/mcp_example.py.

Generate schemas from command line:

function_schema examples/cli_example.py get_weather | jq

For more CLI examples, see examples/cli_example.py.

MIT License