Skip to main content

A library for auto-generating JSON Schema and dispatching tool calls in applications that use the Anthropic API to interact with Claude.

Project description

Claude LLM Tools

A library for auto-generating JSON Schema and dispatching tool calls in applications that use the Anthropic API to interact with Claude.

Installation

pip install claude-llm-tools

Usage

import anthropic
import claude_llm_tools


@claude_llm_tools.tool
def add_numbers(req: claude_llm_tools.Request, a: int, b: int) -> int:
    """
    Add two numbers together and return the result.

    Args:
        a: The first number
        b: The second number

    Returns:
        The sum of a and b
    """
    print(req.tool_use.id)
    return a + b


@claude_llm_tools.tool(
    name='multiply_numbers',
    description='Multiply two numbers together and return the product.'
)
def multiply(req: claude_llm_tools.Request, x: int, y: int) -> int:
    """This docstring will be overridden by the description parameter above."""
    print(req.tool_use.id)
    return x * y


client = anthropic.Anthropic()

# You can implement the Anthropic text editor contract
claude_llm_tools.add_tool(..., tool_type='text_editor_20250124')

message = client.messages.create(
    model="claude-3-7-sonnet-20250219",
    max_tokens=1000,
    temperature=1,
    system="You are a world-class poet. Respond only with short poems about math.",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Why is the ocean salty?"
                }
            ]
        }
    ],
    tools=claude_llm_tools.tools()
)

for block in message.content:
    match block.type:
        case 'text':
            ...
        case 'tool_use':
            result = await claude_llm_tools.dispatch(block)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

claude_llm_tools-0.3.0.tar.gz (12.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

claude_llm_tools-0.3.0-py3-none-any.whl (7.8 kB view details)

Uploaded Python 3

File details

Details for the file claude_llm_tools-0.3.0.tar.gz.

File metadata

  • Download URL: claude_llm_tools-0.3.0.tar.gz
  • Upload date:
  • Size: 12.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for claude_llm_tools-0.3.0.tar.gz
Algorithm Hash digest
SHA256 60bfd6c20793103aa6b0dfb477b3105a541bad2dec63798bd8b3981537c29f07
MD5 2bf475a4a7f43dc716c256de37439d8c
BLAKE2b-256 e49982ffd4546dc8d86080ee7b8f26371b2bfd4e351164fd6f5e6072a6adf66f

See more details on using hashes here.

File details

Details for the file claude_llm_tools-0.3.0-py3-none-any.whl.

File metadata

File hashes

Hashes for claude_llm_tools-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9c2297002eff63c4ec28ab28c111d81c5a64f9a830502adbc729610c17191586
MD5 5f96011fff0a708c38e9069e516b0fd1
BLAKE2b-256 0a937e0b47988dc54096733cc1780c806604ae3044ae37356bb090e63810e124

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page