Skip to main content

A Python framework for LLM tool calls routing, automation, and orchestration

Project description

Voitta

PyPI version Python Versions Downloads License GitHub Stars

A Python framework for routing, automating, and orchestrating LLM tool calls. Voitta simplifies the integration of AI agents with external tools and APIs, enabling more powerful and flexible AI applications.

Features

  • Tool Call Routing: Seamlessly route LLM tool calls to the appropriate handlers
  • Flexible Configuration: Define your tools and routing logic using YAML or Python
  • Framework Agnostic: Works with any LLM provider or framework
  • Extensible Architecture: Easily add custom tools and integrations
  • Observability: Monitor and debug tool calls with built-in logging

Installation

From PyPI (Stable Release)

pip install voitta

From TestPyPI (Pre-release Versions)

To install the latest pre-release version from TestPyPI:

pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ voitta

The --extra-index-url flag is needed to fetch dependencies from the main PyPI repository, as TestPyPI may not have all the required dependencies.

You can also specify a particular version:

pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ voitta==0.2.3

Note: Pre-release versions on TestPyPI may contain experimental features and bugs. Use in production environments at your own risk.

Quick Start

from voitta import Voitta

# Initialize Voitta
voitta = Voitta()

# Register a tool handler
@voitta.tool("get_weather")
def get_weather(location, unit="celsius"):
    # Implementation to fetch weather data
    return {"temperature": 22, "condition": "sunny", "location": location, "unit": unit}

# Process an LLM tool call
result = voitta.process_tool_call({
    "name": "get_weather",
    "arguments": {"location": "San Francisco", "unit": "fahrenheit"}
})

print(result)  # Output: {"temperature": 72, "condition": "sunny", "location": "San Francisco", "unit": "fahrenheit"}

Usage

For detailed usage examples and documentation, please refer to:

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

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

voitta-0.5.0.tar.gz (10.6 kB view details)

Uploaded Source

Built Distribution

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

voitta-0.5.0-py3-none-any.whl (9.3 kB view details)

Uploaded Python 3

File details

Details for the file voitta-0.5.0.tar.gz.

File metadata

  • Download URL: voitta-0.5.0.tar.gz
  • Upload date:
  • Size: 10.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.11

File hashes

Hashes for voitta-0.5.0.tar.gz
Algorithm Hash digest
SHA256 fe701b5617d03b2a488d67115eca3236c9da7deff61bf91a26f5618e8791d4a6
MD5 9ef0488cb1ab7b0a8874e2478aa1d18f
BLAKE2b-256 93bef41bd341e2862219644f6560cafd12712e48ff80164555c2d96bd619ea44

See more details on using hashes here.

File details

Details for the file voitta-0.5.0-py3-none-any.whl.

File metadata

  • Download URL: voitta-0.5.0-py3-none-any.whl
  • Upload date:
  • Size: 9.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.11

File hashes

Hashes for voitta-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 16c7f75eeb9a04348629f4320ddc217e428e521db915f10bf8cf38f08a26e193
MD5 e879594e8b1cca95f275ad686cb2d126
BLAKE2b-256 1d49b5e81a9cb43f8e4d2a2803b7fee1027c6daa3f67d342c609b4cb350bb70d

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