Skip to main content

Paaf is an Agent Framework for building AI agents

Project description

PAAF

PAAF (Peter Akande Agentic Framwork) is a simple Agentic framwork built to be used for all my LLM applications.

Example usage

from paaf.agents.react import ReactAgent
from paaf.llms.openai_llm import OpenAILLM

from paaf.tools.tool_registory import ToolRegistry
from serper import search as serper_search
from wiki import wiki_search


tool_registory = ToolRegistry()

tool_registory.register_tool(serper_search)
tool_registory.register_tool(wiki_search)


@tool_registory.tool()
def my_name() -> str:
    """
    Get the name of the user.

    Returns:
        str: The name of the user.
    """
    return "John Doe"


if __name__ == "__main__":
    llm = OpenAILLM()

    react_agent = ReactAgent(
        llm=llm,
        tool_registry=tool_registory,
        max_iterations=5,
    )

    response = react_agent.run("Who is older, Cristiano Ronaldo or Lionel Messi?")

    print("Response:", response.content)

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

paaf-0.1.8.tar.gz (25.3 kB view details)

Uploaded Source

Built Distribution

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

paaf-0.1.8-py3-none-any.whl (39.3 kB view details)

Uploaded Python 3

File details

Details for the file paaf-0.1.8.tar.gz.

File metadata

  • Download URL: paaf-0.1.8.tar.gz
  • Upload date:
  • Size: 25.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.2

File hashes

Hashes for paaf-0.1.8.tar.gz
Algorithm Hash digest
SHA256 29614d00dbd7d11cb46de578364cb49e6114277ff9b69a096bc5fe462ec0e871
MD5 5cf3521b9352ad2d55aeb579f69114f9
BLAKE2b-256 d24c1807517839c48a8ceb3529a961cd3bf147cfe17c41960c9fca23287acfe0

See more details on using hashes here.

File details

Details for the file paaf-0.1.8-py3-none-any.whl.

File metadata

  • Download URL: paaf-0.1.8-py3-none-any.whl
  • Upload date:
  • Size: 39.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.2

File hashes

Hashes for paaf-0.1.8-py3-none-any.whl
Algorithm Hash digest
SHA256 61a9a5aa2b1f78a1a4f4e51d07af8ad48775c2d8b5652bc1ac33ef5ecb668968
MD5 c5122c20548deadfe03412ad9e1f6553
BLAKE2b-256 5dfddc6d5256a77c291dd1f8d5bf7ed1d2b28aff6d1e568722ee61c8256561d7

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