langchain-praisonai

LangChain integration for PraisonAI multi-agent framework.

Installation

pip install langchain-praisonai

Prerequisites

1. Install and start PraisonAI server:

pip install praisonai
praisonai serve agents.yaml --port 8080

Usage

Basic Usage

from langchain_praisonai import PraisonAITool
from langchain_openai import ChatOpenAI
from langchain.agents import initialize_agent, AgentType

# Create the PraisonAI tool
praisonai_tool = PraisonAITool(api_url="http://localhost:8080")

# Use with LangChain agent
llm = ChatOpenAI(model="gpt-4o-mini")
agent = initialize_agent(
    tools=[praisonai_tool],
    llm=llm,
    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True
)

result = agent.run("Research the latest trends in AI and summarize them")
print(result)

Using Specific Agents

from langchain_praisonai import PraisonAIAgentTool

# Create tools for specific agents
researcher = PraisonAIAgentTool(agent_name="researcher")
writer = PraisonAIAgentTool(agent_name="writer")

# Use multiple agent tools
tools = [researcher, writer]

List Available Agents

from langchain_praisonai import PraisonAIListAgentsTool

list_tool = PraisonAIListAgentsTool()
agents = list_tool.run({})
print(agents)

Direct Tool Usage

from langchain_praisonai import PraisonAITool

tool = PraisonAITool()

# Run with default workflow
result = tool.run({"query": "What are the benefits of AI?"})

# Run with specific agent
result = tool.run({"query": "Research quantum computing", "agent": "researcher"})

Async Usage

import asyncio
from langchain_praisonai import PraisonAITool

async def main():
    tool = PraisonAITool()
    result = await tool.arun({"query": "Analyze market trends"})
    print(result)

asyncio.run(main())

Configuration

Available Tools

Links

• PraisonAI Documentation
• PraisonAI GitHub
• LangChain Documentation

License

MIT