feat: Add LlamaIndex Agent Integration

[tonycdr-prog]

Summary

Implements LlamaIndex agent runner as requested in #264, following the existing integration pattern.

What is LlamaIndex?

LlamaIndex is a data framework for LLM applications, excelling at:

• Retrieval Augmented Generation (RAG)
• Document Q&A and knowledge bases
• Multi-document reasoning
• Structured data extraction

Changes

• New LlamaIndexAgentRunner class in src/openagents/agents/llamaindex_agent.py
• Tool conversion utilities:
  • openagents_tool_to_llamaindex() - convert to LlamaIndex FunctionTool
  • llamaindex_tool_to_openagents() - convert LlamaIndex tools to OpenAgents
• Supports multiple agent interfaces: chat(), query(), achat(), aquery()
• Async-first design with sync fallback

Usage

Basic Agent

from llama_index.core.agent import ReActAgent
from llama_index.llms.openai import OpenAI
from openagents.agents import LlamaIndexAgentRunner

# Create LlamaIndex agent
llm = OpenAI(model='gpt-4')
agent = ReActAgent.from_tools(tools, llm=llm, verbose=True)

# Connect to OpenAgents
runner = LlamaIndexAgentRunner(
    llamaindex_agent=agent,
    agent_id='knowledge-agent'
)
runner.start(network_host='localhost', network_port=8600)
runner.wait_for_stop()

With RAG Pipeline

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.core.agent import ReActAgent
from llama_index.core.tools import QueryEngineTool

# Build index from documents
documents = SimpleDirectoryReader('data').load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()

# Create tool from query engine
query_tool = QueryEngineTool.from_defaults(
    query_engine=query_engine,
    name='knowledge_base',
    description='Search the knowledge base for information'
)

# Create agent with RAG tool
agent = ReActAgent.from_tools([query_tool], llm=llm)
runner = LlamaIndexAgentRunner(
    llamaindex_agent=agent,
    agent_id='rag-agent'
)

Reference

Follows the pattern established in:

• src/openagents/agents/langchain_agent.py

Closes #264

[vercel]

@Bandit-AI is attempting to deploy a commit to the Raphael's projects Team on Vercel.

A member of the Team first needs to authorize it.