apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-06-17 15:25:17 +02:00
Code Issues Projects Releases Packages Wiki Activity
plano/demos/use_cases/rag_agent
History
Adil Hafeez 6ce53c25d3
add rag agent demo
2025-10-14 14:12:13 -07:00
..
src/rag_agent add rag agent demo 2025-10-14 14:12:13 -07:00
arch_config.yaml add rag agent demo 2025-10-14 14:12:13 -07:00
docker-compose.yaml add rag agent demo 2025-10-14 14:12:13 -07:00
pyproject.toml add rag agent demo 2025-10-14 14:12:13 -07:00
README.md add rag agent demo 2025-10-14 14:12:13 -07:00
sample_queries.md add rag agent demo 2025-10-14 14:12:13 -07:00
start_agents.sh add rag agent demo 2025-10-14 14:12:13 -07:00
test.rest add rag agent demo 2025-10-14 14:12:13 -07:00
uv.lock add rag agent demo 2025-10-14 14:12:13 -07:00

README.md

RAG Agent Query Parser

A FastAPI service that rewrites user queries using archgw and gpt-4o-mini for better retrieval accuracy.

How it Works

  1. Receives a chat completion request with conversation history
  2. Calls archgw's LLM gateway with gpt-4o-mini to rewrite the last user query
  3. Returns the rewritten query as the assistant response

Setup and Running

  1. Start archgw:

    archgw up --foreground

  2. Start the query parser service:

    uv run python -m rag_agent.query_parser

Configuration

# archgw LLM Gateway base URL (default: http://localhost:12000/v1)
export LLM_GATEWAY_ENDPOINT="http://localhost:12000/v1"