notadev-iamaura/OneRAG — Production-ready RAG Framework (Python/FastAPI).

Description and use

OneRAG is a production‑ready Retrieval‑Augmented Generation framework built with Python and FastAPI, offering a single‑line configuration to switch among six vector databases (Weaviate, Pinecone, Qdrant, ChromaDB, pgvector, MongoDB) and five LLM providers (Gemini, OpenAI, Claude, Ollama, OpenRouter). It exposes an OpenAI‑compatible API for seamless integration and is backed by a comprehensive test suite of over 2,100 tests. The project targets orchestration, AI/ML, and backend developers seeking a flexible, battle‑tested RAG solution.

Problem

notadev-iamaura/OneRAG helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

Production-ready RAG Framework (Python/FastAPI). 1-line config swaps: 6 Vector DBs (Weaviate, Pinecone, Qdrant, ChromaDB, pgvector, MongoDB), 5 LLMs (Gemini, OpenAI, Claude, Ollama, OpenRouter). OpenAI-compatible API. 2100+ tests.

Source