A developer-first alternative to managed vector databases and RAG APIs for building AI applications. Bundles document ingestion, embedding generation, and vector retrieval into a single Docker container with a REST API.
Tech Stack
PythonAI, ML & Data
Why local-rag-engine?
• Instant setup via Docker Compose
• Agnostic to LLM provider
• Built-in chunking strategies
Limitations
• Limited horizontal scaling
• No managed backup service
• High RAM usage for embeddings
12/23/2025
Last Update
1
Forks
0
Issues
MIT
License
Financial Leak Detected
Stop the "SaaS Tax"
Your team could be burning cash. Switching to local-rag-engine instantly boosts your runway.
