Simple Serverless RAG (AWS)

A serverless RAG (Retrieval‑Augmented Generation) pipeline that turns private documents into searchable knowledge. You submit text/documents, the system chunks content, generates embeddings, and indexes everything for semantic retrieval—so an application can answer questions grounded on your data.

• Ingestion → chunking → embeddings → vector indexing
• Semantic retrieval over your own documents (vector search)
• Async processing with queue-based scaling and retries