RAG Pipeline Developer Needed

Hey! We're building a RAG system to let our team query internal company documents(PDFs, txts, SQL database) and get accurate, sourced answers. Looking for some one who's actually done this before - not just experimented with it. What we need: Document ingestion + chunking strategy that makes sense for our data Embeddings + vector DB setup Retrieval that returns relevant, accurate results LLM integration with proper context handling Some way to reduce hallucinations and cite sources To apply: Please share a work results or demo of a RAG pipeline you've built. Tell me briefly what the use case was and what you'd do differently if you built it again. Tell me your stack of choice and rough timeline. Thanks!