Build a Quick RAG Proof-of-Concept

About the Project We're looking for someone to build a small proof-of-concept RAG (Retrieval-Augmented Generation) system. This is a test task on a limited budget, so the scope is intentionally small think a basic working pipeline on a small dataset, not a production-grade system. What You'll Build A simple RAG pipeline: document ingestion, embedding generation, vector storage, and retrieval Integration with an LLM to generate answers based on retrieved context A basic way to test it (a few sample queries showing it works end-to-end) What We're Looking For Experience working with RAG architectures (embeddings, vector databases, retrieval logic) Comfortable with common tools like LangChain, LlamaIndex, pgvector, FAISS, Pinecone, or similar Able to deliver a clean, working demo quickly To Apply Please briefly describe how you'd approach this and link to any similar RAG projects you've built.