RAG Document Assistant

Overview

A Retrieval-Augmented Generation (RAG) application built for the Endee.io Campus Recruitment Assignment. Users upload text documents, which are stored as vector embeddings in the Endee Vector Database; natural-language questions then retrieve the most semantically relevant chunks and feed them as grounded context to a Groq-hosted LLM (llama-3.3-70b-versatile). Answers are current, domain-specific, and traceable to source documents — the LLM never operates without retrieval grounding.

Architecture

• Ingestion pipeline — documents split into configurable 500-word chunk windows, each independently embedded with all-MiniLM-L6-v2 (384-dim float32) and batch-inserted into Endee
• HNSW vector index — cosine-similarity approximate nearest neighbor search (M=16, ef_con=200) over MDBX persistent storage, returning top-k results in milliseconds
• Query pipeline — the question is encoded into the same vector space, top-k chunks retrieved via Endee's search API (MessagePack-encoded responses), assembled into a context prompt for Groq
• Source attribution — every answer renders the exact retrieved chunks with similarity scores
• Auto-recovery — detects Endee's "required files missing for index" error on ephemeral hosts, transparently deletes the stale index, reprovisions, and retries ingestion
• Defensive parsing — a multi-format metadata parser handles raw dicts, JSON strings, and bytes across Endee versions
• Streamlit frontend with dark theming, real-time system status, live metrics (docs / chunks / latency), and configurable top-k, temperature, and chunk size
• Render blueprint deploy — render.yaml provisions both the Dockerized Endee server and the Streamlit app with internal-hostname networking

What It Demonstrates

The full RAG lifecycle end to end: chunking strategy trade-offs, symmetric query/document embedding, ANN index configuration, binary protocol handling (msgpack), prompt construction for grounded generation, and resilience engineering for free-tier cloud infrastructure.