Built a Retrieval-Augmented Generation backend by Muhammad Ahmad FaizanBuilt a Retrieval-Augmented Generation backend by Muhammad Ahmad Faizan

Built a Retrieval-Augmented Generation backend

Portfolio project
Muhammad Ahmad Faizan
Built a Retrieval-Augmented Generation backend using LangChain and Qdrant: PDF upload and chunking, embedding generation, semantic search, and answer synthesis with inline page-level citations. Diagnosed and fixed a silent fallback bug where missing LLM credentials caused raw chunk dumps instead of real generated answers, then migrated the chat backend to Groq (LLaMA 3.3 70B) for fast, free-tier inference. Supports multi-document querying and follow-up question rewriting for conversational retrieval.

0 likes · 0 views · Jul 15, 2026

Built a Retrieval-Augmented Generation backend using LangChain and Qdrant: PDF upload and chunking, embedding generation, semantic search, and answer synthes...

Tags