AI Document Question Answering System with RAG and LLM

Built PDF upload and natural language QA system with retrieval-augmented generation. This project demonstrates practical execution from architecture and implementation to measurable delivery outcomes.

Personal ProjectsYear 2026

Project Overview

Objective

Built PDF upload and natural language QA system with retrieval-augmented generation.

Stack

FastAPIReactPyPDFLoaderRecursiveCharacterTextSplitterHuggingFaceEmbeddingsFAISSGPT-4o-miniGPT-4.1GPT-5

Delivery highlights

  • Developed a document QA workflow where users upload PDF files and ask questions in natural language, Processed documents with PyPDFLoader and RecursiveCharacterTextSplitter before embedding, Generated semantic embeddings with HuggingFaceEmbeddings (BAAI/bge-m3) and stored them in FAISS for similarity retrieval, and Provided retrieved chunks as context to selectable LLMs (GPT-4o-mini, GPT-4.1, GPT-5) through FastAPI + React UI.
Link DemoBack to Topic ProjectsBack to All Projects

Related Projects

3 items

Visual Question Answering System with YOLO, CLIP, ViT, BLIP, BLIP Caption, and LLM

Personal ProjectsYear: 2026

Built end-to-end VQA platform for image upload, scene understanding, and LLM-based answers.

AI Document Search & Question Answering System (RAG)

Personal ProjectsYear: 2026

Built a multimodal AI system for document, audio, and image understanding with natural language question answering using retrieval-augmented generation (RAG).

AI Resume Chat with LLM and RAG (Portfolio Assistant)

Personal ProjectsYear: 2026

Built a sitemap-driven portfolio assistant that answers recruiter questions with grounded, source-linked responses.