Skip to content

README.md

Latest commit

 

History

History
42 lines (31 loc) · 1.06 KB

README.md

File metadata and controls

42 lines (31 loc) · 1.06 KB

DocChatAI: RAG Chatbot & Report Generator

Building AI course project

Summary

DocChatAI is a Retrieval-Augmented Generation (RAG) chatbot that allows users to upload PDFs, ask questions, and generate structured reports. It uses semantic search and LLMs to provide accurate, context-aware responses and summaries from documents.

Features

  • Upload PDFs and ask questions
  • Context-aware answers using RAG
  • Generate structured summary reports
  • Download reports as text files

Tech Stack

  • Python 3.10
  • Streamlit
  • LangChain
  • FAISS
  • HuggingFace Embeddings
  • Gemini API (Gemini-2.5-Flash)

Evaluation

Retrieval performance was evaluated using a curated set of question–document pairs on user-uploaded PDFs.

  • Top-3 Retrieval Accuracy: 100%
  • Embedding Model: sentence-transformers/all-MiniLM-L6-v2
  • Vector Store: FAISS
  • A query is considered correct if the expected document appears among the top-3 retrieved chunks.

Setup

pip install -r requirements.txt
streamlit run app.py