DocuChat is a Streamlit-based web application that allows users to upload multiple PDF documents and ask natural language questions about their contents. It uses a Retrieval-Augmented Generation (RAG) pipeline powered by LangChain and the fine-tuned Flan-T5 model to provide intelligent, context-based answers.
- 📂 Upload and process multiple PDF files
- 🔍 Extract and chunk text using LangChain
- 🤖 Convert text into embeddings using
MiniLM - 🧠 Retrieve context via FAISS vector search
- 💬 Generate answers using
Flan-T5transformer model - 🧾 Clean and user-friendly Streamlit interface
👉 [Coming soon – Deploy using Streamlit Cloud or HuggingFace Spaces]
git clone https://github.com/muhammed labeeb/docuchat.git
cd docuchat