Work / Side project

A chatbot that answers from your documents

A Django app that ingests PDF, Word, and PowerPoint files and answers questions using retrieval-augmented generation.

How it works

Uploaded PDF, Word, and PowerPoint files go through an ingestion pipeline built on MarkItDown, which turns them into clean text. A retrieval layer finds the passages relevant to a question and gives them to the model as context, so answers come from the documents rather than from the model's memory.