Skip to content
All projects

Local RAG · Full-Stack AI Application / v1.0.0

AI Knowledge Assistant

A full-stack Retrieval-Augmented Generation application that turns PDF, TXT, and Markdown documents into a persistent, searchable knowledge base.

Next.jsTypeScriptTailwind CSSPythonFastAPIRAGOllamaFAISSPyPDFSSEGitHub Actions

Project overview

Separate TypeScript frontend and Python backend layers.

Documents are processed with page-aware extraction and overlapping chunks.

Retrieved chunks become context for llama3.2 with visible source metadata.

Index and metadata persist across backend restarts.

System workflow

01

Ingest

PDF / TXT / Markdown → extraction and chunks

02

Index

Local embeddings → persistent FAISS

03

Retrieve

Question embedding → relevant context

04

Answer

llama3.2 → streamed answer + sources

Explore the implementation

This case study is based on the project’s own documentation.

More projects

Let’s talk about AI and software development