WebPizza AI - Private PDF Chat

Product Hunt

POC: Private PDF AI using only your browser with WebGPU

GitHub & Open Source

Open Source

GitHub

Artificial Intelligence

WebsiteProduct Hunt

I built this POC to test if complete RAG pipelines could run entirely client-side using WebGPU. Key difference: zero server dependency. PDF parsing, embeddings, vector search, and LLM inference all happen in your browser. Select a model (Llama, Phi-3, Mistral), upload a PDF, ask questions. Documents stay local in IndexedDB. Works offline once models are cached. Integrated WeInfer optimization achieving ~3.76x speedup over standard WebLLM through buffer reuse and async pipeline processing.

Similar Apps

Swetrix

Open source, cookieless Google Analytics alternative

Ultracite v6

Opinionated, zero-config code linter and formatter

PikaIA

Minimal Open Source Vibe Coding Tool

Ikiform

Build forms, collect responses & analyze data effortlessly.

Rux Programming Language

Fast, compiled, strongly typed, multi-paradigm