WebAI Studio
Back to Demos

Chat With Your Document

Embeddings

Fully local RAG: retrieve the relevant passages with embeddings, then answer with the Prompt API — citations included.

Why On-Device?

The entire RAG pipeline — chunking, embedding, retrieval, and generation — runs on-device. Your document is never uploaded and no vector database is required.

Interactive Demo

Semantic Embedder: Loading...
Prompt API: Loading...
Your Document
Paragraphs become retrieval chunks.
Grounded Answer
The answer, grounded in the retrieved passages, will appear here...

Implementation Code

demo.js