Available for Android
What Is RAG?
RAG stands for Retrieval-Augmented Generation. It's a technique that makes AI answers more accurate by grounding them in real source material.
Instead of generating answers from memory (which can lead to hallucinations), a RAG system first retrieves relevant passages from your documents, then generates an answer based specifically on what it found.
How RAG Works in Quill
You ask a question
Type or speak your question in natural language. "What are the payment terms?" or "Summarize the main arguments."
Quill searches your document
Using both keyword matching and semantic understanding, Quill finds the passages most relevant to your question. It understands that "compensation" relates to "salary" even if the exact word isn't used.
The AI reads the retrieved text
The language model receives only the relevant passages from your document. It generates an answer based on this specific context, not from general knowledge.
You get a grounded answer
The response is tied to your actual document. You can tap to see exactly which passages informed the answer.
The Key Difference
Standard AI chat can make things up. RAG systems retrieve first, then generate. The answer comes from your document, not the AI's imagination.
RAG in Your Pocket
Quill brings RAG technology to your Android phone. It uses Google's Gemma model running directly on your device, so you can ask questions about any document wherever you are.
Load a PDF, Word document, or even take a photo of a page. Quill indexes the content and lets you have a conversation with it. The answers always come from what's actually written, with links back to the source passages.
Good For
- • Finding specific information in long documents
- • Getting summaries that reflect what's actually written
- • Studying textbooks and research papers
- • Reviewing contracts and legal documents
- • Analyzing reports without re-reading everything
- • Any task where accuracy matters more than creativity