Show HN: Web RAG to generate perplexity like answers from your docs [in browser]
docs.akiradocs.aiHow It Works - Offline Indexing: Docs are processed and embedded using the GTE-small model at build time.
Browser-Based Magic:
- SQLite database (stored in the browser) for vector search.
- Local embedding model for query processing.
- Local LLaMA model for response generation using WebLLM.
- Everything Happens Locally: No data leaves the user’s device.
Key Benefits
- No API Costs: Everything runs in the browser—zero backend expenses.
- Unlimited Chats: No rate limits or usage restrictions.
- Privacy-First: Your data stays on your device, always.
You can find the code here:
https://github.com/Cloud-Code-AI/AkiraDocs Excited to see this shared! Love how everything runs right in the browser - makes the whole experience super smooth for users.