Upload your documents. Configure chunking, embeddings, and retrieval. Chat with your data — powered by Google Gemini. No infrastructure to manage.
file formats
Upload PDFs, DOCX, and plain text. Documents are parsed, chunked with configurable overlap, and embedded using Gemini's latest embedding model.
sessions
Your pipelines are saved to Supabase. Come back anytime, load a pipeline, and continue chatting where you left off. Full history preserved.
dimensions
Embeddings stored in Supabase pgvector with IVFFlat indexing. Cosine similarity retrieval finds the most relevant chunks for every query.
first token
Gemini responses stream in real-time. See answers appear token-by-token with source attribution showing exactly which documents were referenced.
parameters
Tune chunk size, overlap, top-K retrieval, model selection, and system prompts. Every parameter is adjustable to match your use case.
keys stored
Clerk authentication protects every route. Your Gemini API key is used per-request and never stored. Each pipeline is scoped to your account.
| DIY Setup | RAGForge | |
|---|---|---|
| Vector DB setup | Hours | Built-in |
| Document parsing | Write your own | Drag & drop |
| Embedding pipeline | Custom code | Automatic |
| Auth & multi-user | Integrate yourself | Clerk included |
| Chat with sources | Build from scratch | Ready to use |
| Time to first query | Days | Minutes |
Create your account, bring your Gemini API key, and start chatting with your documents in minutes.