Chat
Welcome to Starpi
Ask questions about your knowledge base or about files you add to the on-device workspace. Answers cite their sources, and you can open every citation.
New here? Load three sample files of a fictitious project and ask about them. The files are read on this device; nothing is uploaded.
Preparing connection…
Knowledge base
Documents stored in Supabase that this session may read.
Knowledge graph
People, projects, budgets, technologies and regulations, and how they relate.
Entities (select one to see its details and relations)
Entity details
InfoSelect a node to see its details and connections.
Add knowledge
Search files privately on this device, or save text to the shared knowledge base.
On-device workspace
Private · memory onlyFiles are parsed, split into chunks and indexed with BM25 in a background worker on this device, and removed when you reload the page. Nothing is uploaded or synced; only when the cloud assistant or your own server writes an answer are the matching excerpts sent along with the question. Answers cite them as [Doc: file, Chunk: n].
Drop files here or click to choose
PDF, TXT, Markdown, JSON or CSV · up to 25 MB each
No files in the workspace yet.
Save to the knowledge base
SupabaseThe text is stored as a Markdown document owned by this browser session and protected by Row Level Security.
Saving to the knowledge base needs a browser session, which is not available right now. The on-device workspace above works as usual.
Diagnostics & benchmark
WebGPU adapter properties and a measured inference benchmark of the on-device model.
WebGPU adapter
Checking…- Vendor
- –
- Architecture
- –
- Device
- –
- shader-f16
- –
- System
- –
Limits and features
Features: –
Inference benchmark
A warm-up request, then a fixed prompt of about 64 tokens that generates exactly 128 tokens on the on-device model. Time to first token and decode throughput are measured on that run.
No model is loaded yet. Running the benchmark loads the model selected in Settings (download on first use).
- Time to first token
- –
- Decode throughput
- –
- Prefill throughput
- –
- Total time
- –
Settings
Assistant mode, providers and knowledge base connection.
Assistant mode
The cloud assistant sends your question and the matching excerpts to the provider you configure. Without a key, Starpi quotes the knowledge base directly.
Knowledge base (Supabase)
Connecting- Project
- Supabase
- Access control
- Row Level Security · anonymous session
- Search
- BM25 on device · Postgres full-text · pgvector (backend)
- Chat history
- Checking…
Advanced
No key saved.
No key saved.
Unless you tick the box, keys are kept only until this tab is closed.
A Chat Completions endpoint (/v1/chat/completions). Allowed: https:// addresses, http://localhost and http://127.0.0.1.
Models are downloaded once and cached by the browser. GPUs without shader-f16 use the f32 variant automatically.