Debugger-style panel showing the language model's next-token probabilities, with the top candidate highlighted and bars scaled to softmax weight.
The import and the props worth knowing about, in one place.
import { Ai16 } from "@/components/beste/piece/ai16";
<Ai16
surface="card"
bordered={true}
inverted={false}
title="next_token"
context="The capital of France is"
topPrefix="top"
tokens={[
{
"token": "Paris",
"probability": 0.643
},
{
"token": "the",
"probability": 0.187
},
{
"token": "located",
"probability": 0.081
},
{
"token": "also",
"probability": 0.042
},
{
"token": "a",
"probability": 0.021
}
]}
/>"where is my order?"
Intent ranking panel with the raw user input quoted above and a list of candidate labels with confidence bars.
Vector query bar with namespace name, top_k value, and removable key:value filter chips for metadata.
Live token visualizer with tone-tinted token chips, tokens-per-second rate, and a pulsing caret at the end.
Context-window card with a tokens-used-of-max readout and a violet-to-fuchsia gradient fill bar.