Analyze Text
Analyze Text
Section titled “Analyze Text”Classify text — sentiment, toxicity, or moderation — locally in your browser (DistilBERT-SST2, toxic-bert on transformers.js). Private, offline, no cost.
What it does
Section titled “What it does”Runs the text through the selected on-device classifier and returns the matching labels with confidence scores, filtered by a threshold and capped to the top results.
When to use it
Section titled “When to use it”Moderate user-generated content, gauge feedback tone, or gate a workflow branch on toxicity — without sending the text to a third-party API.
Inputs and settings
Section titled “Inputs and settings”| Setting | Notes |
|---|---|
| Model | Any installed text-moderation model, across engines. |
| Text | The text to analyze. |
| Confidence threshold | Drop labels below this score (default 0). |
| Top-K labels | Keep at most this many labels (default 5). |
Outputs
Section titled “Outputs”Returns { predictions, top, score }:
predictions— array of{ label, score }, highest first.top— the highest-scoring label (ornull).score— that label’s score.
Related nodes
Section titled “Related nodes”- Sentiment Analysis — LLM or on-device engine toggle.
- Answer Question
- Run Local Model