Ternlight

https://ternlight-demo.vercel.app

Admin

Ternlight is a compact 7MB embedding model designed to run efficiently on a CPU, enabling rapid,...

Tokens:372

Snippets:6

Trust Score:7.8

Update:3 months ago

Show doc for...

Tokens:

Raw

### Install Ternlight Base Package

Source: https://ternlight-demo.vercel.app

Install the core Ternlight package using npm. This is the first step to integrating semantic search capabilities into your project.

```bash
npm install @ternlight/base
```

--------------------------------

### Perform Semantic Search with Ternlight

Source: https://ternlight-demo.vercel.app

Use the `embed` and `similar` functions from the `@ternlight/base` package to perform semantic searches. This example demonstrates finding similar items to a query against a dataset named 'recipes'. The operation is fast, with zero network overhead.

```javascript
import { embed, similar } from '@ternlight/base';

similar('easy weeknight dinner ideas', recipes, { topK: 3 });
// → ranked matches · ~5 ms · zero network
```

Tokens:

Raw