Orama Embeddable Search Engine and RAG Pipeline for JavaScript

Orama is a full-text, vector, and hybrid search engine that runs in the browser, on a server, or at the edge in under 2KB. It provides built-in RAG pipeline support, typo tolerance, faceted search, and language-agnostic stemming — all without external dependencies.

Installation

Use the upstream install or setup path that matches your environment:

• npm i @orama/orama
• With Deno, you can just use the same CDN URL or use npm specifiers:

Requirements and caveats from upstream:

• embedding: 'vector[1536]', // Vector size must be expressed during schema initialization
• import '@tensorflow/tfjs-node' // Or any other appropriate TensorflowJS backend, like @tensorflow/tfjs-backend-webgl

Basic usage or getting-started notes:

• You can install Orama using npm, yarn, pnpm, bun:

• sh

• Or import it directly in a browser module:

• Source: https://github.com/oramasearch/orama

• Extracted from upstream docs: https://raw.githubusercontent.com/oramasearch/orama/HEAD/README.md

Source

• Agent Skill Exchange