Orama is a search engine and RAG pipeline that provides full-text, vector, and hybrid search in under 2kb. It runs as a library in the browser, server, or edge, requiring coding knowledge and optional external API calls for generative features.
Project overview
Orama is a search engine and RAG pipeline that provides full-text, vector, and hybrid search in under 2kb. It runs as a library in the browser, server, or edge, requiring coding knowledge and optional external API calls for generative features.
Project type
RAG · AI Search · Vector Database
Use cases
Knowledge Q&A · Search & Research
Deployment
Refer to project documentation
License
License pending
Best for
Developers and data teams who need to integrate search and retrieval capabilities into applications via a library.
Key capabilities
Provides full-text search with typo tolerance, exact match, and BM25 ranking.
Performs vector search using user-provided text embeddings.
Combines full-text and vector search together.
Creates ChatGPT/Perplexity-like search experiences using answer sessions.
Supports 10 different data types including strings, numbers, booleans, enums, geopoints, and vectors.
Generates embeddings automatically at insert-time and search-time using TensorFlowJS.
Supports facets, geosearch, filters, fields boosting, and pinning rules (merchandising).
Allows extending functionality with official or custom plugins.
Limitations and risks
Vector size must be expressed during schema initialization.
RAG and Chat experiences require calling OpenAI APIs, which is an optional paid service dependency.
Calling OpenAI APIs from the client side requires using a secure proxy to avoid exposing API keys.
Getting started
Install the library easily via npm, yarn, pnpm, bun using 'npm i @orama/orama', or import it directly via CDN.
Evidence and sources
GitHub project description: 🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.
README: You can install Orama using `npm`, `yarn`, `pnpm`, `bun`: ```sh npm i @orama/orama ``` Or import it directly in a browser module: ```html <html> <body> <script type="module"> impo…
README: Orama is quite simple to use. The first thing to do is to create a new database instance and set an indexing schema: ```js import { create, insert, remove, search, searchVector }…
README: Orama supports both vector and hybrid search by just setting `mode: 'vector'` when performing search. To perform this kind of search, you'll need to provide [text embeddings](http…
AI Search
Find projects, verify facts, compare options, or turn a complex need into an actionable plan
ProjectsSkillsFactsCompareRankingsSolutions
Try a searchA click only fills the search box; you stay in control