Help users find relevant content in your app

Embedding models turn content into a format that can be searched by meaning instead of exact keywords. Use them for semantic search, retrieval-augmented generation (RAG), FAQ bots, document search, and knowledge bases. Ask Lovable to:

Build semantic search over uploaded documents.
Create a FAQ bot that answers from your help content.
Build a company knowledge base that finds relevant internal docs.

Ask for any of these in the project chat, and Lovable writes the feature and the backend call behind it. See Add an AI feature to your app for the whole flow, including publishing.

Model	Best for
Gemini Embedding 2 (default)	General-purpose semantic search, document retrieval, and recommendations, including multimodal retrieval across text, images, video, and audio.
Gemini Embedding 001	Older text-only model. Use it only when your app already stores search data created with it.
text-embedding-3-small	Cost-sensitive or high-volume text embedding workloads.
text-embedding-3-large	Higher-quality text retrieval when accuracy matters more than cost.

Getting started

Build

Connect

Collaborate

Deploy & host

Grow & optimize

Workspace & account

Plans & billing

Guides & reference

Help users find relevant content in your app