EngineeringUpdated 2026-10-24
Embedding
Converting text, images or other content into vectors whose similarity can be computed.
#Embedding#语义搜索#RAG
In plain language
Embeddings underpin semantic search, clustering, recommendation and RAG. Similar content sits closer in vector space. When choosing an embedding model, consider language support, dimensions, cost and domain fit.
Example
Embed 10,000 documents and retrieve the five closest to a user question.
Recommended tools
Related terms
Models & Architecture
Latent Space
A compressed high-dimensional representation space where diffusion often operates.
3 related terms
EngineeringFeatured
Retrieval-Augmented Generation
Retrieve relevant passages from a knowledge base, then have the model answer from them.
4 related terms
Engineering
Vector Database
A database built to store vectors and retrieve them by similarity.
3 related terms
Applications
Agentic Workflow
Breaking a task into steps planned by AI, executed by tools and reviewed by humans.
3 related terms