Embeddings Glossary

Browse 20 embeddings terms defined in plain English, from the cultural dictionary of computing.

20 Embeddings Terms

AI Vector
A vector representation used in AI systems, typically to encode text, images, or other data numerically so similarity and retrieval operations become possible....
ChromaDB
An open-source embedding database (vector database) designed to be the easiest way to build AI applications that need to search over documents, images, or...
CLIP
A multimodal model trained to align images and text in a shared embedding space. It influences how models are trained, evaluated, or served, and it can...
CLIP Model
A model trained to align images and text in a shared embedding space so they can be compared semantically.
Contrastive Learning
A representation learning approach that pulls related examples together and pushes unrelated examples apart. It influences how models are trained, evaluated,...
Contrastive Loss
A loss function that optimizes embeddings by rewarding similarity for matched pairs and separation for mismatched pairs. It influences how models are trained,...
Dense Retrieval
A search approach that retrieves items by comparing learned dense embeddings rather than sparse term overlap. It influences how models are trained, evaluated,...
Dual Encoder
A retrieval architecture that encodes queries and documents separately for fast vector similarity search. It influences how models are trained, evaluated, or...
ELMo
Embeddings from Language Models, a contextual word representation model built from bidirectional language models. It influences how models are trained,...
Embedding Dimension
The number of numeric dimensions in an embedding vector used to represent data such as text or images. Embedding dimension affects storage cost, retrieval...
Embedding Layer
A neural network layer that maps discrete tokens or categories into dense vector representations that the rest of the model can process. Embedding layers are...
Frozen Embedding
An embedding layer or embedding representation whose parameters are kept fixed during some later stage of training or adaptation. Freezing embeddings can...
Knowledge Graph Embedding
A method for encoding entities and relations from a knowledge graph into continuous vector spaces. It influences how models are trained, evaluated, or served,...
Matryoshka Embeddings
Embeddings designed so truncated lower-dimensional prefixes still retain useful semantic information, making one vector usable at multiple dimensionalities.
Neural Search
Search based on learned vector representations and semantic similarity rather than only keyword overlap. Neural search is widely used to improve relevance when...
RAG Embedding
An embedding used within a retrieval-augmented generation system to represent documents, chunks, or queries for semantic search. The embedding model chosen for...
Semantic Search
Search based on the meaning of queries rather than keyword matching. Converts both queries and documents into vector embeddings and finds the nearest matches...
Token Embedding
The vector representation associated with a token so the model can process it numerically rather than as raw text. Token embeddings are a foundational part of...
Vector Database
A database optimized for storing and querying high-dimensional vectors (embeddings). Uses approximate nearest neighbor (ANN) algorithms like HNSW or IVF to...
Vector Database
Vector Database is a specialized database system optimized for storing, indexing, and querying high-dimensional vectors (arrays of numbers) that represent data...

Related Topics