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
- Ai (8 terms in common)
- Search (4 terms in common)
- Representation Learning (3 terms in common)
- Retrieval (3 terms in common)
- Nlp (2 terms in common)
- Vision (2 terms in common)
- Vectors (2 terms in common)
- Rag (2 terms in common)
- Multimodal (2 terms in common)
- Self Supervised (1 terms in common)
- Neural Networks (1 terms in common)
- Vector Database (1 terms in common)
- Open Source (1 terms in common)
- Loss Functions (1 terms in common)
- Optimization (1 terms in common)
- Contextual Representations (1 terms in common)
- Database (1 terms in common)
- Similarity Search (1 terms in common)
- Architecture (1 terms in common)
- Training (1 terms in common)