Embeddings — Numerical vector representations of text that capture semantic meaning, enabling AI systems to measure similarity between pieces of text.
Embeddings are dense vector representations of text where semantically similar content is placed close together in a high-dimensional space. AI coding tools use embeddings to index codebases and find semantically relevant code snippets when you ask a question. For example, when you ask "how does authentication work?", the tool finds code related to authentication even if it doesn't contain those exact words.
Embeddings are numerical representations of text that capture semantic meaning. They allow AI systems to compare and search for similar content based on meaning rather than exact word matches.
AI coding tools use embeddings to index your entire codebase, enabling semantic search. This lets the AI find relevant code for your query even when the exact words don't match.
RAG (Retrieval-Augmented Generation)
A technique that enhances AI responses by retrieving relevant information from an external knowledge base before generating a response.
Large Language Model (LLM)
A type of AI model trained on massive amounts of text data, capable of understanding and generating human-like text across a wide range of tasks.
EXPLORE MORE
Explore our complete glossary of AI, LLM, and system prompt terminology.
View Full Glossary