Techniques & Methods
Query
In AI and search contexts, a query is the natural language question, command, or structured request that a user submits to obtain a response. Queries vary from single keywords to complex multi-part questions that require decomposition and multi-step reasoning.
Understanding and correctly interpreting queries is the first step in any AI search or RAG pipeline. Query expansion, rewriting, and decomposition techniques improve retrieval quality for ambiguous or complex user inputs.
Authority Links
Related Terms
Core Concepts
Intent
Underlying purpose or goal a user aims to achieve through a query.
Techniques & Methods
Semantic Search
Search technology that retrieves results based on the meaning of a query rather than exact keyword matches — using embeddings to represent queries and documents as vectors and finding nearest neighbors in semantic space.
Techniques & Methods
Retrieval Augmented Generation (RAG)
An inference-time architecture that retrieves relevant documents from a knowledge base or web index and injects them into a language model's context before generation, grounding answers in real source material.
Techniques & Methods
Information Extraction
Automatically extracting structured information from unstructured text.