Glossary · Generative AI and LLMs
What is Text-to-SQL? Definition and meaning
Using a language model to translate a natural-language question into an SQL query against a known schema.
Definition
Text-to-SQL: Using a language model to translate a natural-language question into an SQL query against a known schema.
In short: Plain-language questions, SQL answers.
When it is used
Self-service analytics, BI assistants and data agents.
Where it fits
Text-to-SQL belongs to LLM concepts in the Generative AI and LLMs topic. These are the other terms in the same group:
- Reasoning models: Language models trained to produce long internal reasoning before the final answer, trading extra inference time for accuracy.
- Context engineering: The discipline of selecting, ordering and compressing instructions, data, tools and memory that enter a model's context window.
- Prompt engineering: Techniques for phrasing instructions, examples, roles and output formats so a language model produces the intended result.
- Embeddings: Dense numeric vectors produced by a model so that items with similar meaning are close together in vector space.
- KV cache: Stored attention keys and values from previous tokens, reused so each new token only needs computation for itself.
- Speculative decoding: An inference technique where a cheap draft proposes tokens and the main model verifies several at once, preserving its output distribution.
- Small language models: Language models with relatively few parameters that run on modest hardware or devices, often fine-tuned or distilled for specific tasks.
- Multimodal models: Models that take in or produce several data types, such as text, images, audio and video, within one network.
- BERT: A transformer encoder pre-trained to predict masked words using context from both sides, then fine-tuned for understanding tasks.
- GPT architecture: A transformer that uses causal self-attention to predict the next token, trained on large text corpora and scaled up.
Learn more
The full guide to Text-to-SQL explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.
Previous term: Test-time compute · Next term: TFT