What is Retrieval?

Explained

Retrieval is the step in RAG (and search systems) that finds the most relevant documents or text passages for a user query. It typically uses embeddings and vector similarity search.

Decision guides that use this term

• RAG vs enterprise search: do your people need answers or documents?

Further reading

• Vector Databases for RAG: Powering Semantic Search for LLMs

Related terms

• RAG Retrieve relevant documents and use them as context to generate the answer.
• Vector Numerical representation; see Embedding.
• Big Data Large volumes of data requiring specialized tools; feedstock for training AI models.
• Context Engineering Designing what the model sees—retrieval, memory, summaries, and window budgeting.
• Corpus Collection of documents used to train or feed a system (e.g., RAG).
• Data Lake Repository that stores raw data; source for analytics and ML.