Skip to main content

Retrieval Augmented Generation Fundamentals

Retrieval Augmented Generation (RAG) ensures that generated content is both verifiable and anchored to the data you supply. This minimizes the occurrence of hallucinations (innaccurate or misleading information) commonly found in generative AI systems. Vectara's Retrieval Augmented Generation summarizes search results that answer complex queries directly while providing citations that ground these search results in facts from the data.

Implementing Retrieval Augmented Generation can transform the way information retrieval and AI interactions are conducted, especially in use cases where the integrity of information is critical.

Data Retrieval

The Retrieval Augmented Generation process involves retrieving relevant data from a structured corpus. This data provides a grounding layer for the generative component with a factual basis for its response.

Content Generation

The Vectara platform utilizes the retrieved data to generate informative and contextually relevant answers. Retrieval Augmented Generation is our groundbreaking way of producing generative summaries on top of your own data.


You can test summarizations with queries in our API Playground and in the Vectara Console. The summarizerPromptName is optional and defaults to the best summarizer available to your account type. Scale users can select other available summarizers.

This example shows a complex question with a summary that contains several citations and the search result highlights relevant information:

Retrieval Augmented Generation (RAG) Summary Example