You can search for relevant information in unstructured data using Search Retrievers to ground prompts through retrieval augmented generation, flows, or any platform use case. Retrievers improve the value and relevance of LLM responses for users. The textual data used to augment the LLM response is indexed in a vector database which can include unstructured as well as structured data.
Before you can create a retriever, you need to prepare the data. Data preparation involves loading, chunking, vectorizing, and storing content in a search-optimized way. A search index stores chunked and vectorized data. When a search index is created in Data Cloud, a default retriever is created automaticall...