Manage your RAG knowledge base (corpus)

This page describes how you can manage your corpus for RAG tasks by performing corpus management and file management.

Corpus management

A corpus, also referred to as an index, is a collection of documents or source of information. The corpus can be queried to retrieve relevant contexts for response generation. When creating a corpus for the first time, the process might take an additional minute.

The following corpus operations are supported:

Operation Description Parameters Examples
Create a RAG corpus. Create an index to import or upload documents. Create parameters Create example
Update a RAG corpus. Update a previously-created index to import or upload documents. Update parameters Update example
List a RAG corpus. List all of the indexes. List parameters List example
Get a RAG corpus. Get the metadata describing the index. Get parameters Get example
Delete a RAG corpus. Delete the index. Delete parameters Delete example

Concurrent operations on corpora aren't supported. For more information, see the RAG API reference.

File management

The following file operations are supported:

Operation Description Parameters Examples
Upload a RAG file. Upload a file from local storage with additional information that provides context to the LLM to generate more accurate responses. Upload parameters Upload example
Import RAG files. Import a set of files from some other storage into a storage location. Import parameters Import example
Get a RAG file. Get details about a RAG file for use by the LLM. Get parameters Get example
Delete a RAG file. Upload a file from local storage with additional information that provides context to the LLM to generate more accurate responses. Delete parameters Delete example

For more information, see the RAG API reference.

What's next