Skip to content

README.md

Latest commit

 

History

History
34 lines (22 loc) · 1.33 KB

README.md

File metadata and controls

34 lines (22 loc) · 1.33 KB
Raw

RAG Wikipedia

This package provides an end-to-end example of performing vector search and Retrieval-Augmented Generation (RAG) from an OCI Data Science Notebook Session using Wikipedia's Artificial Intelligence page.

Reviewed: 2025.11.27

When to use this asset?

Use this asset as support material when wanting to showcase Oracle AI Vector Search within Oracle AI Database 26ai. The asset includes explanations along with advanced RAG techniques, including:

  1. Comparing rule-based and semantic-based text splitters
  2. Connecting to the Oracle AI Database 26ai and creating vector-enabled tables
  3. Running hybrid search (keyword + vector similarity)
  4. Applying rerankers to improve retrieved context

Prerequisites

To use this package, you need:

  • Basic Python knowledge
  • Access to an OCI Data Science Notebook Session
  • An Oracle AI Database 26ai or 23ai with Vector Search enabled
  • Required IAM permissions for Data Science and Database access
  • A configured database wallet or secure connection details

Environment

Run the examples in a Jupyter Notebook inside an OCI Data Science Notebook Session.

License

Copyright (c) 2025 Oracle and/or its affiliates.

Licensed under the Universal Permissive License (UPL), Version 1.0.

See LICENSE for more details.