Oracle AI Vector Search provides many parameters for chunking text data, such as SPLIT [BY], OVERLAP, or NORMALIZE. In these examples, you can see how to configure these parameters to define your own chunking specifications and strategies, so that you can create meaningful chunks.

• Explore Chunking Techniques and Examples
  Review these examples of all the supported chunking parameters. These examples can provide an idea on what are good and bad chunking techniques, and thus help you define a strategy when chunking your data.
• Create and Use Custom Vocabulary
  Create and use your own vocabulary of tokens when chunking data.
• Create and Use Custom Language Data
  Create and use your own language-specific conditions (such as common abbreviations) when chunking data.