To add your data to Data 360’s search index, you must first chunk it. Chunking break your data into meaningful chunks, and Data 360 turns those chunks into machine-readable vector embeddings.
Required Editions
| Available in: All Editions supported by Data 360. See Data 360 edition availability |
- Chunking Strategies
Data 360 supports several chunking strategies. Data 360 automatically chooses the optimal chunking strategy based on the content type you're working with. - How the Max Token Setting Affects Chunking
When you set the chunking strategy in a search index configuration, you set the max token limit to control how much text is included in a chunk. In Data 360, the max token limit is set to 512 by default. - Chunk and Index Data Model Objects
When you create a search index configuration, Data 360 creates two additional data model objects: a chunk data model object and an index data model object. These objects store the corresponding data and generated embeddings in Data 360. - Enriched Indexing of Content Chunks
When you create a vector or hybrid search index from unstructured data in Data 360, you can enrich the generated content chunks by extracting metadata from the content. Extracted metadata includes keywords, entities, topic overviews, questions answered by the content, and content summaries. - Citations for Content Chunks
Verify the accuracy of AI responses grounded in your unstructured data with inline citations for content chunks. When you create a search index in Data Cloud, the index creates citations for each chunk.