Follow a few automated steps to create a hybrid search index configuration for a data model object (DMO) or an unstructured data model object (UDMO). Data 360 automatically applies defaults for the chunking and vectorization strategies, and creates chunk and index model objects.
Required Editions
| Available in: All Editions supported by Data 360. See Data 360 edition availability. |
| User Permissions Needed | |
|---|---|
| To create a search index configuration: |
Permission set:
|
Before creating a search index, review the Unstructured Data and Search Index Guidelines and Limits in Data 360 Limits and Guidelines and search index considerations in the Search Reference. Familiarize yourself with the concepts of chunking unstructured data, vectorization, and the chunk and index data model objects.
Easy Setup includes these defaults.
- Chunking strategy: Passage extraction
- Embedding model: E5-Large V2
- Search Type: Hybrid Search
- From App Launcher, select Data Cloud.
- Click Search Index > New.
- Click Easy Setup > Next.
-
From the New Search Index Configuration page, select a Data Space and one or more
UDMOs or DMOs. A search index configuration is created for each object that you
select.
Note A DMO that has mappings from one or more external DLOs can only be used as the data source if caching is enabled for all those external DLOs. For more information see, Caching in Data Federation. - Add a Search Index Configuration Name and Search Index Configuration API Name.
- Click Next.
- Review the configuration and the target data model objects, and click Save.
-
Create a retriever in AI Models (formerly Einstein Studio) to retrieve data from a search index.
Use retrievers in prompt templates and agent actions to get relevant results. For more information see, Create an Individual Retriever.
Data 360 creates a hybrid search index for the DMO or UDMO selected.