Databricks ai_prep_search Function Now Accepts Plain Text and Markdown (Beta)
The Databricks `ai_prep_search()` SQL function now accepts plain text and markdown string content, expanding beyond its previous requirement for structured VARIANT output. This enhancement allows developers to directly chunk and prepare existing textual data for AI Search indexing and retrieval-augmented generation (RAG) pipelines. It streamlines the process by removing the prerequisite of document parsing, enabling more flexible data preparation workflows. This capability is currently available in Beta.
Features (1) ›
- ai_prep_search supports plain text and markdown input
The `ai_prep_search()` SQL function has been updated to accept plain text and markdown string content, removing the previous dependency on `ai_parse_document`'s structured output. This allows direct preparation of existing text for AI Search indexing and RAG pipelines without prior parsing.
https://docs.databricks.com/aws/en/release-notes/product/2026/august#ai_prep_search-supports-plain-text-and-markdown-input-beta
Related releases
- xAI Grok 4.6 Model Now Available on Databricks Model Serving Databricks Release Notes ·
- Databricks enhances Genie Agents with chat sharing, visualization downloads, and bug fixes Databricks Release Notes ·
- Python UDTFs in Unity Catalog Now Generally Available Databricks Release Notes ·
- Databricks Enhances Dashboards and Genie Code with AI-Powered Features Databricks Release Notes ·
- Genie One Enhancements for Task Management, Conversations, and Mobile App Login Databricks Release Notes ·
- Databricks Genie Code Now Available for HIPAA-Compliant Workspaces Databricks Release Notes ·