← All updates Databricks Update One-Pager Light version
databricks Platform · Updated Jun 25, 2025

Use PDFs in Information Extraction and Custom LLM (Beta)

Information Extraction and Custom LLM have a UI workflow to convert PDFs to Markdown and store the results in a table.

Beta Open docs ↗release note ↗
What it does

Information Extraction and Custom LLM have a UI workflow to convert PDFs to Markdown and store the results in a table. Users can then use the resulting table as input in Information Extraction and Custom LLM. Beta This feature is in Beta.

Why it matters

Custom LLM leverages automated evaluation capabilities, including MLflow and Agent Evaluation, to enable rapid assessment of the cost quality tradeoff for your specific extraction task.

Key capabilities
Serverless compute available (enabled by
Serverless compute available (enabled by default in workspaces with Unity Catalog).
Unity Catalog enabled. See Enable
Unity Catalog enabled. See Enable a workspace for Unity Catalog.
Access to Model Serving
Access to Model Serving.
Access to a serverless usage
Access to a serverless usage policy with a nonzero budget. A workspace in one of the supported regions. Ability to use the…
Recommended use cases
Summarizing the issueresolution of customer calls.
Architecture
Databricks Platform → Platform
In short

Information Extraction and Custom LLM have a UI workflow to convert PDFs to Markdown and store the results in a table. Users can then use the resulting table as input in Information Extraction and Custom LLM.

Read the full documentation ↗
Key takeaway
Information Extraction and Custom LLM have a UI workflow to convert PDFs to Markdown and store the results in a table.
2025-06-25-use-pdfs-in-information-extraction-and-custom-llm-beta Generated by the Databricks Updates Agent · browse all updates