This content transformer uses an LLM to extract textual information from images. The outcome is HTML which can used in the subsequent processing steps.

Configuration Parameters

1. Type. OCR Extractor

2. Prompt. This is the system prompt used to tell the model how to extract OCR.

3. Size limitation. This is the maximum size in bytes which is sent to the LLM for extraction.

4. LLM Configuration

   1. See the parameter description at LLM Specific Configurations - Content Transformers