This content transformer uses an LLM to extract further structured metadata out of an unstructured text. The resulting fields must become a dictionary or map in form of a JSON. This dictionary is then added to the document metadata.

Configuration Parameters

1. Transformer Stage Type: choose Classifier

2. Prompt: Displays the prompt which is sent, together with the document body, to the LLM. You can adjust it to your needs. However, please make sure that a proper JSON is returned which comprises key-value pairs. Supported values are lists and scalars (strings, numbers, etc.)

3. Length limitation: Here you can enter a fixed number of characters to reduce the load on the LLM. If you leave this value to 0 or a negative value, the entire document is included.

4. LLM Configuration

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