Understanding Reducto’s Extract endpoint
schema
: A JSON schema that details the specific fields and structure of your output.system_prompt
: An overall system prompt, that helps our models understand your document structure better.array_extract
and generate_citations
Why are the outputs different when I run it multiple times with the same schema?
Why is extraction only working on the first X pages? I want the whole document.
Why are my extraction results missing values present in my schema?
How do I extract different schemas depending on the document type?
What's the best way to approach handling edge cases?
Can I manipulate data directly in the field descriptions or system prompt?