ocr-and-documents

Extract text from PDFs/scans (pymupdf, marker-pdf).

[PDFDocumentsResearchArxiv

PoorRican

0

guidance

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

[PromptEngineeringGuidanceConstrained

PoorRican

0