By Use Case
Build Production Pipelines
Chain processors into versioned pipelines for production use
Process PDFs for RAG/LLM
Convert documents to markdown or chunks for retrieval-augmented generation
Extract Invoice/Receipt Data
Pull structured fields (amounts, dates, line items) from financial documents
Analyze Contracts
Extract parties, dates, and clauses from legal documents
Process Research Papers
Extract titles, authors, abstracts, and citations from academic papers
Fill Out Forms
Automatically fill PDF and image forms with structured data
Generate Documents
Create Word documents from markdown with track changes
Split Batch-Scanned PDFs
Separate multi-document PDFs into individual documents
Review Track Changes
Extract redlines, insertions, deletions, and comments from Word documents
By Feature
| Feature | Description | Guide |
|---|---|---|
| Document Conversion | Convert PDFs, images, and office docs to markdown/HTML/JSON | Guide |
| Batch Processing | Process multiple documents concurrently | Guide |
| Structured Extraction | Extract fields using JSON schemas | Guide |
| Long Document Handling | Strategies for 100+ page documents | Guide |
| Document Segmentation | Split multi-document PDFs by section | Guide |
| Form Filling | Fill PDF and image forms programmatically | Guide |
| Create Document | Generate DOCX files from markdown | Guide |
| File Upload | Upload and manage files for reuse | Guide |
| Pipelines | Chain processors into versioned, reusable configurations | Guide |
| Pipeline Versioning | Manage drafts, publish versions, pin production deployments | Guide |
| Track Changes | Extract redlines and comments from Word docs | Guide |
| Forge Evals | Compare parsing configurations side-by-side | Guide |