Activity
update README with more OCR mode info
update README with more OCR mode info
update project for v0.3.0 release
update project for v0.3.0 release
feat: add docling integration for document OCR
feat: add docling integration for document OCR
use openai predicted outputs for gptparse hybrid
use openai predicted outputs for gptparse hybrid
docs: add hybrid mode documentation
docs: add hybrid mode documentation
feat(hybrid): add hybrid mode combining fast and vision
feat(hybrid): add hybrid mode combining fast and vision
docs(readme): add documentation for fast mode
docs(readme): add documentation for fast mode
feat(fast): add fast PDF parsing mode using pymupdf4llm
feat(fast): add fast PDF parsing mode using pymupdf4llm
Update README to contain more info on processing images
Update README to contain more info on processing images
feat: add support for image files
feat: add support for image files
update configs to use latest anthropic models
update configs to use latest anthropic models
minor improvements to enhance user experience upon installation
minor improvements to enhance user experience upon installation
update pyproject and vision description in cli
update pyproject and vision description in cli