Feature
Fix
Documentation
Feature
Feature
Feature
Fix
- Fix OCR setting for pypdfium, minor refactor (#102) (
d96b96c
)
Documentation
Fix
- Updated the render_as_doctags with the new arguments from docling-core (#93) (
4794ce4
)
Feature
Fix
- Bumped the glm version and adjusted the tests (#83) (
442443a
)
Documentation
- Updated Docling logo.png with transparent background (#88) (
0da7519
)
Fix
- tests: Adjust the test data to match the new version of LayoutPredictor (#82) (
fa9699f
)
Fix
- CLI compatibility with python 3.10 and 3.11 (#79) (
2870fdc
)
Feature
Documentation
- Showcase RAG with LlamaIndex and LangChain (#71) (
53569a1
)
Feature
Feature
- Linux arm64 support and reducing dependencies (#69) (
27a7a15
)
v1.9.0 - 2024-09-03
Feature
- Export document pages as multimodal output (#54) (
1de2e4f
)
Documentation
v1.8.5 - 2024-08-30
Fix
v1.8.4 - 2024-08-30
Fix
Documentation
- Add instructions for cpu-only installation (#56) (
a8a60d5
)
v1.8.3 - 2024-08-28
Fix
- Table cells overlap and model warnings (#53) (
f49ee82
)
v1.8.2 - 2024-08-27
Fix
Documentation
v1.8.1 - 2024-08-26
Fix
v1.8.0 - 2024-08-23
Feature
- Page-level error reporting from PDF backend, introduce PARTIAL_SUCCESS status (#47) (
a294b7e
)
v1.7.1 - 2024-08-23
Fix
- Better raise exception when a page fails to parse (#46) (
8808463
)
- Upgrade docling-parse to 1.1.1, safety checks for failed parse on pages (#45) (
7e84533
)
v1.7.0 - 2024-08-22
Feature
- Upgrade docling-parse PDF backend and interface to use page-by-page parsing (#44) (
a8c6b29
)
v1.6.3 - 2024-08-22
Fix
- Usage of bytesio with docling-parse (#43) (
fac5745
)
v1.6.2 - 2024-08-22
Fix
- Remove [ocr] extra to fix wheel install (#42) (
6995268
)
v1.6.1 - 2024-08-21
Fix
v1.6.0 - 2024-08-20
Feature
- Add adaptive OCR, factor out treatment of OCR areas and cell filtering (#38) (
e94d317
)
v1.5.0 - 2024-08-20
Feature
- Allow computing page images on-demand with scale and cache them (#36) (
78347bf
)
Documentation
v1.4.0 - 2024-08-14
Feature
- Update parser with bytesio interface and set as new default backend (#32) (
90dd676
)
Fix
v1.3.0 - 2024-08-12
Feature
- Output page images and extracted bbox (#31) (
63d80ed
)
v1.2.1 - 2024-08-07
Fix
Documentation
v1.2.0 - 2024-08-07
Feature
v1.1.2 - 2024-07-31
Fix
- Set page number using 1-based indexing (#22) (
d2d9543
)
v1.1.1 - 2024-07-30
Fix
- Correct text extraction for table cells (#21) (
f4bf3d2
)
v1.1.0 - 2024-07-26
Feature
- Add simplified single-doc conversion (#20) (
d603137
)
v1.0.2 - 2024-07-24
Fix
- Add easyocr to main deps for valid extra (#19) (
54b3dda
)
v1.0.1 - 2024-07-24
Fix
v1.0.0 - 2024-07-18
Feature
Breaking
v0.4.0 - 2024-07-17
Feature
- Optimize table extraction quality, add configuration options (#11) (
e9526bb
)
v0.3.1 - 2024-07-17
Fix
Documentation
- Reflect supported Python versions, add badges (#10) (
2baa35c
)
v0.3.0 - 2024-07-17
Feature
- Enable python 3.12 support by updating glm (#8) (
fb72688
)
Documentation
v0.2.0 - 2024-07-16
Feature