 Tim Jaeryang Baek
|
5db60ca34f
Merge pull request #15903 from Hisma/marker-api-update
|
hai 2 meses |
 Hisma
|
a99e20cc3d
add format_lines
|
hai 2 meses |
|
Hisma
|
f31cc07a9d
feat: update marker api
|
hai 2 meses |
 bekzod
|
4bc054a347
Update docling endpoint
|
hai 2 meses |
 expruc
|
453a2bd9b5
fixed issue where text/html files being detected as text when loaded
|
hai 3 meses |
|
Timothy Jaeryang Baek
|
81b8267e85
feat: odt file parse support
|
hai 3 meses |
 Vaclav Cerny
|
4bbc32efa6
fix: serialize picture description parameters to JSON in DoclingLoader
|
hai 3 meses |
|
Timothy Jaeryang Baek
|
0cd400f5ee
refac: docling picture describe params
|
hai 4 meses |
|
Vaclav Cerny
|
99f05561f8
Add configuration options for picture description modes and update related components
|
hai 4 meses |
|
Timothy Jaeryang Baek
|
5e35aab292
chore: format
|
hai 4 meses |
|
Vaclav Cerny
|
9772c18b20
fix(loader): remove deprecated picture description configuration
|
hai 4 meses |
|
Vaclav Cerny
|
c71236ba07
feat(loader): enhance picture description prompt for improved detail and clarity
|
hai 4 meses |
|
Vaclav Cerny
|
c4278f4784
fix description vs classification mismatch
|
hai 4 meses |
|
Vaclav Cerny
|
8644e81a1c
feat(loader): add picture description configuration for DoclingLoader
|
hai 4 meses |
|
Timothy Jaeryang Baek
|
4d364e2967
refac: remove msg from known type
|
hai 4 meses |
|
Timothy Jaeryang Baek
|
7dc7d5c028
refac: PLEASE FOLLOW EXISTING CONVENTION
|
hai 4 meses |
|
Timothy Jaeryang Baek
|
551597b9cc
chore: format
|
hai 4 meses |
|
Hisma
|
a9405cc101
feat: Marker api content extraction support
|
hai 4 meses |
 sree
|
f408b08965
minor bug fix for external document loader not working
|
hai 4 meses |
|
Timothy Jaeryang Baek
|
8732b64b6b
feat: external document loader support
|
hai 4 meses |
|
Timothy Jaeryang Baek
|
de70d0cb64
feat: docling do picture description support
|
hai 4 meses |
|
Timothy Jaeryang Baek
|
e63b8b3879
refac
|
hai 5 meses |
|
Timothy Jaeryang Baek
|
27da31dc83
fix: tikaloader extract images
|
hai 5 meses |
 Athanasios Oikonomou
|
657162e96d
feat(ocr): add support for Docling OCR engine and language configuration
|
hai 5 meses |
 ayan4m1
|
039dec6820
fix: pass header to Tika if PDF_EXTRACT_IMAGES is true
|
hai 5 meses |
|
Timothy Jaeryang Baek
|
ef787e4a79
Merge pull request #12486 from FabioPolito24/text-file-handling-docling
|
hai 6 meses |
 Fabio Polito
|
cd0a1b4852
fix: fix for text file handling with docling
|
hai 6 meses |
 Patrick Wachter
|
0ac00b9256
refactor: update import path for MistralLoader
|
hai 6 meses |
|
Patrick Wachter
|
93d7702e8c
refactor: move MistralLoader to a separate module and just use the requests package instead of mistralai
|
hai 6 meses |
|
Patrick Wachter
|
1ac6879268
Add Mistral OCR integration and configuration support
|
hai 6 meses |
