 Timothy Jaeryang Baek
|
81b8267e85
feat: odt file parse support
|
1 week ago |
 Vaclav Cerny
|
4bbc32efa6
fix: serialize picture description parameters to JSON in DoclingLoader
|
2 weeks ago |
|
Timothy Jaeryang Baek
|
0cd400f5ee
refac: docling picture describe params
|
2 weeks ago |
|
Vaclav Cerny
|
99f05561f8
Add configuration options for picture description modes and update related components
|
2 weeks ago |
|
Timothy Jaeryang Baek
|
5e35aab292
chore: format
|
3 weeks ago |
|
Vaclav Cerny
|
9772c18b20
fix(loader): remove deprecated picture description configuration
|
3 weeks ago |
|
Vaclav Cerny
|
c71236ba07
feat(loader): enhance picture description prompt for improved detail and clarity
|
3 weeks ago |
|
Vaclav Cerny
|
c4278f4784
fix description vs classification mismatch
|
3 weeks ago |
|
Vaclav Cerny
|
8644e81a1c
feat(loader): add picture description configuration for DoclingLoader
|
3 weeks ago |
|
Timothy Jaeryang Baek
|
4d364e2967
refac: remove msg from known type
|
3 weeks ago |
|
Timothy Jaeryang Baek
|
7dc7d5c028
refac: PLEASE FOLLOW EXISTING CONVENTION
|
1 month ago |
|
Timothy Jaeryang Baek
|
551597b9cc
chore: format
|
1 month ago |
 Hisma
|
a9405cc101
feat: Marker api content extraction support
|
1 month ago |
 sree
|
f408b08965
minor bug fix for external document loader not working
|
1 month ago |
|
Timothy Jaeryang Baek
|
8732b64b6b
feat: external document loader support
|
1 month ago |
|
Timothy Jaeryang Baek
|
de70d0cb64
feat: docling do picture description support
|
1 month ago |
|
Timothy Jaeryang Baek
|
e63b8b3879
refac
|
1 month ago |
|
Timothy Jaeryang Baek
|
27da31dc83
fix: tikaloader extract images
|
1 month ago |
 Athanasios Oikonomou
|
657162e96d
feat(ocr): add support for Docling OCR engine and language configuration
|
1 month ago |
 ayan4m1
|
039dec6820
fix: pass header to Tika if PDF_EXTRACT_IMAGES is true
|
2 months ago |
|
Timothy Jaeryang Baek
|
ef787e4a79
Merge pull request #12486 from FabioPolito24/text-file-handling-docling
|
2 months ago |
 Fabio Polito
|
cd0a1b4852
fix: fix for text file handling with docling
|
2 months ago |
 Patrick Wachter
|
0ac00b9256
refactor: update import path for MistralLoader
|
2 months ago |
|
Patrick Wachter
|
93d7702e8c
refactor: move MistralLoader to a separate module and just use the requests package instead of mistralai
|
2 months ago |
|
Patrick Wachter
|
1ac6879268
Add Mistral OCR integration and configuration support
|
3 months ago |
 Junaid Pinjari
|
e782e7d3a7
Fix: CSV loader encoding issue using autodetect_encoding=True
|
3 months ago |
 Iván Baldo
|
115e46a6a2
Fix: Tika 3.1.0.0 sends a lot of blank lines which degrades the RAG results, strip them.
|
3 months ago |
|
Fabio Polito
|
9d6743824e
fix: fix params DoclingLoader
|
3 months ago |
|
Fabio Polito
|
0716f96da8
style: change style in DoclingLoader
|
3 months ago |
|
Fabio Polito
|
9aa407dbd2
feat: merge with main
|
3 months ago |
