 Hisma
|
a9405cc101
feat: Marker api content extraction support
|
4 mesi fa |
 sree
|
f408b08965
minor bug fix for external document loader not working
|
4 mesi fa |
 Timothy Jaeryang Baek
|
8732b64b6b
feat: external document loader support
|
4 mesi fa |
|
Timothy Jaeryang Baek
|
de70d0cb64
feat: docling do picture description support
|
4 mesi fa |
|
Timothy Jaeryang Baek
|
e63b8b3879
refac
|
5 mesi fa |
|
Timothy Jaeryang Baek
|
27da31dc83
fix: tikaloader extract images
|
5 mesi fa |
 Athanasios Oikonomou
|
657162e96d
feat(ocr): add support for Docling OCR engine and language configuration
|
5 mesi fa |
 ayan4m1
|
039dec6820
fix: pass header to Tika if PDF_EXTRACT_IMAGES is true
|
5 mesi fa |
|
Timothy Jaeryang Baek
|
ef787e4a79
Merge pull request #12486 from FabioPolito24/text-file-handling-docling
|
6 mesi fa |
 Fabio Polito
|
cd0a1b4852
fix: fix for text file handling with docling
|
6 mesi fa |
 Patrick Wachter
|
0ac00b9256
refactor: update import path for MistralLoader
|
6 mesi fa |
|
Patrick Wachter
|
93d7702e8c
refactor: move MistralLoader to a separate module and just use the requests package instead of mistralai
|
6 mesi fa |
|
Patrick Wachter
|
1ac6879268
Add Mistral OCR integration and configuration support
|
6 mesi fa |
 Junaid Pinjari
|
e782e7d3a7
Fix: CSV loader encoding issue using autodetect_encoding=True
|
6 mesi fa |
 Iván Baldo
|
115e46a6a2
Fix: Tika 3.1.0.0 sends a lot of blank lines which degrades the RAG results, strip them.
|
6 mesi fa |
|
Fabio Polito
|
9d6743824e
fix: fix params DoclingLoader
|
7 mesi fa |
|
Fabio Polito
|
0716f96da8
style: change style in DoclingLoader
|
7 mesi fa |
|
Fabio Polito
|
9aa407dbd2
feat: merge with main
|
7 mesi fa |
|
Fabio Polito
|
a44b35e99e
fix: fix DoclingLoader input params
|
7 mesi fa |
|
Timothy Jaeryang Baek
|
33d3558ca9
Merge pull request #10817 from NovoNordisk-OpenSource/ivaroli/adding-json-as-supported-file-type
|
7 mesi fa |
 Ívar Óli Sigurðsson
|
c5a09cdd21
adding a comma
|
7 mesi fa |
|
Ívar Óli Sigurðsson
|
661711164a
Adding json as a known source for Tika
|
7 mesi fa |
|
Fabio Polito
|
2419ef06a0
feat: docling support for document preprocessing
|
7 mesi fa |
 Mazurek Michal
|
35f3824932
feat: Implement Document Intelligence as Content Extraction Engine
|
8 mesi fa |
|
Timothy Jaeryang Baek
|
f341971eae
fix
|
9 mesi fa |
 MooreDerek
|
4905c180a5
Only log file contents in debug
|
9 mesi fa |
|
Timothy Jaeryang Baek
|
d3d161f723
wip
|
10 mesi fa |
