Vaclav Cerny
|
c71236ba07
feat(loader): enhance picture description prompt for improved detail and clarity
|
преди 4 месеца |
Vaclav Cerny
|
c4278f4784
fix description vs classification mismatch
|
преди 4 месеца |
Vaclav Cerny
|
8644e81a1c
feat(loader): add picture description configuration for DoclingLoader
|
преди 4 месеца |
Timothy Jaeryang Baek
|
4d364e2967
refac: remove msg from known type
|
преди 4 месеца |
Timothy Jaeryang Baek
|
7dc7d5c028
refac: PLEASE FOLLOW EXISTING CONVENTION
|
преди 4 месеца |
Timothy Jaeryang Baek
|
551597b9cc
chore: format
|
преди 4 месеца |
Hisma
|
a9405cc101
feat: Marker api content extraction support
|
преди 4 месеца |
sree
|
f408b08965
minor bug fix for external document loader not working
|
преди 4 месеца |
Timothy Jaeryang Baek
|
8732b64b6b
feat: external document loader support
|
преди 4 месеца |
Timothy Jaeryang Baek
|
de70d0cb64
feat: docling do picture description support
|
преди 4 месеца |
Timothy Jaeryang Baek
|
e63b8b3879
refac
|
преди 5 месеца |
Timothy Jaeryang Baek
|
27da31dc83
fix: tikaloader extract images
|
преди 5 месеца |
Athanasios Oikonomou
|
657162e96d
feat(ocr): add support for Docling OCR engine and language configuration
|
преди 5 месеца |
ayan4m1
|
039dec6820
fix: pass header to Tika if PDF_EXTRACT_IMAGES is true
|
преди 5 месеца |
Timothy Jaeryang Baek
|
ef787e4a79
Merge pull request #12486 from FabioPolito24/text-file-handling-docling
|
преди 6 месеца |
Fabio Polito
|
cd0a1b4852
fix: fix for text file handling with docling
|
преди 6 месеца |
Patrick Wachter
|
0ac00b9256
refactor: update import path for MistralLoader
|
преди 6 месеца |
Patrick Wachter
|
93d7702e8c
refactor: move MistralLoader to a separate module and just use the requests package instead of mistralai
|
преди 6 месеца |
Patrick Wachter
|
1ac6879268
Add Mistral OCR integration and configuration support
|
преди 6 месеца |
Junaid Pinjari
|
e782e7d3a7
Fix: CSV loader encoding issue using autodetect_encoding=True
|
преди 6 месеца |
Iván Baldo
|
115e46a6a2
Fix: Tika 3.1.0.0 sends a lot of blank lines which degrades the RAG results, strip them.
|
преди 6 месеца |
Fabio Polito
|
9d6743824e
fix: fix params DoclingLoader
|
преди 7 месеца |
Fabio Polito
|
0716f96da8
style: change style in DoclingLoader
|
преди 7 месеца |
Fabio Polito
|
9aa407dbd2
feat: merge with main
|
преди 7 месеца |
Fabio Polito
|
a44b35e99e
fix: fix DoclingLoader input params
|
преди 7 месеца |
Timothy Jaeryang Baek
|
33d3558ca9
Merge pull request #10817 from NovoNordisk-OpenSource/ivaroli/adding-json-as-supported-file-type
|
преди 7 месеца |
Ívar Óli Sigurðsson
|
c5a09cdd21
adding a comma
|
преди 7 месеца |
Ívar Óli Sigurðsson
|
661711164a
Adding json as a known source for Tika
|
преди 7 месеца |
Fabio Polito
|
2419ef06a0
feat: docling support for document preprocessing
|
преди 7 месеца |
Mazurek Michal
|
35f3824932
feat: Implement Document Intelligence as Content Extraction Engine
|
преди 8 месеца |