Raduan A.
bc5a57ec6e
Merge 39d5a088b8 into 73ba69d8cd
2025-02-09 10:47:40 -06:00
KennyZhang1
bfde857420
Add support for conversion via Document Intelligence ( #303 )
...
* added cli params for doc intel
* added DocumentIntelligenceConverter class implementation
* initialized doc intel client instance field
* added isolated doc_intel main conversion function
* temp fix for ContentFormat import bug
* ran tests for docintel and offline for many filetypes
* push doc intel converter to the top of the stack
* formatting changes
* modified project toml file
2025-01-24 14:09:32 -08:00
yeungadrian
08ed32869e
Feature/ Add xls support ( #169 )
...
* add xlrd
* add xls converter with tests
2025-01-03 13:58:17 -08:00
Murat Can Kurtuluş
d248621ba4
feat: outlook ".msg" file converter ( #196 )
...
* feat: outlook .msg converter
* add test, adjust docstring
2025-01-03 13:34:39 -08:00
lumin
c86287b7e3
feat: add project description in pyproject.toml
2024-12-19 13:02:47 +09:00
Raduan77
314c0dced8
format via black
2024-12-18 10:45:05 +01:00
Raduan77
60d2840656
Merge branch 'main' into add-async-wrapper
2024-12-18 10:42:53 +01:00
Adam Fourney
248d64edd0
Added llm tests to the local test set.
2024-12-17 12:13:19 -08:00
Raduan77
eb09e3701d
Add AsyncMarkItDown as a wrapper
2024-12-15 12:18:44 +01:00
Divyansh Singh
52b723724c
Fix character decoding issues with text-like files
2024-12-15 10:37:59 +05:30
Simon Willison
3b88696777
Remove invalid classifiers
...
requires-python says 3.10 and higher only
2024-12-13 10:53:35 -08:00
Adam Fourney
997c7af53c
Added a simple CLI.
2024-11-14 07:50:21 -08:00
Adam Fourney
f20c964f99
Initial commit.
2024-11-13 13:00:01 -08:00
