m.dabbagh
|
b57792eb41
|
feat: add pptx_extractor and html_extractor
|
2026-01-31 18:23:04 +03:30 |
|
m.dabbagh
|
b53f8c47d3
|
add title to Document model and remove display_name form DocumentMetadata
|
2026-01-28 22:13:55 +03:30 |
|
m.dabbagh
|
6259220629
|
disable swagger auth
|
2026-01-28 22:10:24 +03:30 |
|
m.dabbagh
|
2753b913fb
|
enable swagger auth
|
2026-01-28 10:46:37 +03:30 |
|
m.dabbagh
|
a1fbd12874
|
fix: paragraph_chunker was adding "None" when the section.title was none
|
2026-01-27 21:08:32 +03:30 |
|
m.dabbagh
|
80dd901e42
|
fix: remove file extension from DocumentMetadata.display_name
|
2026-01-25 11:33:50 +03:30 |
|
m.dabbagh
|
9e1e49bc59
|
add document title and section title to the beginning of each chunk in paragraph chunker
|
2026-01-25 11:32:35 +03:30 |
|
m.dabbagh
|
cda128e438
|
one paragraph per chunk in paragraph chunking method
|
2026-01-25 11:03:54 +03:30 |
|
m.dabbagh
|
8ecbd88498
|
make DocumentSection.title optional
|
2026-01-24 20:25:34 +03:30 |
|
m.dabbagh
|
3aad734140
|
comment out swagger authentication
|
2026-01-24 17:06:25 +03:30 |
|
m.dabbagh
|
c6302bc792
|
add api-key header and swagger authentication
|
2026-01-24 17:05:29 +03:30 |
|
m.dabbagh
|
2ccb38179d
|
use docling in extractors
|
2026-01-24 13:43:07 +03:30 |
|
m.dabbagh
|
ad163eb665
|
change api defaults
|
2026-01-20 23:36:02 +03:30 |
|
m.dabbagh
|
91f8035043
|
add s3 storage
|
2026-01-20 12:46:47 +03:30 |
|
m.dabbagh
|
0c09c79a2e
|
refactor api routes
|
2026-01-19 22:03:36 +03:30 |
|
m.dabbagh
|
6086ddf818
|
add /chunk route
|
2026-01-19 21:54:23 +03:30 |
|
m.dabbagh
|
2c4a59f84b
|
add extract endpoint
|
2026-01-19 16:05:55 +03:30 |
|
m.dabbagh
|
0084ae6bc0
|
fix
|
2026-01-19 15:42:46 +03:30 |
|
m.dabbagh
|
e783d92eca
|
make chunking method enum and remove some redundant code in core and api
|
2026-01-19 15:19:11 +03:30 |
|
m.dabbagh
|
e2e1c86dd4
|
fix sorting and merging in zip extractor
|
2026-01-19 14:00:17 +03:30 |
|
m.dabbagh
|
6072bb188c
|
fix a bug in zip extractor
|
2026-01-18 20:57:01 +03:30 |
|
m.dabbagh
|
32ca394d91
|
some fixes on the output text
|
2026-01-18 20:05:41 +03:30 |
|
m.dabbagh
|
90c10c79fa
|
add text api
|
2026-01-18 19:38:53 +03:30 |
|
m.dabbagh
|
13b887260f
|
add zip extractor adapter
|
2026-01-18 15:44:49 +03:30 |
|
m.dabbagh
|
f06370e0b9
|
some fixes in concrete implementations of chunkers
|
2026-01-08 16:47:50 +03:30 |
|
m.dabbagh
|
2c375ce6bd
|
make the domain general and open to add crawling system
|
2026-01-08 04:57:35 +03:30 |
|
m.dabbagh
|
359026fa98
|
add SourceFile, DocumentSection models and markdown parser
|
2026-01-08 03:46:35 +03:30 |
|
m.dabbagh
|
10a619494b
|
fix potential race condition in DocumentProcessorService._chunk_document by making the context stateless
|
2026-01-07 21:57:22 +03:30 |
|
m.dabbagh
|
fd39184c0c
|
some fixes on architecture. make bootstrap wraps only the hexagonal plus the outgoing adapters
|
2026-01-07 21:02:38 +03:30 |
|
m.dabbagh
|
70f5b1478c
|
init
|
2026-01-07 19:15:46 +03:30 |
|