Tim Jaeryang Baek
696876d393
Merge pull request #18108 from YetheSamartaka/main
...
fix: "Cannot handle batch sizes > 1 if no padding token is defined" for some reranking models
2025-10-07 10:57:34 -05:00
YetheSamartaka
f69426fd77
Fixed: Cannot handle batch sizes > 1 if no padding token is defined
...
Fixes Cannot handle batch sizes > 1 if no padding token is defined
For reranker models that do not have this defined in their config by using the eos_token_id if present as pad_token_id.
2025-10-07 14:47:35 +02:00
Timothy Jaeryang Baek
a2a2bafdf6
enh/refac: url input handling
2025-10-04 02:02:26 -05:00
Timothy Jaeryang Baek
d40c710354
refac
2025-10-04 01:19:33 -05:00
Timothy Jaeryang Baek
339e95e9d7
refac/enh: docling params
2025-10-02 16:28:06 -05:00
Jan Kessler
c9c0dd367f
log web search queries only with level 'debug' instead of 'info'
2025-09-29 11:59:04 +02:00
Timothy Jaeryang Baek
118549caf3
enh/fix: filter content metadata
2025-09-28 20:17:27 -05:00
Timothy Jaeryang Baek
7f411dd5cc
feat/enh: perplexity search support
2025-09-25 14:02:46 -05:00
Timothy Jaeryang Baek
4b6d34438b
refac
2025-09-24 15:20:31 -05:00
Timothy Jaeryang Baek
e06489d92b
enh: search_ollama_cloud
2025-09-24 15:19:05 -05:00
Timothy Jaeryang Baek
23a51f2d01
refac: robust file upload failed handling
2025-09-24 12:17:01 -05:00
Timothy Jaeryang Baek
60f62c2f59
refac
2025-09-17 11:28:04 -05:00
Timothy Jaeryang Baek
051b6daa82
refac/fix: large file upload
2025-09-11 22:29:02 +04:00
Timothy Jaeryang Baek
edc056351d
refac
2025-09-11 21:38:01 +04:00
Timothy Jaeryang Baek
2185fc61c0
refac
2025-09-11 21:29:56 +04:00
Tim Jaeryang Baek
71fd483fba
Merge pull request #17276 from Elettrotecnica/extend-docling-configuration
...
feat: Extend docling configuration options
2025-09-09 18:04:30 +04:00
Antonio Pisano
daa2a036f8
Extend docling configuration options to include:
...
* do_ocr
* force_ocr
* pdf_backend
* table_mode
* pipeline
as per https://github.com/docling-project/docling-serve/blob/main/docs/usage.md
See https://github.com/open-webui/open-webui/issues/17148
2025-09-08 18:51:33 +02:00
Timothy Jaeryang Baek
0a85dd4bca
refac: web search link display
2025-09-07 03:00:28 +04:00
Timothy Jaeryang Baek
07357afcf6
refac
...
Co-Authored-By: _00_ <131402327+rgaricano@users.noreply.github.com>
2025-08-26 16:54:36 +04:00
Tim Jaeryang Baek
5a66f69460
Merge pull request #16779 from mahenning/fix--clean-unload-embed/reranker-models
...
Fix: Free VRAM memory when updating embedding / reranking models
2025-08-21 21:38:37 +04:00
Marko Henning
f2e78d7940
More formatting
2025-08-21 13:42:03 +02:00
Marko Henning
c821c3ecb0
Formatting
2025-08-21 13:40:56 +02:00
Marko Henning
b3de3295d6
Chage torch import to conditional import
2025-08-21 13:19:24 +02:00
Marko Henning
6663fc3a6c
Unloads only if internal models are used.
2025-08-21 10:49:03 +02:00
Marko Henning
cd02ff2e07
Fix if checks
2025-08-20 14:07:13 +02:00
Marko Henning
39fe385017
Correctly unloads embedding/reranker models
2025-08-20 13:30:45 +02:00
Timothy Jaeryang Baek
5e1f4fa0ff
feat: async file upload
2025-08-20 00:36:13 +04:00
Timothy Jaeryang Baek
f97f21bf3a
refac/fix: rename WEB_SEARCH_CONCURRENT_REQUESTS to WEB_LOADER_CONCURRENT_REQUESTS
2025-08-18 20:06:36 +04:00
Timothy Jaeryang Baek
e8cb57750b
refac/fix: serply
2025-08-09 00:37:37 +04:00
Timothy Jaeryang Baek
736b29ddca
refac
2025-08-09 00:33:41 +04:00
Tim Jaeryang Baek
5db60ca34f
Merge pull request #15903 from Hisma/marker-api-update
...
feat: Add configurable API URL (for self-hosting) and additional_config parameter for Datalab Marker API
2025-08-04 15:21:03 +04:00
Timothy Jaeryang Baek
6a17ba5b7a
refac: metadata handling in vectordb
2025-07-31 17:45:06 +04:00
Hisma
a99e20cc3d
add format_lines
2025-07-22 21:06:29 -04:00
Hisma
f31cc07a9d
feat: update marker api
2025-07-22 20:49:28 -04:00
Azure Wang
9aff166f83
- fix: keep reranker_model config been removed by web search config
2025-07-16 23:51:23 +08:00
Timothy Jaeryang Baek
abe280f0a3
refac/fix: reranking function
2025-07-16 13:56:02 +04:00
Timothy Jaeryang Baek
18bd83413b
refac
2025-07-14 14:05:06 +04:00
Timothy Jaeryang Baek
0013f5c1fc
refac/enh: forward user info header to reranker
2025-07-14 13:59:10 +04:00
Timothy Jaeryang Baek
87847ab31a
chore: format
2025-07-13 00:15:16 +04:00
Tim Jaeryang Baek
e3b8f700e4
Merge pull request #14264 from diwakar-s-maurya/patch-6
...
feat: add langchain markdown document splitter
2025-07-08 15:55:20 +04:00
Tim Jaeryang Baek
2bad7eaa07
Merge pull request #15277 from hankewyczz/bug/restore-exa-search
...
fix Restore exa
2025-06-25 11:04:48 +04:00
Zachar Hankewycz
45d7726ee0
Restore exa
2025-06-24 21:24:53 -04:00
zhangtyzzz
5f60b30320
add missed exa
2025-06-19 13:52:58 +08:00
Timothy Jaeryang Baek
6c54ca552a
feat: global image compression
2025-06-16 16:52:57 +04:00
Timothy Jaeryang Baek
f3cae94028
fix: bypass webloader
...
Co-Authored-By: WilliamGates <3852641+williamgateszhao@users.noreply.github.com>
2025-06-16 16:17:52 +04:00
Timothy Jaeryang Baek
0cd400f5ee
refac: docling picture describe params
2025-06-08 20:02:14 +04:00
Vaclav Cerny
99f05561f8
Add configuration options for picture description modes and update related components
2025-06-08 16:30:26 +02:00
Diwakar Singh Maurya
871efb4ad9
feat: add langchain markdown document splitter
2025-06-07 06:02:53 +00:00
Dave
96e9bfe0e5
feat: add Perplexity model and search context usage configuration options
2025-06-03 00:19:08 +02:00
Timothy Jaeryang Baek
e1e2c096e2
refac: PLEASE follow existing convention
2025-05-30 00:34:18 +04:00