pablodanswer
a385234c0e
Parsing ( #2734 )
...
* k
* update chunking limits
* nit
* nit
* clean up types
* nit
* validate
* k
2024-10-16 16:44:19 +00:00
Yuhong Sun
b212b228fb
Typo Fix ( #2766 )
2024-10-10 10:21:30 -07:00
Yuhong Sun
85d5e6c02f
PDF Encrypted Case ( #2764 )
2024-10-10 10:17:18 -07:00
Yuhong Sun
fffb9c155a
Redis Cache for KV Store ( #2603 )
...
* k
* k
* k
* k
2024-10-01 18:31:18 +00:00
Yuhong Sun and pablodanswer
e229d27734
Unstructured UI ( #2636 )
...
* checkpoint
* k
* k
* need frontend
* add api key check + ui component
* add proper ports + icons + functions
* k
* k
* k
---------
Co-authored-by: pablodanswer <pablo@danswer.ai >
2024-10-01 04:50:03 +00:00
Art Matsak
51a13f5fc7
Implement indexing of simple tables in Word files ( #1651 )
2024-09-08 09:38:46 -07:00
pablodanswer
5abf67fbf0
PDF metadata + list defaults ( #2341 )
...
* validate web list
* update pdf extraction of metadat
* remove pdf + log
* stricter type enforcing
* fix up indexing widths
* minor formatting
* add list case
* check for empty metadata
2024-09-06 21:21:24 +00:00
Yuhong Sun
580848cf8c
mypy ( #2283 )
2024-08-30 18:02:18 -07:00
pablodanswer
76db4b765a
Detect GPU on startup for default multi-pass indexing value ( #2242 )
2024-08-30 17:38:31 -07:00
pablodanswer
5800c7158e
Add typing to pdf extraction ( #2280 )
2024-08-30 17:16:56 -07:00
pablodanswer
4181124e7a
add metadata to pdf extraction ( #2278 )
2024-08-30 15:14:02 -07:00
Yuhong Sun
5ab4d94d94
Logging Level Update ( #2165 )
2024-08-18 21:53:40 -07:00
Yuhong Sun
061dab7f37
Touchup ( #1702 )
2024-06-25 10:34:03 -07:00
hagen-danswer
e65d9e155d
fixed confluence breaking on unknown filetypes ( #1698 )
2024-06-25 10:19:01 -07:00
Kevin Shi
ba58208a85
Transform HTML links to markdown behind config option ( #1671 )
2024-06-20 10:43:15 -07:00
Yuhong Sun
c798ade127
Code for ease of eval ( #1656 )
2024-06-17 20:32:12 -07:00
hagen-danswer
180b592afe
added html support to file text extractor ( #1611 )
2024-06-10 12:46:05 -07:00
hagen-danswer
64a042b94d
cleaned up sharepoint connector ( #1599 )
...
* cleaned up sharepoint connector
* additional cleanup
* fixed dropbox connector string
2024-06-09 12:15:52 -07:00
Yuhong Sun and Weves
57452b1030
File Chat Upload ( #1490 )
...
Also includes minor UX improvements
---------
Co-authored-by: Weves <chrisweaver101@gmail.com >
2024-05-23 15:04:36 -07:00
Yuhong Sun
546815dc8c
Consolidate File Processing ( #1449 )
2024-05-11 23:11:22 -07:00
pablodanswer