pablodanswer
680388537b
UX clarity + minor new features ( #2136 )
2024-08-14 15:23:36 -07:00
pablodanswer
d9bcacfae7
validate messages ( #2139 )
2024-08-14 22:06:48 +00:00
hagen-danswer
2ab192933b
Added import statement to fix typescript error ( #2138 )
2024-08-14 20:10:08 +00:00
Yuhong Sun
1c10f54294
GPU Model Server ( #2135 )
2024-08-14 11:04:28 -07:00
josvdw
0530f4283e
updating readme for widget ( #2132 )
...
Co-authored-by: Jos Van der westhuizen <jos@danser.ai>
2024-08-14 16:55:59 +00:00
pablodanswer
3540aa579b
Add ux improvements ( #2130 )
...
* add ux improvements
* add danswer version display
* show version properly
* improve copy + add web version to settings context
* update copy + danswer version
2024-08-14 16:43:52 +00:00
josvdw
54732a83c9
stopgap: clarify text on standard answer page for improved UX ( #2122 )
...
* stopgap: clarify text on standard answer page for improved UX
* replce apostrophe
* using tailwind:
---------
Co-authored-by: Jos Van der westhuizen <jos@danser.ai>
2024-08-14 01:28:49 +00:00
pablodanswer
5e6365c449
Minor update to clarify user adding ( #2126 )
...
* minor update to clarify user adding
* Update page.tsx
* run pretty
2024-08-13 21:09:51 +00:00
rkuo-danswer
20369fc451
Refactor/default indexing embedder ( #2073 )
...
* refactor embedding model instantiation
* remove unused UNCERTAINTY_PAT constant
* typo fixes
* fix mypy typing issues
* more typing fixes
* log attempt.id on dispatch
* unnecessary check removed after fixing type
2024-08-13 21:01:34 +00:00
rkuo-danswer
f15d6d2b59
allow admin role api keys ( #2124 )
...
* allow admin role api keys
* bump to rerun deployment
* types needs explicit export now for APIKey
* remove api_key.role, use User.role instead
* fix formatting
* formatting
* formatting
---------
Co-authored-by: Richard Kuo <rkuo@rkuo.com>
2024-08-13 21:00:57 +00:00
pablodanswer
5dda047999
Always show search filters ( #2128 )
2024-08-13 13:36:46 -07:00
pablodanswer
ffd9b0180b
Fix overflow for quotes in search section ( #2123 )
...
* fix overflow for quotes in search section
* proper overflow check
2024-08-13 20:32:11 +00:00
Yuhong Sun
5ad54fec87
Inference to handle no link docs ( #2129 )
2024-08-13 12:40:11 -07:00
hagen-danswer
d636181aa5
Added catch for empty link ( #2037 )
2024-08-12 20:08:56 -07:00
pablodanswer
e12ed7750a
Add scrollbar to search / chat ( #2121 )
...
* add scrollbar to search / chat
* show overflow for lists
2024-08-13 03:07:37 +00:00
hagen-danswer
bbb8c5ff0b
Speed up docker launch ( #2099 )
...
* use move instead of copy
* added logging
* fix overwrites
* tested throughly
* fixes
* clearer commenting
2024-08-13 00:45:05 +00:00
pablodanswer
83e945ba57
add cleaner / consolidate no docs found message ( #2119 )
2024-08-12 16:04:59 -07:00
rkuo-danswer
26df869b91
Feature/harden memory limits ( #2118 )
...
* log warning in indexer when size exceeds INDEXING_SIZE_WARNING_THRESHOLD
* add configurable attachment size limit for confluence
* specify "attachments"
2024-08-12 15:12:34 -07:00
Weves
1a4df1d65e
Remove unnecessary LLM settings
2024-08-12 11:33:49 -07:00
Chris Weaver
0a165aae0b
Slack improvements ( #2113 )
2024-08-11 21:27:37 -07:00
rkuo-danswer
e517f47a89
add send-message-simple-with-history endpoint to avoid… ( #2101 )
...
* add send-message-simple-with-history endpoint to support ramp. avoids bad json output in models and allows client to pass history in instead of maintaining it in our own session
* slightly better error checking
* addressing code review
* reject on any empty message
* update test naming
2024-08-12 03:33:52 +00:00
Nathan Schwerdfeger
c7e5b11c63
EE Connector Deletion Bugfix + Refactor ( #2042 )
...
---------
Co-authored-by: Weves <chrisweaver101@gmail.com>
2024-08-11 20:33:07 -07:00
Yuhong Sun
79523f2e0a
Warm up reranker ( #2111 )
2024-08-11 15:20:51 -07:00
pablodanswer
7fae66b766
provider type default to none ( #2110 )
2024-08-11 14:51:12 -07:00
Yuhong Sun
386b229ed3
Cohere Rerank ( #2109 )
2024-08-11 14:22:42 -07:00
Yuhong Sun
ce666f3320
Propagate Embedding Enum ( #2108 )
2024-08-11 12:17:54 -07:00
Yuhong Sun
d60fb15ad3
Allowing users to set Search Settings ( #2106 )
2024-08-10 20:48:58 -07:00
pablodanswer
7358ece008
enable assistant editing
2024-08-10 14:38:34 -07:00
josvdw
9c5d33e198
open chatdocument links in a new tab instead of overriding danswer ( #2090 )
...
Co-authored-by: Jos Van der westhuizen <jos@danser.ai>
2024-08-10 21:37:59 +00:00
pablodanswer
7d5cfd2fa3
Add user specific model defaults ( #2043 )
2024-08-10 14:37:33 -07:00
Yuhong Sun
a4caf66a35
User Notification Backend ( #2104 )
2024-08-10 11:39:21 -07:00
pablodanswer
0a8d44b44c
quote processing for lengthy intros ( #2103 )
2024-08-10 11:09:45 -07:00
pablodanswer
cc8a6da8e3
improve llm-generated citations (account for edge case) ( #2096 )
...
* improve llm-generated citations (account for edge case)
* additional test case
2024-08-10 02:06:39 +00:00
pablodanswer
54d4526b73
(Minor) Add cleaner search, feedback model, and connector view ( #2098 )
...
* add cleaner search, feedback model, and connector view
* Update ChatPage.tsx
2024-08-10 01:54:31 +00:00
Yuhong Sun
c8ead6a0dc
Need Reindexing Flag Setup ( #2102 )
2024-08-09 17:44:57 -07:00
pablodanswer
7bfa99766d
Add support for google slides ( #2083 )
...
* add support for google slides
* remove log + account for dead code
* squash
2024-08-09 17:12:51 +00:00
hagen-danswer
b230082891
Openai encoding temp hotfix ( #2094 )
2024-08-09 08:17:31 -07:00
Yuhong Sun
8cd1eda8b1
Rework Rerankers ( #2093 )
2024-08-08 21:33:49 -07:00
Yuhong Sun
7dcc42aa95
Intent Model Update ( #2069 )
2024-08-08 20:45:53 -07:00
pablodanswer
e59d1a0294
fix edge case with simpler code block + python formatting ( #2092 )
2024-08-08 20:44:32 -07:00
pablodanswer
384e61f4b0
add new gpt-4o model
2024-08-08 16:32:57 -07:00
pablodanswer
f28b930475
Image -> img ( #2087 )
2024-08-08 21:46:42 +00:00
pablodanswer
1d989f5343
Fix model override for persisting default assistant ( #2081 )
...
* fix model override for persisting default assistant
* run pretty
* don't modify
* Update ChatPage.tsx
2024-08-08 21:22:19 +00:00
pablodanswer
c1e3a1b3e7
Select proper assistant override ( #2068 )
...
* encode images properly
* proper assistant default model updates
* remove now unneeded image encoding update
* update naming of persona llm option gathering
2024-08-08 21:02:11 +00:00
rkuo-danswer
be9ed319d5
add unit test for quotes ( #2085 )
...
* add unit test for quotes
* test answer and quotes together
2024-08-08 18:20:07 +00:00
pablodanswer
c630fcffee
Improve code block formatting ( #2084 )
...
* initial update to styling
* fix chat input bar padding
* improve color choices
2024-08-08 17:12:35 +00:00
josvdw
f411b9cb55
quality of life improvements for the launch.json template ( #2082 )
...
Co-authored-by: Jos Van der westhuizen <jos@danser.ai>
2024-08-08 06:39:30 +00:00
Richard Kuo (Danswer)
bdaaebe955
use re.search instead of re.match (which searches from start of string only)
2024-08-07 20:55:18 -07:00
pablodanswer
9eb48ca2c3
account for empty links + fix quote processing
2024-08-07 20:55:18 -07:00
rkuo-danswer
509fa3a994
add postgres configuration ( #2076 )
2024-08-08 00:13:59 +00:00
