33d93b9761
#1813 Fix squash system messages
2024-02-11 15:56:48 +02:00
cbea5bf996
UI Theme import/export
2024-02-10 23:12:16 +02:00
df97f5364b
Regex import/export
2024-02-10 21:57:22 +02:00
6b669bbc22
#1809 Add gitkeep to user
2024-02-10 21:15:59 +02:00
18f84979f2
Use SSE streaming for MakerSuite
2024-02-10 02:43:50 +02:00
867c42cb6d
Add cyrillic special quotes to tts option
2024-02-09 18:33:01 +02:00
d8d4732614
Add koboldcpp param aliases
2024-02-09 15:32:40 +02:00
0f04508f30
Merge pull request #1806 from bdashore3/staging
...
Fixes for text completions
2024-02-09 10:14:52 +02:00
530455979f
Textgen: Add tabby to logprobs
...
Tabby now supports logprob returns. Add support to the backend gate.
Signed-off-by: kingbri <bdashore3@proton.me>
2024-02-08 20:59:54 -05:00
f372b2ac16
Textgen: Fix dynatemp defaults
...
The default min and max temp values should be 1
Signed-off-by: kingbri <bdashore3@proton.me>
2024-02-08 20:57:40 -05:00
03ad72b6c7
Merge pull request #1802 from Technologicat/modelname
...
{{model}} substitution to get name of current LLM
2024-02-08 11:36:02 +02:00
a49d0f1050
use getGeneratingModel
2024-02-08 11:13:54 +02:00
f5d5a75ef5
[fix/smoothing] align numerical input max with slider max
2024-02-08 02:03:49 +01:00
44a3bb8ec7
#1777 Add await argument to /trigger command
2024-02-08 00:20:36 +02:00
d7f86a7f6b
Merge pull request #1800 from EX3-0/patch-1
...
Update openai.js added /proxy command.
2024-02-08 00:05:53 +02:00
90231680a9
Remove extra space
2024-02-08 00:05:23 +02:00
dfc1719c3f
Use fuzzy name matching
2024-02-08 00:04:48 +02:00
04372848c8
Fix for undefined chats
2024-02-07 23:58:05 +02:00
2dcb490e43
add {{model}} substitution macro to get name of current LLM
...
This is useful in the character card for an AI assistant, see #1774 .
Tested with the Textgen backend, but should work with others too.
Horde will show only "Connected", and Novel will show the tier,
but Kobold and Textgen will show the model name.
If not connected, on any backend, will show "no_connection".
2024-02-07 23:29:32 +02:00
c1a5b50aae
improve description for consistency
2024-02-07 23:12:21 +02:00
5183fb40a2
refactor to improve proposed implementation of /getchatname
2024-02-07 23:09:51 +02:00
5d1f3b13ea
add /getchatname slash command to get name of current chat file
...
Example:
/getchatname | /echo {{pipe}}
2024-02-07 22:51:41 +02:00
b2eb361028
Update openai.js added /proxy command.
...
Added "proxy" slash command to openai.js to change between proxy presets in ST script.
2024-02-07 13:52:48 -05:00
c3129da879
[skip ci] Lint fix
2024-02-07 19:28:34 +02:00
b244a1c301
Mark textgen API key as optional
2024-02-07 19:26:34 +02:00
8ecab19966
Merge pull request #1798 from oobabooga/staging
...
Add API key field for text-generation-webui
2024-02-07 19:24:42 +02:00
f0cffb3dd9
fix /delchat for characters with lots of chat files
2024-02-07 15:20:37 +02:00
21fb143718
Add API key
2024-02-06 20:00:16 -08:00
2815990589
Force personas sort before returning to caller
2024-02-05 10:58:35 +02:00
b158a86c25
Firefox copium for expression images
2024-02-05 02:21:20 +02:00
f12aeeed90
Firefox copium for persona images
2024-02-05 02:18:44 +02:00
41f53f4162
Merge pull request #1790 from Technologicat/talkinghead-fixes-feb2024
...
Talkinghead fixes feb2024
2024-02-05 01:33:39 +02:00
634c9aad3b
add logsprobs support for custom OpenAI APIs
2024-02-04 23:11:45 +00:00
ad48d6666a
fix bug: when switching talkinghead off, set character expression
2024-02-05 00:47:14 +02:00
2a39db799a
auto-pause Talkinghead when ST tab is hidden to save GPU resources
2024-02-05 00:46:44 +02:00
91c4de6605
add `/th` (alias `/talkinghead`) to toggle Talkinghead on/off
2024-02-05 00:46:23 +02:00
5ad2a0d064
refresh talkinghead char on expression zip upload
2024-02-05 00:45:50 +02:00
3b526ce207
remove some useless comments
2024-02-05 00:45:37 +02:00
169b1c2c63
talkinghead check: always check also whether the module is enabled
2024-02-05 00:45:20 +02:00
9e8f3e0def
one more debug message
2024-02-05 00:44:46 +02:00
eb634d597f
add comment on TTS
2024-02-05 00:44:39 +02:00
24b315a149
comments
...
The tech is "Talkinghead" (capital T), the Extras module is
"talkinghead" (lowercase t).
2024-02-05 00:44:26 +02:00
83e264db9e
add some debug messages
2024-02-05 00:40:03 +02:00
b7921f1edd
#1630 Fix regex depth application
2024-02-04 21:34:17 +02:00
bdf7602fab
Add SpeechT5 TTS provider
2024-02-04 20:31:20 +02:00
f1cadfde2b
Fix llamacpp server
2024-02-04 17:41:46 +02:00
c03966d19a
Merge pull request #1786 from bdashore3/staging
...
Fix requests with sampling params
2024-02-04 17:26:54 +09:00
3e34123b31
Textgen: Fix sampling param requests
...
1. TabbyAPI was not being included in temperature_last
2. DynaTemp parameters were still being sent even though the checkbox
was off. Cleanup the parameters if dynatemp is off for backends that
don't take in a dynatemp boolean.
Signed-off-by: kingbri <bdashore3@proton.me>
2024-02-04 01:44:07 -05:00
7ac6ed267f
#1782 OpenAI multiswipe
2024-02-04 03:36:37 +02:00
07677584c4
#1781 Fix /len and unescape for non-string arguments
2024-02-03 02:06:49 +02:00
Cohee
kingbri
Juha Jeronen
lucy
EX3-0
oobabooga
anon
RossAscends