7ec9996c1f
Add prompt cost for OpenRouter under text completion
2024-03-13 02:55:09 +02:00
e24fbfdc1d
Update default OAI sampler parameters
2024-03-13 02:25:20 +02:00
da6545e615
Add {{name}} macro for instruct sequences. Resolves to an actual name behind the message (useful for group chats). When can't be determined, defaults to "System".
2024-03-12 23:26:45 +02:00
7ad2473f99
Add char.card Jailbreak support for Text Completion APIs
2024-03-12 23:22:29 +02:00
5efdecc825
Add new OpenAI embedding models for selection
2024-03-12 21:41:30 +02:00
44a7dd3d74
Add NomicAI for vectorization ( #1922 )
...
* Crudely add NomicAi for vectorization
* Move NomicAI to its own endpoint, properly handle API key
* Adjust clear button html
* Remove leftover nomicai http header code
* Revert changes to openai-vectors.js
* Fix UI issues
* Revert change to settings, fix UI
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
2024-03-12 21:10:25 +02:00
700c20d441
Add moment mutability notice for future generations
2024-03-12 20:45:30 +02:00
a9ec171c50
Cache parsed timestamps for quicker rendering
2024-03-12 20:29:07 +02:00
3912c67965
Skip applying translations if no locale data is loaded
2024-03-12 20:24:45 +02:00
b6c29f7129
added new langs
...
+added new lang: Arabic, Portugese, Vietnamese
+added display names for all langs
+added data-i18n= tags for translation
2024-03-12 19:03:12 +01:00
6b2374c405
Add function to write extension fields to character cards.
2024-03-12 01:49:05 +02:00
9f0c2e0ddb
Neither is this.
2024-03-11 02:56:43 +02:00
a1256d9753
This doesn't actually work.
2024-03-11 02:55:15 +02:00
d0fec68768
Extend markdown guide
2024-03-10 23:53:55 +02:00
5f246aa756
Deduplicate locale loading logic
2024-03-10 20:49:11 +02:00
c9374bce13
remove useless console.log
2024-03-09 23:04:22 +00:00
458535c7bc
Split i18n.json file
2024-03-09 23:03:51 +00:00
c69b8137d7
Reduced motion disables background transition
2024-03-10 00:55:34 +02:00
596ab89ef7
Run macro substitution before adding text to WI recursion buffer
2024-03-10 00:52:27 +02:00
62a073c51a
Merge branch 'release' into staging
2024-03-10 00:43:08 +02:00
d9ff9e796b
Add tip to AllTalk endpoint field.
2024-03-09 15:57:01 -05:00
91d6a139e5
Merge pull request #1906 from DreamGenX/dreamgen_api
...
Add support for DreamGen API.
2024-03-08 21:16:37 +02:00
a0279b636b
Remove dead code
2024-03-08 08:41:54 +02:00
2cdfda9d69
Actually use getCurrentDreamGenModelTokenizer
2024-03-08 08:40:03 +02:00
ae378789fe
Merge branch 'release' into staging
2024-03-08 08:35:19 +02:00
15eb18740e
Pass char/user names for Claude example messages converter
2024-03-08 08:31:36 +02:00
bc8d41b530
Implement suggestions
2024-03-07 17:28:38 +01:00
5c410986a4
Add support for DreamGen API.
...
API docs: https://dreamgen.com/docs/models/opus/v1
API keys: https://dreamgen.com/account/api-keys
I decided to base this on the text-completion API since it's more
flexible with SillyTavern's prompt formating capabilities.
This also means that custom context and instruct settings are required.
Will add documentation in a followup PR.
2024-03-07 12:25:48 +01:00
8036a07df4
clarified placeholder comfyui text
2024-03-06 21:34:31 -05:00
bb53fef531
Clean-up docs and leftover logs
2024-03-06 23:10:52 +02:00
9a6824f86c
Merge pull request #1886 from parsedone/patch-2
...
Fixes [BUG] STscript parser() incorrectly manages spaces
2024-03-06 23:04:10 +02:00
00a4a12d7d
Remove "Exclude Assistant suffix" option
2024-03-05 20:41:53 +02:00
3e1d44fc29
remove deprecated option + reverse proxy support in claude vision
2024-03-06 02:47:00 +10:00
de0e0dad27
he forgor oop
2024-03-05 15:33:07 +10:00
8d9175f3f2
update default settings preset
2024-03-05 15:22:16 +10:00
64d9c9dc5d
anthropic captioning
2024-03-05 07:07:38 +10:00
7bb8741cfa
fix older model naming for the new api
2024-03-05 05:50:29 +10:00
04bb882e90
implement messages api and selector for nuclaude models
2024-03-05 04:40:19 +10:00
7acd2916ec
Fix image uploading if character name contains a dot
2024-03-03 20:39:20 +02:00
c4da1e3576
Fix for stats with no chat open
2024-03-03 19:36:40 +02:00
2a5c240399
Fix for old iOS
2024-03-03 19:36:23 +02:00
b9392893dc
[FEATURE_REQUEST] Option to toggle disable instruct formatting for example dialogue insertion #1881
2024-03-03 19:12:20 +02:00
314c52fa5f
Merge pull request #1885 from parsedone/patch-1
...
Fixes [BUG] STscript /fuzzy returning wrong answer
2024-03-03 16:07:12 +02:00
975206fd06
Clean-up /fuzzy command doc comments
2024-03-03 16:04:48 +02:00
39c588f30e
Showdown: parse single underscores as italics
2024-03-03 15:26:29 +02:00
77791ae3e9
revamp creator note & spoiler hide/show
2024-03-03 18:55:16 +09:00
d217a4e32f
Fixes [BUG] STscript SlashCommandParser.parser() incorrectly manages spaces
...
Fixes bug SillyTavern#1884
Parses a command even when spaces are present in arguments
Examples that now work:
/buttons labels=["OK","I do not accept"] some text /fuzzy list=[ "red pink" , "yellow" ] threshold=" 0.6 " he yelled when the color was reddish and not pink | /echo
2024-03-03 04:09:58 +01:00
88f42132c2
Update slash-commands.js [BUG] STscript /fuzzy returning wrong answer
...
Implements fix of the bug #1883 "[BUG] STscript /fuzzy returning wrong answer".
Fix the params so tha /fuzzy detect when a "candidate" item is found (using fuzzy matching) in the text passed without argument name.
Also added optional "threshold" that allows to change the value used by Fuse in order to have stricter or looselier matching.
Also updated the parser.addCommand('fuzzy', fuzzyCallback
2024-03-03 03:43:44 +01:00
b490978142
Refactor vector models code
2024-03-02 23:16:18 +02:00
adfb9c5097
Implement TogetherAI as vectorization provider
2024-03-01 23:52:49 +01:00
Cohee
Kristian Schlikow
deffcolony
AlexVeeBee
johnbenac
DreamGenX
based
RossAscends
parsedone
Kristan Schlikow