266752bf93
Fix new character highlight
2024-11-04 00:41:59 +02:00
77be125a99
NanoGPT: Add to image generation extension
2024-11-03 20:37:30 +02:00
649c3911eb
Add shouldRegister arg to /tools-register
2024-11-03 19:11:07 +02:00
fe469745b3
Merge pull request #3037 from yar3333/release
...
Remove embedded images before send text to TTS
2024-11-03 19:02:44 +02:00
52a4c9202d
Update public/scripts/extensions/tts/index.js
...
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
2024-11-03 19:57:33 +03:00
8b32ee9e80
Remove embedded images before send text to TTS
2024-11-02 20:25:25 +03:00
8c3ac0ac5a
Fix instruct macros not using a proper enabled field
2024-11-02 16:34:21 +02:00
cfd1545b8a
Merge pull request #3036 from procule/update-token-probabilities
...
Enhancement: Token Probabilities viewer with dynamic prefix adjustment via Ctrl-click
2024-11-02 16:25:20 +02:00
237381ac3d
Merge pull request #3035 from SillyTavern/macro-1.5
...
Totally not a new macro engine
2024-11-02 15:43:06 +02:00
48c3e81f42
DRY
2024-11-02 13:22:41 +02:00
293d6ff60d
Run mutating variable macros first
2024-11-02 12:53:44 +02:00
abf7b90135
Enhance Token Probabilities viewer with selective reroll functionality and text extraction helper
...
- Updated onPrefixClicked() to add Ctrl-click functionality:
- Default click rerolls the entire prefix text to continue the generation.
- Ctrl-click rerolls only the text before the clicked word, allowing users to more precisely control generation output.
- Introduced getTextBeforeClickedWord() helper function:
- Extracts the text before a clicked word based on click coordinates, enhancing control over prefix selection.
- Provides a fallback to return the entire span text if word extraction is not possible.
- Updated function documentation to clarify new behaviors and helper purpose.
This change allows users to reset the prefix at a certain point if needed, adding flexibility to the generation process and enabling more intentional selection of alternatives.
2024-11-02 01:49:37 -04:00
48d8e6e2c3
Port #3031 onto new engine
2024-11-02 00:55:34 +02:00
5c90c8b1f6
Add post-process fn to evaluation
2024-11-02 00:44:12 +02:00
8f373cf1dc
Macros: refactor with a single replace point
2024-11-01 21:47:25 +02:00
b837c482fc
Merge pull request #3029 from P3il4/staging
...
Optimize chat manager logic
2024-11-01 20:17:29 +02:00
4f6c5522bc
Independent chat management content scroll
2024-11-01 20:16:51 +02:00
07feccbe35
koboldcpp: parse logprobs
2024-11-01 11:38:31 +02:00
8c568bfa13
Merge branch 'staging' into optimize-chat-manager
2024-10-31 21:05:36 +02:00
5fe1bc46e6
Fix jquery plugins typedef
2024-10-31 21:05:22 +02:00
a52129392e
Align chat block items
2024-10-31 20:56:07 +02:00
c303e27f62
Set search type to the input
2024-10-31 20:51:57 +02:00
c7f94c6c14
Adjust doc link
2024-10-31 20:51:10 +02:00
a8ff518b65
Add a space to message counter
2024-10-31 20:50:22 +02:00
47b7745ceb
Extend message preview length
2024-10-31 20:47:31 +02:00
e0e60a1d00
Fix incorrect message counter
2024-10-31 20:07:23 +02:00
6e36b77f1a
Remove TAI artifact
2024-10-31 19:57:29 +02:00
547c4f6757
Fix sorting and selected highlight
2024-10-31 19:54:24 +02:00
f4ef324203
Merge pull request #3024 from dylan1951/add-nano-gpt-provider
...
Add NanoGPT chat completions provider
2024-10-31 19:30:24 +02:00
2a451cf6a1
Add logo img
2024-10-31 19:29:43 +02:00
30e9e90b38
optimize chat manager logic
2024-10-31 17:48:58 +03:00
4babf322c1
Fix model restoration on load
2024-10-30 02:09:28 +02:00
f5f11eebb2
Support auto-connect
2024-10-30 02:02:56 +02:00
085d852b57
Trigger inputs
2024-10-30 01:52:53 +02:00
5ee0a6ec30
Support unlocked context size
2024-10-30 01:50:31 +02:00
e7522bba76
Populate model list from models endpoint
2024-10-29 19:38:46 +13:00
b6c4b3cdd2
Merge branch 'release' into staging
2024-10-28 14:22:39 +00:00
17b7f17676
Fix auto-continue with stream aborting
...
Closes #3021
2024-10-28 14:22:19 +00:00
00f0f755fc
Support comma-separated list of llama.cpp sequence breakers #3026
2024-10-28 11:44:26 +00:00
542f77aeb8
Safe sequence breakers parse
2024-10-28 11:39:59 +00:00
08d177e7ba
Don't auto-swipe on aborted stream
2024-10-28 11:31:37 +00:00
ef3cb73477
Don't auto-swipe on aborted stream
2024-10-28 11:31:15 +00:00
2030c2c711
Fix auto-continue with stream aborting
...
Closes #3021
2024-10-28 11:14:35 +02:00
517b140911
Localize only the moment instance
2024-10-28 11:07:39 +02:00
9493d05f2c
Localize only the moment instance
2024-10-28 11:01:48 +02:00
ebd6377d5d
Merge pull request #3023 from bal-spec/patch-2
...
Update azure.js
2024-10-28 10:18:19 +02:00
9cc67ae43f
Merge pull request #3017 from Beinsezii/lcpp-dry-fix
...
llama.cpp Enable dry w/ array convert
2024-10-28 10:16:34 +02:00
135639642b
Update azure.js
...
Change Azure TTS audio format from ogg-48khz-16bit-mono-opus to webm-24khz-16bit-mono-opus because this works with WebKit-based browsers so brings Azure TTS to iOS, iPadOS and Safari on macOS.
2024-10-27 19:56:07 -07:00
ace2902cb8
llama.cpp Enable dry w/ array convert
...
The new PR that was merged needs an array instead of a str
https://github.com/ggerganov/llama.cpp/pull/9702
2024-10-26 16:07:07 -07:00
5848806e6a
Merge branch 'release' into staging
2024-10-26 21:40:30 +03:00
Cohee
Yaroslav Sivakov
Olivier Gagnon
p3il4
dylan
bal-spec
Beinsezii