d024d7c700
Allow max value for per-entry depth
2024-02-27 23:34:07 +02:00
149a65cf62
migrate model name in old presets to new naming scheme
2024-02-27 02:23:07 +10:00
f962ad5c02
Add OpenRouter as a text completion source
2024-02-25 22:47:07 +02:00
670f08fad2
Update group-chats.js
...
After deleting a group chat, the oldest chat became active. I've fixed it so that the most recent chat becomes active instead.
2024-02-25 21:11:56 +04:00
9e5505a7d4
Autocomplete for WI automation IDs
2024-02-25 03:54:40 +02:00
fc289126fa
Add event type for text completion generation request settings ready
2024-02-24 21:45:33 +02:00
d5bf9fc28c
Non-streaming logprobs for Aphrodite
2024-02-24 20:53:23 +02:00
d140b8d5be
Parse non-streaming tabby logprobs
2024-02-24 20:10:53 +02:00
3cedf64f66
Add autocomplete for WI inclusion groups
2024-02-24 19:04:44 +02:00
3441667336
#1853 Add WI/Script link by entry automation id
2024-02-24 17:22:51 +02:00
7b8ac8f4c4
Properly use vector insert setting
2024-02-24 15:57:26 +02:00
8848818d67
Fix dynatemp neutralization
2024-02-24 15:32:12 +02:00
299bd9d563
Merge branch 'staging' into llamacpp-sampler-order
2024-02-24 15:10:58 +02:00
13aebc623a
Merge pull request #1854 from deciare/llamacpp-probs
...
Request and display token probabilities from llama.cpp backend
2024-02-24 15:06:28 +02:00
eaadfea639
Extend debounce duration of logprobs renderer
2024-02-24 15:03:57 +02:00
9287ff18de
Fix for non-streaming
2024-02-24 14:50:06 +02:00
dab9bbb514
Merge pull request #1844 from infermaticAI/InfermaticAI
...
Add InfermaticAI as a text completion source
2024-02-24 14:28:09 +02:00
445cbda02f
If token probability is a logarithm it'll be < 0
...
No need to read settings to find out if llama.cpp backend is in use...
2024-02-24 00:13:33 -05:00
9eba076ae4
Sampler order for llama.cpp server backend
2024-02-23 23:01:04 -05:00
936fbac6c5
Merge remote-tracking branch 'origin/staging' into llamacpp-probs
2024-02-23 17:45:54 -05:00
737a0bd3ae
Fix purge extras and mistral vectors
2024-02-23 22:37:00 +02:00
9b34ac1bde
Merge pull request #1852 from berbant/staging
...
Display TranslateProvider link
2024-02-23 21:43:59 +02:00
cb536a7611
Save a list of safe to export secret keys
2024-02-23 21:41:54 +02:00
82c5042bad
Prevent extra loop iterations on buffer init
2024-02-23 21:23:44 +02:00
4baefeba68
Extend per-entry scan depth limit, add warnings on overflow
2024-02-23 21:18:40 +02:00
344b9eedbc
Request token probabilities from llama.cpp backend
...
llama.cpp server token probabilities are given as values ranging from
0 to 1 instead of as logarithms.
2024-02-23 14:01:46 -05:00
eb89337f51
Update index.js
2024-02-22 23:49:47 +04:00
c9f0d61f19
#1851 Substitute macros in new example chat
2024-02-22 18:45:50 +02:00
f569424f3e
Merge branch 'staging' into InfermaticAI
2024-02-22 08:32:10 -06:00
ece3b2a7c1
Fix Chat Completions status check on settings loading if another API is selected
2024-02-22 04:36:06 +02:00
0ccdfe4bb7
Fix duped line
2024-02-22 02:45:35 +02:00
40aa971d11
Merge branch 'staging' into sampler-order-ooba
2024-02-22 02:44:32 +02:00
0c1cf9ff2e
Send sampler priority as array
2024-02-21 00:53:54 +02:00
f0141b4dd1
Update slash-commands.js
2024-02-20 16:57:00 +02:00
095cd873de
Update slash-commands.js
...
added the word "persona" to the /sync description to make it easier for users to find.
2024-02-20 16:48:43 +04:00
8ba9b5c38b
Merge branch 'staging' into sampler-order-ooba
2024-02-20 02:32:33 +02:00
8e66a14e37
Add hints to doc strings about additional command prompts
2024-02-20 02:29:14 +02:00
32ee58e5e6
fix kcpp order reset
2024-02-19 18:12:56 -06:00
550d8483cc
Extend impersonate/continue/regenerate with possible custom prompts
...
- Use custom prompt provided via slash command arguments (similar to /sysgen and others)
- Use written text from textbox, if the popout menu actions are clicked
2024-02-19 22:23:58 +01:00
2e00a1baaf
[FEATURE_REQUEST] Can the unlocked max context size for OpenAI completion be increased from 102k to 200k for example? #1842
2024-02-19 19:37:18 +02:00
030806bf1e
Merge remote-tracking branch 'origin/staging' into InfermaticAI
2024-02-19 10:14:06 -06:00
3c2113a6e7
Add ability to preserve file names when loading from assets downloader
2024-02-19 00:17:23 +02:00
29b971a986
Merge branch 'staging' into slash-fix-bleed
2024-02-16 20:48:32 +02:00
c06fe6abfc
Add character asset type
2024-02-16 20:42:56 +02:00
a8cd6c9fe7
Allow finding characters in slash commands by exact PNG name
2024-02-16 20:24:47 +02:00
8075e4cd1e
Changes
2024-02-16 09:07:06 -06:00
b5887960b6
Merge branch 'release' into InfermaticAI
2024-02-16 08:53:04 -06:00
0da0d490c7
#1796 Attempt to fix alltalk on remote servers
2024-02-14 19:44:47 +02:00
6ab918605e
Allow single quotes in generated SD prompts
2024-02-14 15:39:56 +02:00
e3102bb26f
#1823 Add -1 as min value for top k
2024-02-14 01:45:07 +02:00
8d4c4c1945
Only snap resolution if pixel counts change
2024-02-13 11:40:37 +02:00
b8387df15e
#1826 Allow snapping to known resolutions for face/bg generations
2024-02-12 17:28:39 +02:00
9d713825c2
#1827 Consolidate {{group}} macro behavior
2024-02-12 16:23:01 +02:00
0480488127
Merge pull request #1815 from bdashore3/staging
...
Fix zen slider values
2024-02-11 19:27:37 +02:00
33d93b9761
#1813 Fix squash system messages
2024-02-11 15:56:48 +02:00
6e10c43c63
Zen Sliders: Add off values for dynatemp and smoothing factor
...
Off for dynatemp is 1.0, smoothing factor is 0.0
Signed-off-by: kingbri <bdashore3@proton.me>
2024-02-11 01:32:32 -05:00
9fed7ed742
Make the neutralize option turn off quad sampling
2024-02-10 17:57:00 -06:00
70deb11d27
implement jank js + drag n drop sampler priority
2024-02-10 16:32:46 -06:00
818029288e
Remove sending it if it's Aphrodite or TabbyAPI
2024-02-10 15:22:24 -06:00
cbea5bf996
UI Theme import/export
2024-02-10 23:12:16 +02:00
2065f95edc
Sampler priority support
2024-02-10 14:57:41 -06:00
df97f5364b
Regex import/export
2024-02-10 21:57:22 +02:00
18f84979f2
Use SSE streaming for MakerSuite
2024-02-10 02:43:50 +02:00
cab6f90519
stop named args from nested commands bleeding into parent
2024-02-09 22:49:38 +00:00
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
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
44a3bb8ec7
#1777 Add await argument to /trigger command
2024-02-08 00:20:36 +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
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
21fb143718
Add API key
2024-02-06 20:00:16 -08:00
b158a86c25
Firefox copium for expression images
2024-02-05 02:21:20 +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
17a783f9c6
Merge pull request #1780 from Spacellary/patch-1
...
(Small) Add Handling for Dangling Characters in "trimToEndSentence" - utils.js
2024-02-02 21:34:51 +02:00
4649c806e0
Use regex to match whitespace
2024-02-02 21:30:32 +02:00
db82b5bb3d
Merge branch 'staging' into slash-escapes
2024-02-02 18:13:19 +00:00
6d0d92aaff
Add grammar and dynatemp for aphrodite
2024-02-02 20:06:46 +02:00
e4025cb413
Add Handling for Dangling Characters in "trimToEndSentence" - utils.js
...
New: Considered the presence of whitespace or newline characters preceding the punctuation for accurate trimming.
2024-02-02 13:42:31 -03:00
30213c8430
Merge remote-tracking branch 'upstream/staging' into quad-sample
2024-02-01 22:27:38 -05:00
a746077a1e
Sort personas by name.
2024-02-02 04:07:51 +02:00
10d78f9a25
Aphrodite tokenizer
2024-02-02 01:09:03 +02:00
7618133d6d
unrestricted amount_gen for madlab mode
2024-02-01 15:24:35 +09:00
ed875ec77d
Update index.js
...
Added new translateProvider: Lingva Translate
2024-01-31 22:42:28 +04:00
8d9a373292
Merge remote-tracking branch 'upstream/staging' into quad-sample
2024-01-31 11:08:13 -05:00
872418757c
#1761 Personas grid view (slight return)
2024-01-31 12:13:01 +02:00
fa73c523f0
Persist current page on persona actions
2024-01-31 11:01:50 +02:00
da68d35ca5
Remove Noisy Sampling
...
Leaves DynaTemp Exponent and Quadratic Sampling.
2024-01-30 21:50:50 -05:00
766cd49953
Merge remote-tracking branch 'upstream/staging' into quad-sample
2024-01-30 21:20:37 -05:00
c01217ac76
Clean-up styles and handlers
2024-01-30 20:16:48 +02:00
4542c66664
#1761 Persona management overhaul
2024-01-30 19:12:56 +02:00
079ab7db07
#1758 Mute character in group chat but keep character card
2024-01-30 12:27:31 +02:00
9c33a04806
Merge remote-tracking branch 'upstream/staging' into quad-sample
2024-01-29 18:38:17 -05:00
da7b435b7c
Merge pull request #1751 from kingbased/proxypreset
...
Reverse proxy presets
2024-01-29 22:09:33 +02:00
b4646da187
Fix logprobs parser on NovelAI non-streaming
2024-01-29 11:13:48 +02:00
d1f41a4191
Merge branch 'staging' into quad-sample
2024-01-28 19:20:20 -05:00
5f1e290bda
Disallow multiple {{original}} macro substitutions
2024-01-29 00:58:29 +02:00
a9464daffa
Merge branch 'staging' into macro-separation
2024-01-29 00:51:06 +02:00
92aae0da04
Enter the Kalo Zone
2024-01-28 15:14:21 -05:00
f732b8ae4c
Add optional module to vectors manifest
2024-01-27 23:09:41 +02:00
71f47588cd
Pass macro variables in to evaluateMacros
...
This doesn't cover *all* the variables yet, just the ones that were
previously passed in as arguments. I'll expand this later to separate
the macro parsing from the execution of the functions themselves.
2024-01-27 13:20:44 -05:00
ee7ee9f60a
merged mistral proxy support
2024-01-27 06:26:23 +10:00
aa976d0de2
implemented proxy preset manager
2024-01-27 06:21:00 +10:00
2cdf928fc7
unescape args before calling callback
2024-01-26 18:58:44 +00:00
4d534e3042
[BUG] Incorrect context size for gpt-4-turbo-0125 #1748
2024-01-26 18:51:20 +02:00
8af3939f09
fix: logprobs for Aphrodite
...
Since Aphrodite follows the same logprobs style as ooba, we can enable it easily.
2024-01-26 07:15:39 +00:00
3cf01e765a
#1741 Filter non-unique chunks
2024-01-26 04:18:15 +02:00
1647e5ae49
Merge pull request #1734 from khanonnie/alternative-tokens
...
Implement Token Probabilities UI panel using logprobs
2024-01-26 03:39:25 +02:00
60044c18a4
Implement Token Probabilities UI using logprobs
2024-01-25 18:34:46 -06:00
40476dca3b
New OAI models
2024-01-25 22:01:02 +02:00
515e3859ec
Merge pull request #1689 from h-a-s-k/staging
...
Group chat fixes
2024-01-25 20:51:55 +02:00
6ff998816d
#1728 Missed one
2024-01-25 03:28:30 +02:00
e627e89722
Merge pull request #1726 from Technologicat/tooltips-vol1
...
add/improve tooltips
2024-01-24 22:50:02 +02:00
3f3529ef89
#1630 Add min/max depth for prompt/display regex scripts.
2024-01-24 22:48:58 +02:00
55984a59bb
#1728 Allow zeros in {{pipe}} macro
2024-01-24 21:19:29 +02:00
e537def312
Add return value to /sd command and quiet flag
2024-01-24 20:15:10 +02:00
0683d7a538
Merge branch 'staging' into tooltips-vol1
2024-01-24 17:05:09 +02:00
532c86b051
Merge pull request #1737 from Technologicat/vectordb-with-extras
...
Initial support for Extras vectorizer, for Vector Storage
2024-01-24 17:01:54 +02:00
0ad756c923
Add check for "embeddings" module.
2024-01-24 16:51:57 +02:00
b4e7ee05e6
Remove regex replace strategy selector
2024-01-24 16:10:50 +02:00
a1c7e2918b
Merge branch 'staging' into vectordb-with-extras
2024-01-24 15:48:01 +02:00
4823bcf4ff
Add option to forbid external images
2024-01-24 15:47:54 +02:00
8b43535352
Initial support for Extras vectorizer, for Vector Storage
2024-01-24 15:16:55 +02:00
f29f934c6b
Progress
2024-01-24 06:59:27 -06:00
d5a2f5d9fc
Fix /rand returning zero #1728
2024-01-24 14:04:45 +02:00
e329bd8497
Fix JSdoc comments
2024-01-24 13:07:56 +02:00
c76cc20a7d
Fix default value for new fields
2024-01-24 13:00:43 +02:00
9cf29b3651
Breaking - Count scan depth as individual messages, not pairs.
2024-01-24 00:07:22 +02:00
8a69f63044
#1727 Add per entry WI setting overrides
2024-01-23 22:44:20 +02:00
107fe85543
Add OpenRouter filtered reason display
2024-01-23 00:10:53 +02:00
6a03980db6
add/improve tooltips
2024-01-22 15:56:12 +02:00
814ed49c31
#1719 Clear text nodes in rendered formulas
2024-01-21 17:27:09 +02:00
e2becdf7a9
Add typedefs for TTS audioJob
2024-01-21 15:19:13 +02:00
f3fc3f12a7
Merge pull request #1716 from Tony-sama/staging
...
VRM extension support
2024-01-21 15:12:44 +02:00
ffbf35e468
Update index.js
2024-01-21 15:11:47 +02:00
b2509f8de4
Rethrow AllTalk init error
2024-01-20 20:44:11 +02:00
570d5a30bd
[skip ci] Lint fix
2024-01-20 20:40:40 +02:00
2846d0fd58
#1720 Fetch no-cache images when uploading
2024-01-20 19:48:56 +02:00
b741f32ae9
Clean comments
2024-01-19 09:34:32 +01:00
5b201bce7a
Merge branch 'SillyTavern:staging' into staging
2024-01-19 09:26:28 +01:00
0b322c0e3d
Add repetition penalty control for OpenRouter
2024-01-18 23:55:09 +02:00
9ce2771dad
make finalizeInit blocking just to be sure
2024-01-18 20:47:46 +00:00
65d9c944d8
await init and wait for APP_READY
2024-01-18 20:43:31 +00:00
8874ffffc5
Adjust UI label.
...
Group members are peacenik
2024-01-18 18:23:00 +02:00
4f55824d7f
QR auto-execute on group member draft
2024-01-18 18:08:38 +02:00
b8445eb2cd
Add slash commands for instruct and context
2024-01-18 17:24:07 +02:00
f966c398ef
Increase preset command timeouts
2024-01-18 16:36:26 +02:00
7d34ed56e6
#1712 Add authorization only if Extras key is set
2024-01-18 16:33:02 +02:00
d19ba9a68c
Fix format
2024-01-18 02:36:18 +02:00
05d292e055
Merge branch 'staging' into erew123/release
2024-01-18 02:35:26 +02:00
9aa4b50a86
Merge pull request #1709 from LenAnderson/qr-autoexec-queue
...
queue all auto-executes until APP_READY
2024-01-18 01:11:19 +02:00
3af2164187
AllTalk Updates
...
Streaming passed URL to global ST audio.
Localstorage removed for saving TTS elements.
Styles stored in CSS
Duplicate checks on fetchresponse removed.
2024-01-17 21:55:24 +00:00
f293c20e9f
Merge branch 'SillyTavern:release' into release
2024-01-17 21:28:08 +00:00
12a40c25a0
fix QR settings UI out of sync after update via API
2024-01-17 20:41:59 +00:00
6fe17a1bed
queue all auto-executes until APP_READY
2024-01-17 20:32:25 +00:00
617cabd7b5
Merge pull request #1707 from LenAnderson/qr-fixes
...
Several QR fixes
2024-01-17 11:12:38 +02:00
d38700ca08
Merge pull request #1706 from LenAnderson/vars-fix-addvar-array
...
fix addvar on array using setGlobalVariable
2024-01-17 11:11:17 +02:00
1a50c9f976
use isTrueBoolean on all bools
2024-01-16 22:40:40 +00:00
9f4ae351db
fix bools in /qr-update
2024-01-16 22:37:12 +00:00
acaae1b973
fix type in helpstring
2024-01-16 22:36:55 +00:00
d1966d9d5f
fix addvar on array using setGlobalVariable
2024-01-16 22:20:46 +00:00
7af43023b1
init quick replies immediately
2024-01-16 21:04:25 +00:00
a8a993c5ba
Update tts processing to keep track of character for VRM lip sync.
2024-01-16 04:54:14 +01:00
baab494ed4
Merge branch 'SillyTavern:staging' into staging
2024-01-16 00:15:13 +01:00
5cb4dbc280
Trim TG types after split
2024-01-15 20:45:21 +02:00
22e605168b
Properly reset seed with neutralize samplers
2024-01-15 20:44:07 +02:00
25a695c783
Await QR auto-execution
2024-01-15 19:30:14 +02:00
d72b5125ac
Merge branch 'SillyTavern:release' into release
2024-01-15 14:51:47 +00:00
0751d746db
Merge pull request #1683 from Technologicat/talkinghead-configurable
...
talkinghead: per-character configs
2024-01-14 19:00:02 +02:00
c6487fa9cb
make sampler nuke button work with zensliders
2024-01-14 18:33:40 +09:00
80b39bdac1
add neutralize samplers button for text completion slider panel
2024-01-14 18:07:43 +09:00
44bd57f763
filter ooba-only samplers out of non-ooba text completion slider panels
2024-01-14 17:26:22 +09:00
017ac8a515
Added vrm tts lip sync call
2024-01-14 04:26:06 +01:00
b78350cc8e
AllTalk initial commit
...
AllTalk TTS initial commit from https://github.com/erew123/alltalk_tts
ST index.js is updated to have "Pass Asterisks to TTS Engine" which allows AllTalk to split text as character/narrator voices. This setting has been left disabled as standard, so wont affect other TTS engines. The setting will save along with other settings on the page (if checked).
2024-01-13 19:43:38 +00:00
074cc13e60
Fix group chat example messages not including character name
2024-01-13 14:34:17 -03:00
9354697753
Actually call them example chats
2024-01-13 13:06:51 -03:00
4fe13fab8e
Customizable /gen instruct name
2024-01-12 19:16:42 +02:00
b528520693
read and send talkinghead per-character configs
2024-01-12 18:26:14 +02:00
f4c7fff8c0
Mistral API got fixed
2024-01-12 18:17:43 +02:00
e33ac6a78a
Add min_p and top_a for OpenRouter
2024-01-12 17:15:13 +02:00
Cohee
based
berbant
Deciare
NWilson
Sneha C
kalomaze
Wolfsblvt
kingbri
LenAnderson
EX3-0
oobabooga
anon
Juha Jeronen
RossAscends
Spacellary
Alexander Abushady
valadaptive
AlpinDale
khanon
Tony Ribeiro
Tony Ribeiro
erew123
h-a-s-k