Commit Graph

2559 Commits

Author SHA1 Message Date
Cohee d281767867 Add /caption command 2024-04-18 16:22:33 +03:00
RossAscends 75afe29f28 don't force amt_gen to model max on mancer model swap 2024-04-18 11:10:17 +09:00
Cohee 8a4b675143 Disable-able chat history and examples 2024-04-17 21:23:06 +03:00
Aisu Wata fc380fa522 fix: css `decodeStyles`: remove `</br>` tags before parsing 2024-04-17 01:15:55 -03:00
Cohee 341f02e425 Fix default classify API migration 2024-04-15 04:04:30 +03:00
Cohee f7eb57082a
Merge pull request #2090 from Dakraid/feature/zoomed-avatar-tweaks
Adjust style and add magnification to zoomed avatar
2024-04-15 00:44:27 +03:00
Cohee 4a553e1fc8 Merge branch 'release' into staging 2024-04-15 00:26:43 +03:00
Cohee 1e088ac124 Fix /proxy command to return a name 2024-04-14 21:31:59 +03:00
Cohee f5955bdd37 Throw if couldn't classify 2024-04-14 20:02:34 +03:00
Cohee 0ff5d0b5f1 Substitute macro is LLM prompt 2024-04-14 19:53:40 +03:00
Cohee 6dca8b28fe Fix talkinghead check 2024-04-14 19:46:33 +03:00
Cohee bd6fe19bf1 Merge branch 'staging' into llm-expressions 2024-04-14 19:43:34 +03:00
Cohee 607e85639c Code clean-up 2024-04-14 19:31:38 +03:00
Kristan Schlikow 835d6c71fa
Add option to toggle magnification behaviour 2024-04-14 17:00:10 +02:00
Cohee 3e60919289 Specify LLM prompt in case JSON schema is not supported 2024-04-14 17:13:54 +03:00
Cohee b02394008c Fix settings migration. Add lint rule. 2024-04-14 15:40:10 +03:00
Ondřej Sakala 5ce625fb6b added a web-search toggle for Cohere API 2024-04-14 02:25:11 +02:00
Cohee 306bff0a92 #2085 Switch to async token counters 2024-04-13 21:33:19 +03:00
Cohee 1c4bad35b2 #2085 Implement async token counting 2024-04-13 21:05:31 +03:00
Cohee ba397dd2a8 #2062 Extend unlock for MakerSuite models 2024-04-13 20:09:51 +03:00
Cohee de8339f77b Fix ESLint 2024-04-13 15:24:49 +03:00
Cohee f79f335491
Merge pull request #2078 from LenAnderson/fix-popup
Fix popup
2024-04-13 15:23:39 +03:00
kingbri 913085ba74 Expressions: Let the user know if classification failed
Send a message if the classifer fails and fallback to the default
expression.

Signed-off-by: kingbri <bdashore3@proton.me>
2024-04-13 01:29:54 -04:00
LenAnderson 278ec029f5 add missing cancelButton setting to callGenericPopup 2024-04-12 20:50:14 -04:00
LenAnderson 91558ad9ea add enter to submit on input type 2024-04-12 20:49:55 -04:00
kingbri 8c4dd6ce1e Expressions: Ignore stopping strings
Don't use stopping strings when triggering a classify generation.

Signed-off-by: kingbri <bdashore3@proton.me>
2024-04-12 09:57:09 -04:00
Cohee 9c218455c4 [chore] Run ESLint 2024-04-12 14:22:12 +03:00
Cohee d9baff45bb Fix return types. Async functions must return a Promise. 2024-04-12 14:18:59 +03:00
ThisIsPIRI 6603e33fd8 Add hideChatMessage back 2024-04-12 20:05:58 +09:00
ThisIsPIRI 208e089761 Replace hideChatMessage with hideChatMessageRange 2024-04-12 16:03:50 +09:00
kingbri bea63a2efe Expressions: Remove TalkingHead from choices
This is a sub-choice under extras.

Signed-off-by: kingbri <bdashore3@proton.me>
2024-04-12 01:59:44 -04:00
kingbri 6b656bf380 Expressions: Classify using LLM
Rather than using a separate BERT model to classify the last message,
use the LLM itself to get the classified expression label as a JSON
and set that as the current sprite. Doing this should take more information
into consideration and cut down on extra processing.

This is made possible by the use of constrained generation with JSON
schemas. Only available to TabbyAPI since it's the only backend that
supports the use of JSON schemas, but there can hopefully be a way
to use this with other backends as well.

Intercepts the generation and sets top_k = 1 (for greedy sampling)
and the json_schema to an emotion enum. Doing this also prevents
reingestion of the entire context every time a message is sent and
then asked to be classified, which doesn't compromise the chat
experience.

Signed-off-by: kingbri <bdashore3@proton.me>
2024-04-12 01:55:16 -04:00
RossAscends 626c93a1ab Merge branch 'staging' of https://github.com/Cohee1207/SillyTavern into staging 2024-04-12 08:21:18 +09:00
RossAscends 94f14340ae add background image name reporting for /bg with no args 2024-04-12 08:21:17 +09:00
Cohee 356f1f9c39 Clean-up non-character state checks 2024-04-11 23:50:01 +03:00
Cohee 123131074c Change built-in extensions template render to async 2024-04-11 23:38:44 +03:00
Cohee 16cabb38ad Fix init order in RA mods 2024-04-11 22:47:28 +03:00
Cohee 3da9fb4efe Switch to module exports 2024-04-11 22:39:42 +03:00
Cohee 369c3512c0 Add async template renderer 2024-04-11 22:36:23 +03:00
Cohee 6290dff3d9 #2065 Add option to translate text before classification 2024-04-11 22:09:05 +03:00
Cohee 210f388d7a Switch button style to use class 2024-04-11 21:33:15 +03:00
the big boss 063c81540d
IVC + support new settings and turbo model (#2067) 2024-04-11 21:29:19 +03:00
Cohee ee62f77e96
Merge pull request #2063 from kingbased/goog
Gemini system prompt support
2024-04-11 19:49:20 +03:00
Cohee d2ac782c3c Fix broken HTML and code style 2024-04-11 19:21:59 +03:00
Yokayo 0486fe0126
Bind strings to locale 2024-04-11 14:58:07 +07:00
Yokayo 40cae057a5
Bind string to locale 2024-04-11 14:55:38 +07:00
based 34bca69950 system prompt support for gemini 1.5 2024-04-11 16:38:20 +10:00
Cohee 5f6d895acf Add attribution links 2024-04-10 21:21:31 +03:00
Cohee c90105e9f6 Merge branch 'staging' into pollinations 2024-04-10 21:14:36 +03:00
Cohee 53baa7aae7 #2051 #2031 Selectable prompt converter for custom OAI type 2024-04-10 21:12:57 +03:00