Commit Graph

863 Commits

Author SHA1 Message Date
Cohee dcb98b2969 Substitute macros in TTS text before narrating 2024-04-21 01:02:49 +03:00
Cohee 366e2abb8b Move expressions LLM request setting mode listener 2024-04-19 23:01:31 +03:00
Cohee eab545cafc Error handling for Comfy request 2024-04-19 00:39:04 +03:00
Cohee 901ffa3cdc Add char and user avatar placeholders to ComfyUI workflow editor
They resolve to base64 encoded data URIs of respective avatars.
2024-04-19 00:32:38 +03:00
Cohee 16a2ac0bbe Add missing awaiters to getQueryText 2024-04-18 22:58:14 +03:00
Cohee cc1c3f173c
Merge pull request #2097 from Dakraid/feature/summarize-before-embedding
Summarize the chat messages handed to the embedding beforehand
2024-04-18 22:49:34 +03:00
Cohee 5e18b1872b Hide vector summarization unless chat vectors is enabled 2024-04-18 22:32:01 +03:00
Cohee d281767867 Add /caption command 2024-04-18 16:22:33 +03:00
Kristan Schlikow abd8acd9fc
Add experimental flask icon with title 2024-04-17 20:35:51 +02:00
Kristan Schlikow 977c1d4ac4
Add missing hr to the settings html 2024-04-17 20:35:51 +02:00
Kristan Schlikow 21b5bb5a29
Rearrange settings 2024-04-17 20:35:51 +02:00
Kristan Schlikow 10692523f0
Improve settings, add settings for prompt, sent message summarize toggle 2024-04-17 20:35:50 +02:00
Kristan Schlikow a022c9eccb
Set css class for summary dropdown in vectors 2024-04-17 20:35:50 +02:00
Kristan Schlikow 4cfd0c71cf
Add extras summarization API, fix missing substitution of placeholders 2024-04-17 20:35:49 +02:00
Kristan Schlikow a1473dedd0
Make summarization toggleable 2024-04-17 20:35:49 +02:00
Kristan Schlikow 59abee3043
Summarize the chat messages handed to the embedding beforehand 2024-04-17 20:35:48 +02:00
Cohee 341f02e425 Fix default classify API migration 2024-04-15 04:04:30 +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 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
Cohee 306bff0a92 #2085 Switch to async token counters 2024-04-13 21:33:19 +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
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
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
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 3da9fb4efe Switch to module exports 2024-04-11 22:39:42 +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 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
based 540cddf300 new turbo model 2024-04-10 14:24:43 +10:00
Cohee fc1896dcff #2047 (WIP) Refactor TTS worker to use event source 2024-04-09 17:50:27 +03:00
Cohee 235afb5d15 Fix asset title for non-extension types 2024-04-09 11:30:24 +03:00
LenAnderson b461c6f0bb use generic popups for QR editor 2024-04-08 18:43:21 -04:00
RossAscends d56722a4b6 helper text and repo link tooltip for asset list items 2024-04-09 02:48:39 +09:00
Cohee c55181f955 Fix control alignment funkiness 2024-04-08 14:55:31 +03:00
LenAnderson 63cbfda9b1 add ctrl-enter to execute from editor 2024-04-07 17:01:26 -04:00
LenAnderson 21d3a7dc3e add tab size setting to QR editor 2024-04-07 17:01:02 -04:00
LenAnderson 3ed0564d73 add default value to qr editor wrap setting 2024-04-07 16:59:50 -04:00
Wolfsblvt e26c7827bc Fallback expression reset if custom expression deleted 2024-04-07 06:26:48 +02:00
Wolfsblvt 2ffb44b4e1 Add extension setting for fallback expression 2024-04-07 06:12:52 +02:00
Cohee 7cedce01a8 Merge branch 'release' into staging 2024-04-06 15:29:22 +03:00
johnbenac 3b6c32113f
added await to tts to properly catch the error on this async function 2024-04-05 18:57:51 -04:00
johnbenac 6cf897219e
Added toastr messages to tts index file 2024-04-05 18:41:36 -04:00