Commit Graph

1773 Commits

Author SHA1 Message Date
Cohee
249cb7777c Merge branch 'staging' into welcome-screen 2025-05-13 19:52:40 +03:00
Cohee
7659dfb85c Remove reasoning from raw builder summaries 2025-05-13 00:59:27 +03:00
Cohee
637e9d5469 Set any char as assistant. Rework welcome prompt 2025-05-12 20:50:17 +03:00
Cohee
420d568cd3 Pollinations - Text (#3985)
* [wip] Pollinations for text

* Implement generate API request

* Determine Pollinations model tools via models list

* Add Pollinations option to /model command

* Add Pollinations support to caption

* Update link to pollinations site

* Fix type errors in openai.js

* Fix API connection test to use AbortController for request cancellation

* Remove hard coded list of pollinations vision models

* Remove openai-audio from captioning models
2025-05-11 20:14:11 +03:00
Cohee
aef005007f Do not remove data URI prefix from llamacpp caption requests 2025-05-09 23:23:34 +03:00
Cohee
8a4da487dd llamacpp: use generic CC endpoint for captioning 2025-05-09 22:33:25 +03:00
Cohee
fa8ea7c60d mistral-medium-2505 2025-05-07 20:09:56 +03:00
sirius422
edb9702055 Add support for gemini-2.5-pro-preview-05-06 2025-05-07 00:29:26 +08:00
Cohee
b25322b844 Merge pull request #3933 from SillyTavern/feat/ext-installer-branch
Add branch selection on extension installer
2025-05-04 12:35:05 +03:00
Cohee
a122109e0c Add new model option 'embed-v4.0' to Cohere vectorization settings
Closes #3951
2025-05-04 12:26:44 +03:00
Cohee
310b0f30cd Add branch selection on extension installer
Closes #3865
2025-04-28 22:53:22 +03:00
Cohee
05daddb60c Fix KoboldCpp saved vectors retrieval 2025-04-27 23:18:39 +03:00
Cohee
0f8b610454 Prettify captioning model redirects 2025-04-27 20:36:14 +03:00
cloak1505
4599797baf Revert responsive Google models per Cohee's executive order
I was wrong on a few models. At least Gemini still fits on a 1440p monitor.
2025-04-26 20:04:50 -05:00
cloak1505
fc09be75a6 Almost done with Google pruning
* Put back 1.5-latest
* Put back missing flash 002 (same deal about safetySettings like pro 001 vs 002)
* Remove dead models and gemma from BLOCK_NONE check
2025-04-26 17:54:34 -05:00
cloak1505
af64ac001a Update caption_multimodal_model
And fix optgroup typo
2025-04-26 14:33:47 -05:00
cloak1505
28d42e5200 Prune Google models 2025-04-26 11:39:44 -05:00
Cohee
0520f3ccf4 Fix gpt-4o-mini snapshots 2025-04-22 23:28:49 +03:00
Cohee
586ce36167 Merge pull request #3868 from YunZLu/staging
Fix Edge Browser TTS Compatibility
2025-04-19 01:15:14 +03:00
Cohee
9d8283e4c7 Fix assets_menu selector 2025-04-18 22:42:12 +03:00
Cohee
352a8c3c97 Fix TTS provider settings
Fixes #3877
2025-04-18 22:03:17 +03:00
Daryl
e0b7c9ef4c Fixed image viewing capabilities and added option for caption extension 2025-04-17 17:34:35 -04:00
YunZLu
41c2dd16f2 fix(eslint): resolve no-trailing-spaces error 2025-04-18 04:12:37 +08:00
YunZLu
d7cc70256a cleaned all redundant comments 2025-04-18 03:58:04 +08:00
YunZLu
d511875db9 Fix Edge Browser TTS Compatibility
Edge-compatible fallback for empty Web Speech voice lists
2025-04-17 19:46:49 +08:00
Cohee
7b2f1f7c7a Add o3 and o4-mini 2025-04-16 23:12:40 +03:00
pl752
07fb92b37d Added vector secondary url placeholder example 2025-04-16 17:39:29 +05:00
pl752
f8bccb472f Adjusted naming and validation 2025-04-16 17:34:58 +05:00
pl752
bfe50403af Forgot semicolons 2025-04-16 16:45:01 +05:00
pl752
5cf3198da1 Added option to use secondary API URL in vector extension 2025-04-16 16:04:33 +05:00
Cohee
36e3627705 gpt-4.1 2025-04-14 20:54:18 +03:00
Cohee
78bda9954d Increase maximum injection depth and WI order (#3800) 2025-04-13 21:31:57 +03:00
Cohee
91fc50b82d Merge branch 'staging' into gork-ai 2025-04-11 21:15:54 +03:00
Cohee
0c4c86ef06 Add xAI for image generation extension 2025-04-11 20:32:06 +03:00
bmen25124
fc5e0563ba Added ability to override request payload 2025-04-11 19:07:00 +03:00
Cohee
17cdc78a91 Add xAI for image captioning 2025-04-11 19:05:03 +03:00
bmen25124
4736f533a5 Added proxy support to ChatCompletionService 2025-04-11 19:04:32 +03:00
Cohee
df7c2226f6 Fix Gemini captioning 2025-04-06 13:31:16 +03:00
Cohee
70fe5b6e01 Add Gemini embedding model for vector storage 2025-04-01 21:42:26 +03:00
Cohee
80e821d12d Add support for KoboldCpp embeddings in Vector Storage (#3795)
* Add support for KoboldCpp embeddings in vector processing

* Add validation for KoboldCpp embeddings to handle empty data

* Improve toast handling
2025-04-01 21:21:29 +03:00
bmen25124
50b2eeb61f Added api check for ConnectionManagerRequestService.handleDropdown 2025-04-01 04:39:41 +03:00
Cohee
65a6e428d1 Improve tilde code blocks in message formatting and TTS processing 2025-03-30 13:25:15 +03:00
Cohee
68c572f2eb Merge branch 'staging' into custom_request_stop_string_cleanup 2025-03-27 22:41:11 +02:00
equal-l2
2a31f6af2d Remove Block Entropy references
Block Entropy shut down their service at the end of 2024.
2025-03-28 00:47:30 +09:00
bmen25124
972b1e5fa7 Fixed variable naming, better jsdoc 2025-03-26 23:30:09 +03:00
bmen25124
a7d48b1aed Added overridable instruct settings, removed macro override 2025-03-26 23:21:48 +03:00
Cohee
f4eb32c71c Merge pull request #3760 from SillyTavern/feat/expressions-none-default-option
Add 'none' expression classifier API option and set as default
2025-03-26 11:10:13 +02:00
Azariel Del Carmen
b96bed7240 chore: make layer updates exportable 2025-03-25 20:09:48 -05:00
Wolfsblvt
cbfc1f7a0e Add 'none' classifier API option and set as default
Introduces a no-op API selection to disable expression classification
Shows warnings when no valid API is selected to prevent silent failures
Updates migration logic and settings UI to use new default value

This allows users to explicitly opt-out of automatic expression detection
while maintaining backwards compatibility with existing configurations
2025-03-26 01:50:26 +01:00
Cohee
264d77414a Gemini 2.5 Pro 2025-03-25 21:21:23 +02:00