Commit Graph

9949 Commits

Author SHA1 Message Date
1cb9287684 Vectors WebLLM (#3631)
* Add WebLLM support for vectorization

* Load models when WebLLM extension installed

* Consistency updated

* Move checkWebLlm to initEngine

* Refactor vector request handling to use getAdditionalArgs

* Add error handling for unsupported WebLLM extension

* Add prefix to error causes
2025-03-09 00:51:44 +02:00
0ea64050ff Parse reasoning in multi-swipe swipes 2025-03-08 23:06:56 +02:00
d0068ecbab Clean-up swipe_info of multi-swipes 2025-03-08 22:48:42 +02:00
ca14352972 Fix syncMesToSwipe checks
Ported from #3634
2025-03-08 22:33:26 +02:00
50a0f41736 Sync mes to swipe on stream finished 2025-03-08 22:29:18 +02:00
7e3946c152 Add tools parameter to AI21 request 2025-03-08 22:26:32 +02:00
edabd1128b Add tags in toShallow
Closes #3638
2025-03-08 22:04:49 +02:00
f38898e03f Merge pull request #3640 from Succubyss/patch-7
Re-enable logit bias and stop strings for 4.5
2025-03-08 21:56:11 +02:00
98f92f6270 Fix syntax of model name check 2025-03-08 21:50:39 +02:00
5d275998ed Merge branch 'staging' into patch-7 2025-03-08 21:46:38 +02:00
c3b5382882 Re-enable logit bias and stop strings for 4.5 2025-03-08 12:57:11 -06:00
de0e65fe13 Enable tool calling for ai21 2025-03-08 17:25:37 +02:00
ff5835278b Add Jamba 1.6 models
Closes #3633
2025-03-08 15:16:49 +02:00
980ed76cc3 Fix auto-parsing of continue from reasoning
Continues #3606
2025-03-08 12:58:26 +02:00
91fe2841e3 Fix reasoning rendering on auto-save message 2025-03-08 05:52:11 +01:00
b813bcad8a Merge pull request #3629 from kingbri1/staging
Make mesExamples macros consistent
2025-03-07 22:55:31 +02:00
0423cb7ad3 Do not apply instruct formatting if on CC 2025-03-07 22:53:30 +02:00
5ff4c457c0 Merge pull request #3630 from cloak1505/staging
Update OpenRouter providers
2025-03-07 22:15:39 +02:00
c593c9fe2a Update OpenRouter providers 2025-03-07 13:47:12 -06:00
e476063f32 Macros: Update mesExamplesRaw documentation
Works as a normal macro and not just with story string.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
2025-03-07 13:08:30 -05:00
95e0be7e9e MesExamples: Make macros consistent with story string
mesExamples in the story string is formatted while mesExamplesRaw
is unformatted. However mesExamples when used as a normal macro
is unformatted. This causes an inconsistency in usage which is now
corrected.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
2025-03-07 13:03:44 -05:00
a9c2af19e3 Add null checks for querySelector stscript_autocomplete_width
Closes #3582
2025-03-07 11:32:58 +00:00
1a52314812 MistalAI: Add custom stop strings
Closes #3627
2025-03-07 11:29:14 +00:00
7de516e5e7 Merge pull request #3621 from Sorro123/staging
Add gemini tools support.
2025-03-07 00:23:17 +02:00
381956652b Remove tools assignment 2025-03-07 00:22:45 +02:00
7fd0f3e2bf Merge branch 'staging' into geminiStructured 2025-03-07 00:22:18 +02:00
bcb2096020 Merge pull request #3625 from SillyTavern/gemini-search
Add backend-provided websearch connectors for OpenRouter and Gemini
2025-03-07 00:18:15 +02:00
fa699956e6 Fix functionResponse part merging 2025-03-07 00:09:11 +02:00
c9277cec28 Gemini: Add tool calling 2025-03-06 23:52:35 +02:00
e9cf606c70 Add backend-provided websearch connectors for OpenRouter and Gemini 2025-03-06 22:23:35 +02:00
50f1e3f0f2 Added translation to reasoning block (#3617)
* Added translate to reasoning block

* Added mising reset value

* Shortcut nullable type

* Added reasoning edited/deleted events, better naming

* Fixed async call

* Added await to saveChat calls

* Exported updateReasoningUI

* Removed translated reasoning on edit if auto mode is none

* Added new value check before updating reasoning block, fixed an issue that display value stays same when we edit the message.

* Translate reasoning before the main message

* Fixed auto mode translate for reasoning message

* Translate reasoning first. Prevent out of bounds access

* Fix translating reasoning on swipe generation

---------

Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
2025-03-06 21:30:17 +02:00
4d81dfb085 Merge pull request #3614 from SillyTavern/char-shallow
Lazy load characters
2025-03-06 20:57:24 +02:00
8161690ce6 Merge branch 'staging' into char-shallow 2025-03-06 20:55:22 +02:00
02a8c8c460 Fix server crash if request was aborted during out of quota retry 2025-03-06 20:54:10 +02:00
8565df13e4 Merge pull request #3618 from annoawesome/electron
Add support for Electron
2025-03-06 19:43:06 +02:00
35b72cc6e6 Merge pull request #3624 from SillyTavern/server-events
Add server events emitter
2025-03-06 19:21:36 +02:00
6b821409e0 Add server events emitter 2025-03-06 14:55:50 +00:00
fc94ed64c1 Same changes but on staging 2025-03-06 01:22:45 +01:00
c36607be6f Merge pull request #3610 from bmen25124/time_to_first_token
Added time to first token
2025-03-05 21:55:36 +02:00
3b9fcfae60 Console log Ollama model pulls 2025-03-05 21:42:56 +02:00
2d2bf48d3d Make Groq happier 2025-03-05 21:38:38 +02:00
c167890d26 Add multimodal captioning for Cohere 2025-03-05 21:36:43 +02:00
a09b9fa746 Added Aya Vision support (#3615) 2025-03-05 21:17:33 +02:00
fb5f3e0f97 Changed param order, saved a tree 2025-03-05 18:39:19 +03:00
3cb24507a7 Shortcut nullable type 2025-03-05 17:53:44 +03:00
5398684ea2 Token rate round from 1 to 3 2025-03-05 17:28:15 +03:00
d3263b0e0f Removed rounding from time to first token display 2025-03-05 17:16:53 +03:00
06beaccdae Formatting 2025-03-05 14:44:07 +03:00
17d2771a75 time_to_first_token moved to extras 2025-03-05 14:42:29 +03:00
858b750346 Document the magic number for future generations 2025-03-05 09:26:16 +00:00