Wolfsblvt a8899f7d81 Clean reasoning from classify response ...

- If a reasoning model is used (via LLM, or R1 distill via webLLM), it'll likely return reasoning. That should not be used for the search of classification inside the response

2025-03-19 03:30:53 +01:00

..

assets

Update tl

2025-03-17 16:09:36 +07:00

attachments

Update tl

2025-03-17 16:09:36 +07:00

caption

MistralAI: Add new models

2025-03-18 19:53:02 +02:00

connection-manager

Merge branch 'staging' into reasoning-template

2025-03-16 22:51:28 +02:00

expressions

Clean reasoning from classify response

2025-03-19 03:30:53 +01:00

gallery

Add gallery folder and sort order controls (#3605)

2025-03-04 23:16:56 +02:00

memory

Refactor context change checks during chat summarization

2025-02-28 12:54:52 +00:00

quick-reply

feature: 'kokoro-js' supports TTS #3412 (#3656)

2025-03-10 22:54:54 +02:00

regex

Update tl

2025-03-17 16:09:36 +07:00

stable-diffusion

better type name, simplified context

2025-03-13 02:27:03 +03:00

third-party

[wip] Add global extensions

2024-12-07 17:10:26 +02:00

token-counter

Work on tl

2025-02-16 18:43:57 +07:00

translate

Added translation to reasoning block (#3617)

2025-03-06 21:30:17 +02:00

tts

Fix TTS

2025-03-18 00:59:04 +02:00

vectors

Vectors WebLLM (#3631)

2025-03-09 00:51:44 +02:00

shared.js

Added "custom_url" to ChatCompletionService

2025-03-17 14:54:59 +03:00