v3.5.0

Added

• Add support for together ai @kyteinsky #197

Changed

• Enable use_max_completion_tokens_param by default for OpenAI, disable by default for non-OpenAI @julien-nc #184
• Add admin setting to toggle authentication in the image retrieval request @julien-nc #186
• Add a warning in the admin settings if the assistant app is not installed @julien-nc #185
• Raise the default image size for compatibility @Rello #193
• Bump max NC version to 32

Fixed

• Prevent browser autocomplete for API key inputs and credentials @julien-nc #187
• Do not attempt to update local quota if chat/completion response does not have usage.total_tokens set @julien-nc #189
• Prevent error log flood when not configured @kyteinsky #199

v3.4.0

3.4.0 – 2025-01-22

Changed

• Use max_completion_tokens instead of deprecated max_tokens @julien-nc #176

Added

• Add reuse compliance @AndyScherzinger #173
• Make image generation work with base64 responses (e.g. IONOS) @julien-nc @janepie #177
• Mention IONOS as service with an OpenAI-compatible API @julien-nc #178
• Support chatting with o1 models @julien-nc #179

v3.3.0

Added

• Change tone task type + provider @janepie #163 #172
• Proofread provider @janepie #169
• ChatWithTools provider @julien-nc #167

Changed

• Add ability to summarize by chunks @edward-ly #157

Fixed

• Fix headline prompt @janepie #162
• Grammar mistake @rakekniven #165

v3.2.0

Added

• Admin setting to choose transcription model @julien-nc #154
• Admin setting to set the default image size @julien-nc #135
• Add ability to customize API root path in service URL @edward-ly #143

Changed

• Encrypt api keys and basic passwords for app config and user settings @julien-nc #136 #139
• Remove old providers since old APIs can use TaskProcessing providers @julien-nc #140
• Cache the models for 30min in distributed cache @julien-nc #152

Fixed

• Missuse of user ID in most providers @julien-nc #153
• Use api key in image retrieval request @julien-nc #147

v3.1.2

Changed

• Simple cache for model list to speed up provider loading @julien-nc #133
• Change default image generation size @kyteinsky #124

v3.1.1

Added

• Ability to choose model in the assistant for most providers @julien-nc #130

Changed

• Switch from webpack to vite @julien-nc #131

Fixed

• Fix admin settings not saving the models in some cases @julien-nc #130

v3.1.0

3.1.0 – 2024-09-05

Added

• admin-settings: add image model selection dropdown @kyteinsky #122

Changed

• bump max NC version to 31, update composer dev dependencies @julien-nc
• Bring back textProcessing, translation, STT, and image generation providers @julien-nc #120
• Avoid ambiguity between old and new providers @julien-nc #121

Fixed

• fix(TextToText,Translate): Don't throw in getOptionalInputShapeEnumValues @marcelklehr #115
• fix(providers): do no implement useless 'getOptionalOutputShapeDefaults' method, use the size param in text2image provider @julien-nc #119

v3.0.1

Added

• Translation provider for the task processing API @julien-nc #111

Changed

• Adjust providers to changes in server (enum values and defaults) @julien-nc #111
• Drop the old translation provider @julien-nc #111

v3.0.0

Added

• Create all task processing providers that were text processing ones + image generation + audio transcription @julien-nc #102
• ContextWrite provider
• Chat provider
• Add password confirmation when setting sensitive values in user and admin settings

Changed

• Drop old image generation, audio transcription and text processing providers
• Use nc/vue 8.14.0

Fixed

• Fix topics provider output: make it comma separated

v2.0.3

Fixed

• incorrect numeric settings handling on the server side @julien-nc

Changed

• move personal and admin settings to AI sections @julien-nc
• update npm pkgs @julien-nc