Fixes

• Fixed inconsistent rendering of messages being generated
• Fixed random crashes related to instance updater

Full Changelog: 7.5.1...7.5.2

Hi everyone, the hotfixes are ready!

New

• Save message edit with ctrl+enter

Fixes

• Fixed Live Chat and Quick Ask not working sometimes
• Fixed model creation and GGUF import

Full Changelog: 7.5.0...7.5.1

Hi everyone, I've prepared a nice updated focused on the model manager!

New

• Added option to use tools by default
• Redesign model manager
• Added option to attach audio and video files (audio transcription)
• Added Spotify controller tool

Fixes

• Fixed thinking mode being on bugs out normal models

What's Changed (Other Contributors)

• Add JavaScript fallback for code blocks by @mags0ft in #859
• Minor improvements for title generation by @mags0ft in #870
• added kimi moonshot api by @olumolu in #877

Full Changelog: 7.0.1...7.5.0

Fixes

• Fixed Alpaca crashing when chats database has incorrect metadata (type)
• Fixed Quick Ask and Live Chat not running when opened from terminal whilst Alpaca is running
• Fixed stop button not working when pressed before text generation beggins
• Fixed instances sometimes not appearing
• Fixed Live Chat / Quick Ask not being able to download stt models

What's Changed (Other Contributors)

• added deepinfra by @olumolu in #846
• enable deepinfra by @olumolu in #847

Full Changelog: 7.0.0...7.0.1

Hi everyone, I hope you guys enjoy this new update!

Discussion

New

• Live Chat (Talk to models as if you were on a call)
• Live message rendering
• Faster dictation
• Dictation whilst message is being generated
• Camera picture attachment
• Quick Ask now supports attachments
• Separator element for message and attachment rendering
• Redesigned popups
• Thought switch for Ollama instances
• Username sharing for Ollama instances
• Redesign for instance manager and tool manager
• Better web searching tool with options

Fixes

• Fixed duplication of thought attachments
• Fixed weird behavior with model selector
• Ollama (Managed) instances behave better
• Better optimizations for RAM (~2GB difference)
• Instant chat rendering
• Models profile pictures are now saved at a higher resolution
• Quick Ask messages can now be sent by using the enter key
• Alpaca is less prone to crashes now

Backend

• Check if Whisper (STT) and Kokoro (TTS) are available
• Move preferences from SQLite to GLib
• Separated message controls from window code
• New system for YouTube attaching

What's Changed (Other Contributors)

• Fix typo in README by @mags0ft in #801
• Replace image.get_content() with image["content"] by @BurntRanch in #806
• Update bn.po by @olumolu in #812
• po: Update Arabic translation by @x9a in #811
• feat/translations: Kannada Translations added in kn.po file by @roche-jeethan in #823
• Update bn.po by @olumolu in #828
• Update hi.po by @olumolu in #829
• Update bn.po for 7.0 by @olumolu in #833
• Update hi.po for 7.0.0 by @olumolu in #834
• added qwen ai api support by @olumolu in #835
• add mistral ai api support by @olumolu in #836
• l10n: Updated Telugu (te) translation by @SpaciousCoder78 in #837
• Update hi.po by @olumolu in #840
• Update bn.po by @olumolu in #839

New Contributors

• @BurntRanch made their first contribution in #806
• @roche-jeethan made their first contribution in #823

Full Changelog: 6.1.7...7.0.0

Fix

• Fixed new chat not being created when the chat list is empty

Full Changelog: 6.1.6...6.1.7

Hi everyone, this is just a small update to fix some errors!

Fixes

• Chat exporting now works as expected
• Fixed automatic creation of Ollama instance
• Added Hebrew and Telugu credits
• Fixed STT model selector

Note

I won't include sha256sum.txt in releases since GitHub now generates a sha256 next to the filename.

What's Changed (Other Contributors)

• fix: Added import of STT_MODELS from constants, needed for whisper support by @kenvandine in #790
• Updated the Simplified Chinese translation texts to release 6.1.5 by @8ar10der in #787
• feat: Make whisper optional by @kenvandine in #791

New Contributors

• @kenvandine made their first contribution in #790

Full Changelog: 6.1.5...6.1.6

Hi everyone, yes, there's another update hahaha.

I made changes to Quick Ask, you can see them here.

New

• Multiple Quick Ask window rendering

Fixes

• Better stability for Quick Ask
• Creating a new chat now selects it

Full Changelog: 6.1.0...6.1.5

Hi everyone, thanks for your patience during my break, I cooked a nice update focused in performance and stability.

Also thanks for 1k stars!

New

• Chat Search
• Hide "latest" and "custom" tags from model selector
• Hide model's languages behind popup
• New models listed for Ollama
• Added option to autodictate new mesages
• Added Meta Llama API to list of instances
• Added new env variables options ("24H hour formatting" and "only Ollama mode")
• Made Mermaid scripts executable using Python HTTP server

Fixes

• Better stability when switching instances
• Better performance when navigating menus
• Fixed some dialogs not appearing in Quick Ask window
• Faster message search
• Faster message rendering

What's Changed (Other Contributors)

• Remove duplicated "vision" tags by @mags0ft in #767
• Update remaining strings for hipo by @olumolu in #765
• Update remaining strings of bn.po by @olumolu in #764
• Add missing reasoning tags to new models by @mags0ft in #763
• Add all missing German translation strings by @mags0ft in #760
• Add Arabic translation by @x9a in #769
• feat(l10n): Updated Telugu (te) Translation by @SpaciousCoder78 in #784

New Contributors

• @x9a made their first contribution in #769

Full Changelog: 6.0.5...6.1.0

Hi, I just wanted to fix a specific error regarding the whisper directory

Fix

• Fixed whisper directory not existing causing error

Full Changelog: 6.0.4...6.0.5