40 Commits

Author SHA1 Message Date
Anton Novoselov
574e381b0a Update Groq Kimi K2 model name 2025-09-11 09:42:10 +01:00
Alexey Haidamaka
d666343121
added mistral-medium-latest
https://docs.mistral.ai/getting-started/models/models_overview/#api-versioning

Medium offers a reasonable balance between Small and Large in output and speed. Especially now when Large is sometimes is frequently over capacity.

This is my go to model for Mistral.
2025-08-26 16:32:43 +02:00
Beingpax
3c84bcf757 Logging of failed API verification and adding GPT‑4 models again. 2025-08-19 09:57:32 +05:45
Beingpax
08657224d4 Add gpt-oss from groq 2025-08-18 17:00:40 +05:45
Beingpax
8d319aa99a Fix Mistral enhancement endpoint 2025-08-14 09:26:41 +05:45
Beingpax
a3b25bb15f Fix OpenAI API verification compatibility issue 2025-08-09 19:58:36 +05:45
Beingpax
2ae40c3e91 Updated openAI models to use gpt 5 2025-08-08 22:01:33 +05:45
Prakash Joshi Pax
135ab6c53a
Update AIService.swift 2025-08-07 14:22:38 +05:45
Palash Oswal
c820964a16
Add gpt-oss-120b to cerebras 2025-08-05 13:52:04 -04:00
Beingpax
41cfc2eca3 refactor: Centralize notification definitions 2025-08-05 21:48:11 +05:45
Beingpax
b9fad57d3e feat: Update Power Mode session dynamically 2025-08-05 21:45:11 +05:45
Beingpax
7580edc8ea Remove Qwen thinking model 2025-08-02 17:22:08 +05:45
Beingpax
cfd09ed36b Add correct model name for Qwen-3-235b-a22b-thinking-250 2025-08-02 12:24:28 +05:45
Beingpax
d658668fed feat: Set Qwen3 235B as default 2025-08-02 09:26:56 +05:45
Beingpax
8de706ba41 feat: Add Qwen3 235B Thinking model 2025-08-02 09:22:07 +05:45
Beingpax
7acad499b4 Add gemini-2.5-flash-lite model 2025-08-01 17:40:14 +05:45
Beingpax
a4356e7fb8 Update AI Enhancement Service: Remove retry logic and fix unused error logging 2025-07-25 16:20:45 +05:45
Beingpax
597352e149 feat: Remove DeepSeek from AI providers 2025-07-25 11:53:16 +05:45
Beingpax
f7357b2fcf feat: Reorder AI providers 2025-07-25 11:51:20 +05:45
Palash Oswal
e389636a19
Add a better model option for cerebras 2025-07-24 15:14:47 -04:00
Beingpax
378dd80189 Model filtering 2025-07-23 21:21:02 +05:45
Beingpax
f9adfd5269 cerebras AI provider integration 2025-07-23 21:08:14 +05:45
Beingpax
fd03c1ca81 Add Kimi 2 Model 2025-07-17 19:35:52 +05:45
Beingpax
46e9e91ea6 Fixed Mistral LLM 2025-07-17 17:29:59 +05:45
Beingpax
2f92a632a9 Added Mistral Mini Cloud Model 2025-07-17 17:26:44 +05:45
Beingpax
b405fee0b8 Add Llama 4 model to Groq provider 2025-07-14 23:18:14 +05:45
Beingpax
2bd2c96be2 Remove enhancement opacity, update Gemini models, add AI reasoning filter 2025-07-14 22:55:42 +05:45
Beingpax
28dbe5a2f6 Fix: Cloud transcription errors 2025-07-09 10:20:02 +05:45
Beingpax
abe5972d1e Fixed Open Router model issues with Power Mode 2025-06-30 12:55:24 +05:45
Beingpax
1ff124a7ce fixed locale and looping issue 2025-06-26 13:59:40 +05:45
Beingpax
9629d8b8ef Add Claude Opus 4 models 2025-06-26 12:52:15 +05:45
Beingpax
cb5a515d70 Refine enhancement retry logic 2025-06-24 16:34:40 +05:45
Beingpax
6ddb89cbf8 Add OpenRouter support and enhancement error handling 2025-06-24 16:29:12 +05:45
Beingpax
9b0c2366b6 Remove Ollama startup initialization 2025-06-24 11:43:21 +05:45
Beingpax
2e23f043f9 Updated Gemini AI models 2025-06-21 18:52:16 +05:45
Beingpax
00e1d5e8da feat: Added Deepgram transcription support 2025-06-16 21:26:35 +05:45
Beingpax
9b507ce615 feat: Added support for cloud transcription service 2025-06-09 19:15:50 +05:45
Beingpax
d389d8ecc1 feat: add AI model selection support 2025-05-04 16:58:03 +05:45
Beingpax
117ce1744f Mistral support by Vaygr 2025-04-05 21:56:52 +05:45
Beingpax
76a154706c Initial commit: Open-sourcing VoiceInk 2025-02-22 11:52:41 +05:45