cclohmar/NextExpense
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions
NextExpense/internal/ai
History
cclohmar 1eca4ae777 fix: qwen3.5 reasoning model outputs to thinking field not content 
- ollamaResponse now reads both content and thinking fields
- Falls back to thinking if content is empty
- Install script adds model warm-up prompt to preload into memory
- Warm-up uses OLLAMA_HOST for correct user context
- Makes first real receipt analysis faster
2026-05-30 16:51:43 +00:00
..
gemini.go fix: remove hardcoded credentials from .env.example and source 2026-05-30 15:08:01 +00:00
llm.go feat: configurable AI provider system (Gemini, OpenAI, Ollama) 2026-05-30 14:05:19 +00:00
ollama.go fix: qwen3.5 reasoning model outputs to thinking field not content 2026-05-30 16:51:43 +00:00
openai.go feat: configurable AI provider system (Gemini, OpenAI, Ollama) 2026-05-30 14:05:19 +00:00
receipt.go feat: configurable AI provider system (Gemini, OpenAI, Ollama) 2026-05-30 14:05:19 +00:00