cclohmar/NextExpense
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions
NextExpense/internal/ai
History
cclohmar 3327fd4fac feat: use glm-ocr as default Ollama model (specialized OCR, not a general LLM) 
- glm-ocr is a 1.1B parameter model built specifically for OCR
- No reasoning overhead, no thinking field issues
- Faster inference than qwen3.5 on CPU
- Removed old qwen3.5 models (2B + 0.8B) to free ~4GB disk
- Updated install.sh, ollama.go, .env.example defaults
2026-05-30 17:17:06 +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 feat: use glm-ocr as default Ollama model (specialized OCR, not a general LLM) 2026-05-30 17:17:06 +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