cclohmar
3327fd4fac
- 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
29 lines
711 B
Text
29 lines
711 B
Text
# ReceiptNext Configuration
|
|
# Copy this file to .env and fill in your credentials.
|
|
# Run `sudo ./install.sh` for interactive setup.
|
|
|
|
# --- AI Provider ---
|
|
# Choose one: gemini, openai, ollama
|
|
AI_PROVIDER=gemini
|
|
|
|
# For AI_PROVIDER=gemini:
|
|
# GEMINI_API_KEY=your-gemini-api-key
|
|
|
|
# For AI_PROVIDER=openai:
|
|
# OPENAI_API_KEY=sk-...
|
|
# AI_MODEL=gpt-4o-mini
|
|
# AI_BASE_URL=https://api.openai.com/v1
|
|
|
|
# For AI_PROVIDER=ollama:
|
|
# AI_BASE_URL=http://localhost:11434
|
|
# AI_MODEL=glm-ocr
|
|
|
|
# --- SMTP (optional — needed for OTP emails and report delivery) ---
|
|
# SMTP_HOST=smtp.example.com
|
|
# SMTP_PORT=587
|
|
# SMTP_USER=your-email@example.com
|
|
# SMTP_PASS=your-password
|
|
|
|
# --- General ---
|
|
PORT=8080
|
|
BASE_URL=http://localhost:8080
|