cclohmar
5ca3ff7555
- New provider architecture with common interface - Provider selected via AI_PROVIDER env var (gemini/openai/ollama) - Gemini (default): existing implementation, uses GEMINI_API_KEY - OpenAI-compatible: uses OPENAI_API_KEY + AI_MODEL + AI_BASE_URL - Works with OpenAI, Perplexity, Together AI, Groq, etc. - Ollama: local LLM, uses AI_BASE_URL + AI_MODEL - Supports llava, bakllava, and other vision models - deepseek.go renamed to llm.go (cleanup) - .env.example updated with all AI provider options
27 lines
750 B
Text
27 lines
750 B
Text
# ExpenseFlow Configuration
|
|
# Copy this file to .env and fill in your credentials.
|
|
|
|
# SMTP Configuration
|
|
SMTP_HOST=smtp.openxchange.eu
|
|
SMTP_PORT=587
|
|
SMTP_USER=post@2-4-h.app
|
|
SMTP_PASS=D9AW8JP74r1V
|
|
|
|
# --- AI Provider Configuration ---
|
|
# Choose one: gemini (default), openai, ollama
|
|
AI_PROVIDER=gemini
|
|
|
|
# Gemini (default, used when AI_PROVIDER=gemini)
|
|
GEMINI_API_KEY=AQ.Ab8RN6IQjKTQofuKOW2TT5mZ0zwt8rFa8X3SHGyYyce4DrbBJw
|
|
|
|
# OpenAI / Compatible (used when AI_PROVIDER=openai)
|
|
# OPENAI_API_KEY=sk-...
|
|
# AI_MODEL=gpt-4o-mini
|
|
# AI_BASE_URL=https://api.openai.com/v1
|
|
|
|
# Ollama - Local LLM (used when AI_PROVIDER=ollama)
|
|
# AI_BASE_URL=http://localhost:11434
|
|
# AI_MODEL=llava
|
|
|
|
# Base URL for generating absolute links in emails
|
|
BASE_URL=http://localhost:8080
|