Files
the-island/backend/.env.example
empty 8bb78a808d revert: remove auto-prefix, user specifies full provider/model
Support both OpenAI-compatible and Anthropic-compatible endpoints.
User must specify full model name with provider prefix.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-01 14:07:17 +08:00

58 lines
2.3 KiB
Plaintext

# LLM Configuration for The Island Backend
# Copy this file to .env and fill in your values
# =============================================================================
# Option 1: OpenAI (default)
# =============================================================================
# OPENAI_API_KEY=sk-xxx
# LLM_MODEL=gpt-3.5-turbo
# =============================================================================
# Option 2: Anthropic Claude
# =============================================================================
# ANTHROPIC_API_KEY=sk-ant-xxx
# LLM_MODEL=claude-3-haiku-20240307
# =============================================================================
# Option 3: Google Gemini
# =============================================================================
# GEMINI_API_KEY=xxx
# LLM_MODEL=gemini/gemini-pro
# =============================================================================
# Option 4: Azure OpenAI
# =============================================================================
# AZURE_API_KEY=xxx
# AZURE_API_BASE=https://your-resource.openai.azure.com
# LLM_MODEL=azure/your-deployment-name
# =============================================================================
# Option 5: OpenRouter (access multiple models)
# =============================================================================
# OPENROUTER_API_KEY=sk-or-xxx
# LLM_MODEL=openrouter/anthropic/claude-3-haiku
# =============================================================================
# Option 6: Local Ollama
# =============================================================================
# OLLAMA_API_BASE=http://localhost:11434
# LLM_MODEL=ollama/llama2
# =============================================================================
# Option 7: Custom/Self-hosted endpoint
# See: https://docs.litellm.ai/docs/providers
# =============================================================================
# LLM_API_BASE=http://localhost:8000/v1
# LLM_API_KEY=your-key
#
# For OpenAI-compatible API:
# LLM_MODEL=openai/your-model-name
#
# For Anthropic-compatible API:
# LLM_MODEL=anthropic/your-model-name
# =============================================================================
# Force mock mode (no API calls, uses predefined responses)
# =============================================================================
# LLM_MOCK_MODE=true