10563900a3
- Add multi-provider LLM architecture supporting OpenRouter, OpenAI, Gemini, and custom providers - Implement global LLM on/off switch with default DISABLED state for cost protection - Add per-character LLM configuration with provider-specific models and settings - Create performance-optimized caching system for LLM enabled status checks - Add API key validation before enabling LLM providers to prevent broken configurations - Implement audit logging for all LLM enable/disable actions for cost accountability - Create comprehensive admin UI with prominent cost warnings and confirmation dialogs - Add visual indicators in character list for custom AI model configurations - Build character-specific LLM client system with global fallback mechanism - Add database schema support for per-character LLM settings - Implement graceful fallback responses when LLM is globally disabled - Create provider testing and validation system for reliable connections
79 lines
2.3 KiB
YAML
79 lines
2.3 KiB
YAML
# Example LLM Provider Configuration
|
|
# Copy this section to your main fishbowl_config.json under "llm" -> "providers"
|
|
|
|
llm:
|
|
# Legacy config (still supported for backwards compatibility)
|
|
base_url: "${LLM_BASE_URL:http://localhost:11434}"
|
|
model: "${LLM_MODEL:llama2}"
|
|
timeout: ${LLM_TIMEOUT:300}
|
|
max_tokens: ${LLM_MAX_TOKENS:2000}
|
|
temperature: ${LLM_TEMPERATURE:0.8}
|
|
|
|
# New multi-provider configuration
|
|
providers:
|
|
# OpenRouter (supports many models including Claude, GPT, Llama)
|
|
openrouter:
|
|
type: "openrouter"
|
|
enabled: ${OPENROUTER_ENABLED:false}
|
|
priority: 100 # Highest priority
|
|
config:
|
|
api_key: "${OPENROUTER_API_KEY:}"
|
|
base_url: "https://openrouter.ai/api/v1"
|
|
model: "${OPENROUTER_MODEL:anthropic/claude-3-sonnet}"
|
|
timeout: 300
|
|
max_tokens: 2000
|
|
temperature: 0.8
|
|
app_name: "discord-fishbowl"
|
|
|
|
# OpenAI
|
|
openai:
|
|
type: "openai"
|
|
enabled: ${OPENAI_ENABLED:false}
|
|
priority: 90
|
|
config:
|
|
api_key: "${OPENAI_API_KEY:}"
|
|
base_url: "https://api.openai.com/v1"
|
|
model: "${OPENAI_MODEL:gpt-4o-mini}"
|
|
timeout: 300
|
|
max_tokens: 2000
|
|
temperature: 0.8
|
|
|
|
# Google Gemini
|
|
gemini:
|
|
type: "gemini"
|
|
enabled: ${GEMINI_ENABLED:false}
|
|
priority: 80
|
|
config:
|
|
api_key: "${GEMINI_API_KEY:}"
|
|
base_url: "https://generativelanguage.googleapis.com/v1beta"
|
|
model: "${GEMINI_MODEL:gemini-1.5-flash}"
|
|
timeout: 300
|
|
max_tokens: 2000
|
|
temperature: 0.8
|
|
|
|
# Custom/Local (KoboldCPP, Ollama, etc.)
|
|
custom:
|
|
type: "custom"
|
|
enabled: ${CUSTOM_LLM_ENABLED:true}
|
|
priority: 70 # Lower priority - fallback
|
|
config:
|
|
base_url: "${LLM_BASE_URL:http://192.168.1.200:5005/v1}"
|
|
model: "${LLM_MODEL:koboldcpp/Broken-Tutu-24B-Transgression-v2.0.i1-Q4_K_M}"
|
|
api_key: "${LLM_API_KEY:x}"
|
|
timeout: 300
|
|
max_tokens: 2000
|
|
temperature: 0.8
|
|
api_format: "openai" # or "ollama"
|
|
|
|
# Ollama (local models)
|
|
ollama:
|
|
type: "custom"
|
|
enabled: ${OLLAMA_ENABLED:false}
|
|
priority: 60
|
|
config:
|
|
base_url: "http://localhost:11434"
|
|
model: "${OLLAMA_MODEL:llama3}"
|
|
timeout: 300
|
|
max_tokens: 2000
|
|
temperature: 0.8
|
|
api_format: "ollama" |