Krishna Chaitanya Cheedella
Refactor to use FREE HuggingFace models + OpenAI instead of OpenRouter
aa61236
| """Configuration for the LLM Council - IMPROVED VERSION.""" | |
| import os | |
| from dotenv import load_dotenv | |
| load_dotenv() | |
| # OpenRouter API key | |
| OPENROUTER_API_KEY = os.getenv("OPENROUTER_API_KEY") | |
| # Council members - list of OpenRouter model identifiers | |
| # IMPROVED: Using latest and most capable models as of late 2024/early 2025 | |
| COUNCIL_MODELS = [ | |
| # DeepSeek V3 - excellent reasoning, cost-effective | |
| "deepseek/deepseek-chat", | |
| # Claude 3.7 Sonnet - strong analytical capabilities | |
| "anthropic/claude-3.7-sonnet", | |
| # GPT-4o - OpenAI's latest multimodal model | |
| "openai/gpt-4o", | |
| # Gemini 2.0 Flash Thinking - Google's fast thinking model | |
| "google/gemini-2.0-flash-thinking-exp:free", | |
| # Qwen QwQ - strong reasoning model | |
| "qwen/qwq-32b-preview", | |
| ] | |
| # Alternative council configurations for different use cases: | |
| # | |
| # BUDGET_COUNCIL (faster, cheaper): | |
| # COUNCIL_MODELS = [ | |
| # "deepseek/deepseek-chat", | |
| # "google/gemini-2.0-flash-exp:free", | |
| # "qwen/qwen-2.5-72b-instruct", | |
| # "meta-llama/llama-3.3-70b-instruct", | |
| # ] | |
| # | |
| # PREMIUM_COUNCIL (best quality, higher cost): | |
| # COUNCIL_MODELS = [ | |
| # "anthropic/claude-3.7-sonnet", | |
| # "openai/o1", | |
| # "google/gemini-exp-1206", | |
| # "anthropic/claude-3-opus", | |
| # "x-ai/grok-2-1212", | |
| # ] | |
| # | |
| # REASONING_COUNCIL (focused on complex reasoning): | |
| # COUNCIL_MODELS = [ | |
| # "openai/o1-mini", | |
| # "deepseek/deepseek-reasoner", | |
| # "google/gemini-2.0-flash-thinking-exp:free", | |
| # "qwen/qwq-32b-preview", | |
| # ] | |
| # Chairman model - synthesizes final response | |
| # IMPROVED: Using DeepSeek R1 for superior reasoning and synthesis | |
| CHAIRMAN_MODEL = "deepseek/deepseek-reasoner" | |
| # Alternative chairman options: | |
| # CHAIRMAN_MODEL = "anthropic/claude-3.7-sonnet" # Excellent at synthesis | |
| # CHAIRMAN_MODEL = "openai/o1" # Best reasoning but slower/expensive | |
| # CHAIRMAN_MODEL = "google/gemini-exp-1206" # Strong context handling | |
| # OpenRouter API endpoint | |
| OPENROUTER_API_URL = "https://openrouter.ai/api/v1/chat/completions" | |
| # Data directory for conversation storage | |
| DATA_DIR = "data/conversations" | |
| # Timeout settings | |
| DEFAULT_TIMEOUT = 120.0 # seconds | |
| CHAIRMAN_TIMEOUT = 180.0 # Chairman might need more time for synthesis | |
| # Retry settings | |
| MAX_RETRIES = 2 | |
| RETRY_DELAY = 2.0 # seconds | |