backend/config_free.py

"""Configuration for LLM Council using FREE HuggingFace models + OpenAI."""

import os
from dotenv import load_dotenv

load_dotenv()

# API Keys
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
HUGGINGFACE_API_KEY = os.getenv("HUGGINGFACE_API_KEY")  # For Inference API

# Council members - Mix of FREE HuggingFace models + OpenAI
# HuggingFace Inference API provides free access to many models
COUNCIL_MODELS = [
    # OpenAI models (using your key)
    {
        "id": "openai/gpt-4o-mini",
        "provider": "openai",
        "model": "gpt-4o-mini",
        "description": "OpenAI GPT-4o mini - fast and capable"
    },
    {
        "id": "openai/gpt-3.5-turbo",
        "provider": "openai", 
        "model": "gpt-3.5-turbo",
        "description": "OpenAI GPT-3.5 Turbo - reliable"
    },
    
    # FREE HuggingFace models via Inference API
    {
        "id": "meta-llama/Llama-3.3-70B-Instruct",
        "provider": "huggingface",
        "model": "meta-llama/Llama-3.3-70B-Instruct",
        "description": "Meta Llama 3.3 70B - excellent reasoning"
    },
    {
        "id": "Qwen/Qwen2.5-72B-Instruct",
        "provider": "huggingface",
        "model": "Qwen/Qwen2.5-72B-Instruct",
        "description": "Qwen 2.5 72B - strong performance"
    },
    {
        "id": "mistralai/Mixtral-8x7B-Instruct-v0.1",
        "provider": "huggingface",
        "model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
        "description": "Mixtral 8x7B - mixture of experts"
    },
]

# Chairman model - Use OpenAI GPT-4o for best synthesis
CHAIRMAN_MODEL = {
    "id": "openai/gpt-4o-mini",
    "provider": "openai",
    "model": "gpt-4o-mini",
    "description": "OpenAI GPT-4o mini - excellent synthesis"
}

# Alternative configurations
# 
# ALL FREE (HuggingFace only):
# COUNCIL_MODELS = [
#     {"id": "meta-llama/Llama-3.3-70B-Instruct", "provider": "huggingface", ...},
#     {"id": "Qwen/Qwen2.5-72B-Instruct", "provider": "huggingface", ...},
#     {"id": "mistralai/Mixtral-8x7B-Instruct-v0.1", "provider": "huggingface", ...},
#     {"id": "google/gemma-2-27b-it", "provider": "huggingface", ...},
#     {"id": "microsoft/Phi-3.5-mini-instruct", "provider": "huggingface", ...},
# ]
#
# PREMIUM (More OpenAI):
# COUNCIL_MODELS = [
#     {"id": "openai/gpt-4o", "provider": "openai", "model": "gpt-4o", ...},
#     {"id": "openai/gpt-4o-mini", "provider": "openai", "model": "gpt-4o-mini", ...},
#     {"id": "meta-llama/Llama-3.3-70B-Instruct", "provider": "huggingface", ...},
#     {"id": "Qwen/Qwen2.5-72B-Instruct", "provider": "huggingface", ...},
# ]

# Data directory for conversation storage
DATA_DIR = "data/conversations"

# Timeout settings
DEFAULT_TIMEOUT = 120.0
CHAIRMAN_TIMEOUT = 180.0

# Retry settings
MAX_RETRIES = 2
RETRY_DELAY = 2.0