File size: 2,286 Bytes
aa61236 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 |
"""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
|