app/config.py

# file: app/config.py
import os
from pathlib import Path
from dotenv import load_dotenv

load_dotenv()

# Paths
BASE_DIR = Path(__file__).parent.parent
DATA_DIR = BASE_DIR / "data"

# Hugging Face Inference API
HF_API_TOKEN = os.getenv("HF_API_TOKEN", "")

# LLM Configuration - Optimized for FREE HF CPU Inference
# Primary: Qwen2.5-3B (3B params - 2.3x faster than 7B, better for CPU)
# Alternative options for CPU:
#   - "Qwen/Qwen2.5-3B-Instruct" (3B - fast, high quality)
#   - "microsoft/Phi-3-mini-4k-instruct" (3.8B - ultra efficient)
#   - "HuggingFaceTB/SmolLM2-1.7B-Instruct" (1.7B - fastest)
MODEL_NAME = os.getenv("MODEL_NAME", "Qwen/Qwen2.5-3B-Instruct")
MODEL_NAME_FALLBACK = os.getenv("MODEL_NAME_FALLBACK", "microsoft/Phi-3-mini-4k-instruct")

# Web Search Configuration
# Set to "true" to skip web search and use fallback data (recommended for demo/rate-limited environments)
SKIP_WEB_SEARCH = os.getenv("SKIP_WEB_SEARCH", "false").lower() == "true"

# Vector Store
VECTOR_INDEX_PATH = os.getenv("VECTOR_INDEX_PATH", str(DATA_DIR / "faiss.index"))
EMBEDDING_MODEL = "sentence-transformers/all-MiniLM-L6-v2"
EMBEDDING_DIM = 384

# MCP Servers
MCP_SEARCH_PORT = int(os.getenv("MCP_SEARCH_PORT", "9001"))
MCP_EMAIL_PORT = int(os.getenv("MCP_EMAIL_PORT", "9002"))
MCP_CALENDAR_PORT = int(os.getenv("MCP_CALENDAR_PORT", "9003"))
MCP_STORE_PORT = int(os.getenv("MCP_STORE_PORT", "9004"))

# Compliance
COMPANY_FOOTER_PATH = os.getenv("COMPANY_FOOTER_PATH", str(DATA_DIR / "footer.txt"))
ENABLE_CAN_SPAM = os.getenv("ENABLE_CAN_SPAM", "true").lower() == "true"
ENABLE_PECR = os.getenv("ENABLE_PECR", "true").lower() == "true"
ENABLE_CASL = os.getenv("ENABLE_CASL", "true").lower() == "true"

# Scoring
MIN_FIT_SCORE = float(os.getenv("MIN_FIT_SCORE", "0.5"))
FACT_TTL_HOURS = int(os.getenv("FACT_TTL_HOURS", "168"))  # 1 week

# Data Files
COMPANIES_FILE = DATA_DIR / "companies.json"
SUPPRESSION_FILE = DATA_DIR / "suppression.json"