import os

# --- Architecture Constants ---
NUM_CLUSTERS = 32
FRESHNESS_SHARD_ID = 999
MRL_DIMS = 64

# --- Qdrant Configuration ---
# Use in-memory for testing if QDRANT_URL is not set, otherwise connect to cloud/local instance
QDRANT_URL = os.getenv("QDRANT_URL", "https://justmotes-xvector-db-node.hf.space") 
QDRANT_API_KEY = os.getenv("QDRANT_API_KEY", "xvector_secret_pass_123")
COLLECTION_NAME = "dashVector_v1"

# --- Model Configurations ---
# --- Model Configurations ---
EMBEDDING_MODELS = {
    "minilm": "sentence-transformers/all-MiniLM-L6-v2", # 384 dims
    "bge": "BAAI/bge-small-en-v1.5", # 384 dims (Replacement for gated Gemma)
    # "qwen": "Qwen/Qwen2.5-0.5B-Instruct", # 0.5B params
}

ROUTER_MODELS = ["lightgbm", "logistic", "mlp"]

# --- Collection Names ---
# Collection Names (Prod = Sharded, Base = Unsharded)
COLLECTIONS = {
    "minilm": {"prod": "dashVector_minilm_prod", "base": "dashVector_minilm_base"},
    "bge": {"prod": "dashVector_bge_prod", "base": "dashVector_bge_base"},
    # "qwen": {"prod": "dashVector_qwen_prod", "base": "dashVector_qwen_base"},
}

# --- Paths ---
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
LOGS_DIR = os.path.join(BASE_DIR, "logs")
ACTIVE_LEARNING_LOG = os.path.join(LOGS_DIR, "active_learning_queue.jsonl")

# Ensure logs directory exists
os.makedirs(LOGS_DIR, exist_ok=True)