import os
from pathlib import Path
from dotenv import load_dotenv
from qdrant_client import QdrantClient

load_dotenv()

# Paths
BASE_DIR = Path(__file__).parent.parent
DATA_DIR = BASE_DIR / "data"
RAW_DATA_DIR = DATA_DIR / "raw"
VECTOR_DB_DIR = DATA_DIR / "qdrant_db"

# Ensure directories exist
RAW_DATA_DIR.mkdir(parents=True, exist_ok=True)
VECTOR_DB_DIR.mkdir(parents=True, exist_ok=True)

# Secrets
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
if not OPENAI_API_KEY:
    raise ValueError("CRITICAL: OPENAI_API_KEY missing from .env file.")

# Models
EMBEDDING_MODEL = "text-embedding-3-small"
SPARSE_MODEL = "Qdrant/bm25"
LLM_MODEL = "gpt-4o-mini"
COLLECTION_NAME = "geneseek_clinical_trials"

qdrant_client = QdrantClient(
    url=os.getenv("QDRANT_URL"),
    api_key=os.getenv("QDRANT_API_KEY")
)