config.py

from pathlib import Path
from dotenv import load_dotenv
import os

load_dotenv()

BASE_DIR = Path(__file__).parent
DATA_DIR = BASE_DIR / "data"
INDEX_DIR = DATA_DIR / "index"
DOCS_DIR = DATA_DIR / "docs"

# Ensure data dirs exist
INDEX_DIR.mkdir(parents=True, exist_ok=True)
DOCS_DIR.mkdir(parents=True, exist_ok=True)

# FAISS index files
FAISS_INDEX_PATH = INDEX_DIR / "physics.index"
METADATA_PATH = INDEX_DIR / "metadata.pkl"

# Embeddings
EMBEDDING_MODEL = "all-MiniLM-L6-v2"
EMBEDDING_DIM = 384

# Chunking
CHUNK_SIZE = 1200       # characters
CHUNK_OVERLAP = 200     # characters

# Ollama
OLLAMA_BASE_URL = os.getenv("OLLAMA_BASE_URL", "http://localhost:11434")
OLLAMA_MODEL = os.getenv("OLLAMA_MODEL", "mistral")

# Retrieval
TOP_K = 5               # chunks to retrieve

# arXiv
ARXIV_MAX_RESULTS = 5