config.py

"""
Central configuration for NLP4ASD.
Change values here to switch models, paths, or behavior globally.
"""

import os

# --- Paths ---
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
DATA_RAW_DIR = os.path.join(BASE_DIR, "data", "raw")
DATA_PROCESSED_DIR = os.path.join(BASE_DIR, "data", "processed")
VECTOR_INDEX_PATH = os.path.join(DATA_PROCESSED_DIR, "faiss_index")
CHUNKS_PATH = os.path.join(DATA_PROCESSED_DIR, "chunks.json")
METADATA_PATH = os.path.join(BASE_DIR, "data", "sources_metadata.json")

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

# --- Chunking ---
CHUNK_SIZE = 512       # characters per chunk
CHUNK_OVERLAP = 64     # overlap between chunks

# --- Retrieval ---
TOP_K = 4              # number of chunks to retrieve

# --- Generation ---
# Lightweight model suitable for Hugging Face Spaces (CPU-friendly)
# Switch to "BioMistral/BioMistral-7B", "google/gemma-2b-it", etc. as needed
GENERATOR_MODEL = "google/flan-t5-base"
MAX_NEW_TOKENS = 512
TEMPERATURE = 0.3

# --- User Profiles ---
PROFILES = [
    "Parent",
    "Patient / Autistic person",
    "Healthcare Professional",
    "Teacher / Educator",
    "Researcher",
]

# --- Languages ---
LANGUAGES = ["English", "French"]

# --- Disclaimer (appended to all answers) ---
DISCLAIMER = (
    "⚠️ This information is based on retrieved scientific sources and is for "
    "informational purposes only. It does not replace professional medical advice."
)