archived_scripts/cleanup_chroma.py

#!/usr/bin/env python3
"""Script to clean up ChromaDB collections and cache."""

import shutil
import os
from pathlib import Path

def cleanup_chroma_db():
    """Clean up ChromaDB collections and cache."""
    
    print("=" * 60)
    print("ChromaDB Cleanup Utility")
    print("=" * 60)
    
    # First, forcefully delete the chroma_db directory
    chroma_path = Path("./chroma_db")
    if chroma_path.exists():
        print(f"\n🗑️  Removing chroma_db directory: {chroma_path}")
        try:
            shutil.rmtree(chroma_path)
            print(f"✅ Deleted directory: {chroma_path}")
        except Exception as e:
            print(f"❌ Error deleting directory: {e}")
    else:
        print(f"\n✅ chroma_db directory not found: {chroma_path}")
    
    # Also check for ChromaDB in .chroma directory (alternative location)
    chroma_alt_path = Path("./.chroma")
    if chroma_alt_path.exists():
        print(f"\n🗑️  Removing .chroma directory: {chroma_alt_path}")
        try:
            shutil.rmtree(chroma_alt_path)
            print(f"✅ Deleted directory: {chroma_alt_path}")
        except Exception as e:
            print(f"❌ Error deleting directory: {e}")
    
    # Clear HuggingFace dataset cache (optional)
    response = input("\n🗑️  Clear HuggingFace dataset cache? (y/n): ").lower()
    if response == 'y':
        cache_path = Path.home() / ".cache" / "huggingface" / "datasets"
        if cache_path.exists():
            print(f"🗑️  Removing HF cache: {cache_path}")
            try:
                shutil.rmtree(cache_path)
                print(f"✅ Deleted HF cache: {cache_path}")
            except Exception as e:
                print(f"❌ Error deleting HF cache: {e}")
        else:
            print("ℹ️  HuggingFace cache not found")
    
    # Clear ChromaDB chroma cache directory
    response = input("\n🗑️  Clear ChromaDB chroma cache? (y/n): ").lower()
    if response == 'y':
        chroma_cache = Path.home() / ".chroma"
        if chroma_cache.exists():
            print(f"🗑️  Removing ChromaDB cache: {chroma_cache}")
            try:
                shutil.rmtree(chroma_cache)
                print(f"✅ Deleted ChromaDB cache: {chroma_cache}")
            except Exception as e:
                print(f"❌ Error deleting ChromaDB cache: {e}")
    
    # Try to use ChromaDBManager if possible
    print("\n📋 Attempting to connect to ChromaDB...")
    try:
        from vector_store import ChromaDBManager
        
        manager = ChromaDBManager(persist_directory="./chroma_db")
        
        # List existing collections
        collections = manager.list_collections()
        print(f"📊 Found {len(collections)} collection(s):")
        for col in collections:
            print(f"   - {col}")
        
        # Clear all collections
        if collections:
            print("\n🗑️  Clearing all collections...")
            deleted = manager.clear_all_collections()
            print(f"✅ Deleted {deleted} collection(s)")
        else:
            print("\n✅ No collections to delete")
    except Exception as e:
        print(f"⚠️  Could not connect to ChromaDB via manager: {e}")
        print("ℹ️  This is OK - the directory has been deleted already.")
    
    print("\n" + "=" * 60)
    print("✅ Cleanup completed! You can now start fresh.")
    print("=" * 60)


if __name__ == "__main__":
    cleanup_chroma_db()