scripts/check_collections.py

import sqlite3
from pathlib import Path
import sys

# Add project root to path
project_root = Path(__file__).parent.parent
sys.path.append(str(project_root))

from config.settings import Settings

def check_collections():
    """Check collections in ChromaDB"""
    chroma_path = Settings.get_chroma_path()
    sqlite_file = chroma_path / "chroma.sqlite3"
    
    print(f"\nExamining: {sqlite_file}")
    conn = sqlite3.connect(sqlite_file)
    cursor = conn.cursor()
    
    try:
        # List collections
        cursor.execute("SELECT name, id FROM collections;")
        collections = cursor.fetchall()
        
        print("\nCollections found:")
        for name, coll_id in collections:
            print(f"Name: {name}")
            print(f"ID: {coll_id}")
            
            # Get count of embeddings using correct schema
            try:
                cursor.execute("""
                    SELECT COUNT(*) 
                    FROM embeddings e
                    JOIN segments s ON e.segment_id = s.id
                    WHERE s.collection = ?
                """, (coll_id,))
                count = cursor.fetchone()[0]
                print(f"Embeddings count: {count}")
            except sqlite3.OperationalError as e:
                print(f"Could not get count: {e}")
            
            # Get metadata using correct schema
            try:
                cursor.execute("""
                    SELECT key, str_value 
                    FROM collection_metadata 
                    WHERE collection_id = ?
                """, (coll_id,))
                metadata = cursor.fetchall()
                if metadata:
                    print("Collection Metadata:")
                    for key, value in metadata:
                        print(f"  {key}: {value}")
            except sqlite3.OperationalError as e:
                print(f"Could not get metadata: {e}")
            print()
    
    finally:
        conn.close()

if __name__ == "__main__":
    check_collections()