"""
检查 Qdrant 中课程知识库的数据结构
"""

import asyncio
import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).parent.parent))

from qdrant_client import AsyncQdrantClient

from app.core.config import get_settings


from app.core.qdrant_client import QdrantClient


async def check_course_kb():
    """检查课程知识库"""
    settings = get_settings()
    
    client = QdrantClient()
    qdrant = await client.get_client()
    
    tenant_id = "szmp@ash@2026"
    course_kb_id = "75c465fe-277d-455d-a30b-4b168adcc03b"
    
    safe_tenant_id = tenant_id.replace('@', '_')
    prefix = settings.qdrant_collection_prefix
    
    expected_collection = f"{prefix}{safe_tenant_id}_{course_kb_id}"
    
    print(f"\n{'='*80}")
    print(f"检查课程知识库 Collection")
    print(f"{'='*80}")
    print(f"租户 ID: {tenant_id}")
    print(f"课程知识库 ID: {course_kb_id}")
    print(f"预期 Collection 名称: {expected_collection}")
    
    collections = await qdrant.get_collections()
    collection_names = [c.name for c in collections.collections]
    
    print(f"\n租户的所有 Collections:")
    for name in collection_names:
        if safe_tenant_id in name:
            print(f"  - {name}")
    
    if expected_collection in collection_names:
        print(f"\n✅ 课程知识库 Collection 存在: {expected_collection}")
        
        points, _ = qdrant.scroll(
            collection_name=expected_collection,
            limit=3,
            with_vectors=False,
        )
        
        print(f"\n课程知识库数据 (共 {len(points)} 条):")
        for i, point in enumerate(points, 1):
            payload = point.get('payload', {})
            print(f"\n  [{i}] id: {point.get('id')}")
            print(f"      payload keys: {list(payload.keys())}")
            if 'metadata' in payload:
                print(f"      metadata: {payload['metadata']}")
    else:
        print(f"\n❌ 课程知识库 Collection 不存在!")
        print(f"   可用的 Collections: {collection_names}")


if __name__ == "__main__":
    asyncio.run(check_course_kb())