#!/opt/homebrew/bin/python3.11
"""
Vector Search Test with nomic-embed-text:v1.5 using prefixes - detailed results
"""

import time
import requests


VIDEO_UUID = "39567a0eb16f39fd"

POSTGRES_CONFIG = {
    "host": "localhost",
    "port": 5432,
    "user": "accusys",
    "password": "Test3200",
    "database": "momentry",
}

MODEL = "nomic-embed-text:v1.5"
QDRANT_COLLECTION = "chunks_v2"


def get_embedding(text, prefix=""):
    prompt = f"{prefix}{text}"
    resp = requests.post(
        "http://localhost:11434/api/embeddings", json={"model": MODEL, "prompt": prompt}
    )
    return resp.json()["embedding"]


def test_queries(queries, use_prefix=True):
    """Test queries against Qdrant"""
    prefix = "search_query: " if use_prefix else ""
    results_data = []

    for query in queries:
        embedding = get_embedding(query, prefix)

        start = time.time()
        resp = requests.post(
            f"http://localhost:6333/collections/{QDRANT_COLLECTION}/points/search",
            headers={
                "api-key": "Test3200Test3200Test3200",
                "Content-Type": "application/json",
            },
            json={"vector": embedding, "limit": 3, "with_payload": True},
        )
        elapsed = (time.time() - start) * 1000

        results = resp.json().get("result", [])

        print(f"\nQuery: '{query}' ({elapsed:.1f}ms)")
        print("-" * 60)
        for i, r in enumerate(results):
            score = r.get("score", 0)
            payload = r.get("payload", {})
            text = payload.get("text", "")[:60]
            print(f"  {i + 1}. [{score:.3f}] {text}")

        results_data.append(
            {
                "query": query,
                "time_ms": elapsed,
                "top_score": results[0].get("score", 0) if results else 0,
                "top_text": results[0].get("payload", {}).get("text", "")[:50]
                if results
                else "",
            }
        )

    return results_data


# English queries
ENGLISH_QUERIES = [
    "a person talking",
    "someone speaking on camera",
    "outdoor scene",
    "indoor setting",
    "walking or moving",
    "dialogue or conversation",
    "looking at something",
    "happy or joyful",
    "serious or dramatic",
    "comedy or funny",
    "wearing a tie",
    "holding an object",
    "sitting on a chair",
    "city or urban",
    "building or room",
    "open space",
]

# Chinese queries
CHINESE_QUERIES = [
    "有人在說話",
    "戶外場景",
    "室內場景",
    "走路或移動",
    "對話或交談",
    "看著某樣東西",
    "快樂或開心",
    "嚴肅或戲劇性",
    "喜劇或有趣",
    "戴著領帶",
    "拿著東西",
    "坐在椅子上",
    "城市或都市",
    "建築物或房間",
    "開放空間",
]


if __name__ == "__main__":
    print("=" * 70)
    print(f"Testing with {QDRANT_COLLECTION}")
    print(f"Model: {MODEL}")
    print("Prefix for chunks: search_document:")
    print("Prefix for queries: search_query:")
    print("=" * 70)

    print("\n" + "=" * 70)
    print("ENGLISH QUERIES")
    print("=" * 70)
    en_results = test_queries(ENGLISH_QUERIES)

    print("\n" + "=" * 70)
    print("CHINESE QUERIES")
    print("=" * 70)
    zh_results = test_queries(CHINESE_QUERIES)

    # Summary
    print("\n" + "=" * 70)
    print("SUMMARY")
    print("=" * 70)

    en_avg = sum(r["time_ms"] for r in en_results) / len(en_results)
    zh_avg = sum(r["time_ms"] for r in zh_results) / len(zh_results)

    print(f"\nEnglish avg time: {en_avg:.1f}ms")
    print(f"Chinese avg time: {zh_avg:.1f}ms")

    print("\nTop results:")
    print(f"\n{'Query':<25} | {'Time':<8} | {'Score':<8} | {'Text'}")
    print("-" * 70)
    for r in en_results[:5]:
        print(
            f"{r['query']:<25} | {r['time_ms']:>5.1f}ms | {r['top_score']:.3f} | {r['top_text']}"
        )

    print()
    for r in zh_results[:5]:
        print(
            f"{r['query']:<25} | {r['time_ms']:>5.1f}ms | {r['top_score']:.3f} | {r['top_text']}"
        )