结巴分词/embedding 测试

curl --location -g --request GET 'http://localhost:5000/datasets/embeddings?query=C:\Users\MLTZ\.local\bin\uv.exe run D:/code/llm-ops/llmops-api/.venv/Scripts/python.exe D:\code\llm-ops\llmops-api\app\http\app.py uv run --link-mode=copy python app\http\app.py D:\code\llm-ops\llmops-api\.venv\Lib\site-packages\langchain_classic\embeddings\cache.py:58: UserWarning: Using default key encoder: SHA-1 is *not* collision-resistant. While acceptable for most cache scenarios, a motivated attacker can craft two different payloads that map to the same cache key. If that risk matters in your environment, supply a stronger encoder (e.g. SHA-256 or BLAKE2) via the `key_encoder` argument. If you change the key encoder, consider also creating a new cache, to avoid (the potential for) collisions with existing keys.  _warn_about_sha1_encoder() * Serving Flask app '\''app'\'' * Debug mode: on[2026-04-20 13:18:02,162.162] _internal.py -> _log line:97 [INFO]: WARNING: This is a development server. Do not use it in a production deployment. Use a production WSGI server instead. * Running on http://127.0.0.1:5000[2026-04-20 13:18:02,162.162] _internal.py -> _log line:97 [INFO]: Press CTRL+C to quit[2026-04-20 13:18:02,168.168] _internal.py -> _log line:97 [INFO]:  * Restarting with watchdog (windowsapi)D:\code\llm-ops\llmops-api\.venv\Lib\site-packages\langchain_classic\embeddings\cache.py:58: UserWarning: Using default key encoder: SHA-1 is *not* collision-resistant. While acceptable for most cache scenarios, a motivated attacker can craft two different payloads that map to the same cache key. If that risk matters in your environment, supply a stronger encoder (e.g. SHA-256 or BLAKE2) via the `key_encoder` argument. If you change the key encoder, consider also creating a new cache, to avoid (the potential for) collisions with existing keys.  _warn_about_sha1_encoder()[2026-04-20 13:18:15,681.681] _internal.py -> _log line:97 [WARNING]:  * Debugger is active![2026-04-20 13:18:15,686.686] _internal.py -> _log line:97 [INFO]:  * Debugger PIN: 109-481-337Building prefix dict from the default dictionary ...[2026-04-20 13:18:15,889.889] __init__.py -> initialize line:113 [DEBUG]: Building prefix dict from the default dictionary ...Loading model from cache C:\Users\MLTZ\AppData\Local\Temp\jieba.cache[2026-04-20 13:18:15,891.891] __init__.py -> initialize line:132 [DEBUG]: Loading model from cache C:\Users\MLTZ\AppData\Local\Temp\jieba.cacheLoading model cost 0.440 seconds.[2026-04-20 13:18:16,330.330] __init__.py -> initialize line:164 [DEBUG]: Loading model cost 0.440 seconds.Prefix dict has been built successfully.[2026-04-20 13:18:16,330.330] __init__.py -> initialize line:166 [DEBUG]: Prefix dict has been built successfully.[2026-04-20 13:18:16,331.331] _internal.py -> _log line:97 [INFO]: 127.0.0.1 - - [20/Apr/2026 13:18:16] "GET /datasets/embeddings?query=你好,%20我是野猪佩奇 HTTP/1.1" 200 -'