1 · 输入、来源、编码和缓存身份 · 实现代码

# 独立材料，不依赖另一册 notebook 的内存；重复运行复用本项目已下载内容。
from pathlib import Path
import io, json, zipfile, requests, sys, hashlib
_candidates=[Path.cwd()/'lecture03-clip-retrieval', Path.cwd()]
RETRIEVAL_ROOT=next((p for p in _candidates if (p/'cache/clip-features.npz').exists()),None)
if RETRIEVAL_ROOT is None:
    _response=requests.get('https://codingai-lec03.pages.dev/course/materials/lecture03-clip-retrieval.zip',timeout=60)
    _response.raise_for_status()
    _data=_response.content
    print('下载材料 ZIP:',len(_data),'bytes; SHA256',hashlib.sha256(_data).hexdigest())
    with zipfile.ZipFile(io.BytesIO(_data)) as z:
        for info in z.infolist():
            target=(Path.cwd()/info.filename).resolve()
            assert target.is_relative_to(Path.cwd().resolve()), '拒绝越界路径'
            if info.is_dir():target.mkdir(parents=True,exist_ok=True)
            elif not target.exists():
                target.parent.mkdir(parents=True,exist_ok=True);target.write_bytes(z.read(info))
    RETRIEVAL_ROOT=Path.cwd()/'lecture03-clip-retrieval'
assert (RETRIEVAL_ROOT/'cache/provenance.json').is_file()
sys.path.insert(0,str(RETRIEVAL_ROOT))
import run_clip_retrieval as cr
import numpy as np
p=json.loads((RETRIEVAL_ROOT/'cache/provenance.json').read_text())
assert cr.sha(RETRIEVAL_ROOT/'cache/clip-features.npz')==p['cache_sha256']
assert cr.sha(RETRIEVAL_ROOT/'assets/manifest.json')==p['manifest_sha256']
manifest=json.loads((RETRIEVAL_ROOT/'assets/manifest.json').read_text())
for r in manifest['gallery']+manifest['relation']+manifest['holder']:
    assert cr.sha(RETRIEVAL_ROOT/r['path'])==r['sha256']
a=np.load(RETRIEVAL_ROOT/'cache/clip-features.npz')
print('已核验真实 CLIP 缓存；生成时间',p['generated_at_utc'])
print('本格只载入缓存，没有在当前 notebook 运行 CLIP 编码器。')
print('gallery, queries:',a['gallery'].shape,a['queries'].shape)