17 · 真实搜索：词法、语义、融合与重排

from pathlib import Path
import os, sys
root = Path.cwd()
if not (root / "reclab").exists(): root = root.parent
os.chdir(root)
sys.path.insert(0, str(root))
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from reclab.search import latest, verify_sources, BM25, rrf
from reclab.retrieval import topk
receipt, result = latest()
verify_sources()
print(receipt['run_id'], result['scope'])
print('所有20项公开输入SHA已核验；数据/权重不进入Git。')

20261030T124927-d1467622 SciFact BEIR: all 5,183 documents, all 300 test queries; 200 lexicographically selected train queries; frozen MiniLM/TinyBERT, no neural fine-tuning. Unjudged documents treated as nonrelevant, not verified negatives.
所有20项公开输入SHA已核验；数据/权重不进入Git。

table = pd.DataFrame(result['rows']).set_index('method')
display(table.round(4))
fig, axes = plt.subplots(1, 2, figsize=(12, 4))
table[['ndcg@10','recall@10']].plot.barh(ax=axes[0], title='SciFact: relevance (binary qrels)')
table[['latency_p50_ms','latency_p95_ms']].plot.barh(ax=axes[1], title='Warm CPU query latency (ms)')
plt.tight_layout(); plt.show()
print('候选Recall@20:', result['rerank_candidate_recall@20'])
print('近似索引:', result['approximation'])
assert result['approximation']['dense_coarse12']['exact_top10_agreement'] == 1.0

Notebook 保存的输出 · 本页未执行

	recall@10	ndcg@10	mrr@10	hit_rate@10	recall@100	latency_p50_ms	latency_p95_ms	known_positive_fraction@10
method
bm25	0.7909	0.6617	0.6276	0.8100	0.8859	2.3056	3.0286	0.0873
dense	0.7883	0.6484	0.6068	0.8000	0.9250	13.2233	14.7887	0.0890
hybrid_rrf	0.8089	0.6855	0.6510	0.8267	0.9550	15.6706	17.3551	0.0907
linear_rerank	0.8107	0.7034	0.6747	0.8267	0.8752	17.1305	18.8177	0.0910
tinybert_rerank	0.7868	0.6670	0.6357	0.8000	0.8752	50.9085	55.7259	0.0890
dense_coarse2	0.6242	0.5153	0.4848	0.6367	0.6942	12.9576	14.7254	0.0723
dense_coarse12	0.7883	0.6484	0.6068	0.8000	0.9250	14.4022	16.2226	0.0890

<Figure size 1200x400 with 2 Axes>

候选Recall@20: 0.8752222222222222
近似索引: {'dense_coarse2': {'exact_top10_agreement': 0.7679999999999999, 'mean_candidates': 879.9366666666666}, 'dense_coarse12': {'exact_top10_agreement': 1.0, 'mean_candidates': 5183.0}}

toy_rankings = [[2, 1, 3], [3, 1, 2]]
for depth in [1, 2]:
    print('depth', depth, topk(rrf(toy_rankings, 3, depth=depth), 3))
# 查看正式算法源码；本格不自动训练。
import inspect
from reclab import search
print(inspect.getsource(search.rrf))

depth 1 [2, 3]
depth 2 [1, 2, 3]
def rrf(rankings, n_documents, depth=100, constant=60):
    scores = np.zeros(n_documents + 1)
    scores[0] = -np.inf
    for ranking in rankings:
        for rank, doc in enumerate(ranking[:depth], 1):
            scores[doc] += 1 / (constant + rank)
    # Documents outside the candidate union must never fill a truncated candidate list.
    scores[scores == 0] = -np.inf
    return scores

for failure in result['failures'][:3]:
    print('Query ID', failure['qid'])
    print('Relevant documents', failure['relevant_document_ids'])
    display(pd.DataFrame(failure['metrics']).T[['ndcg@10','mrr@10','recall@10']].round(3))
    # 本机 result['failures'] 可查看原查询/标题；Git只保留ID与精简指标。
# 数值上确认：在同一前20候选集内重排，Recall@100必须相同。
assert np.isclose(table.loc['linear_rerank','recall@100'], result['rerank_candidate_recall@20'])
assert np.isclose(table.loc['tinybert_rerank','recall@100'], result['rerank_candidate_recall@20'])

Query ID 1363
Relevant documents ['8290953']

Query ID 659
Relevant documents ['1215116']

Query ID 660
Relevant documents ['1215116']