تصفية البيانات الوصفية للبحث الهجين

metadata = {
    'tenant_id': 'acme',
    'language': 'en',
    'source': 'help-docs',
    'updated_at': '2024-08-12',
    'tags': ['shipping', 'returns']
}
for k, v in metadata.items():
    print(f"{k}: {v}")

results = index.query(
    vector=query_vec,
    top_k=5,
    filter={
        'tenant_id': 'acme',
        'language': 'en'
    }
)

filter = {
    'updated_at': {'$gte': '2024-01-01'},
    'score': {'$gt': 0.5}
}
print(filter)

filter = {
    'tags': {'$in': ['shipping', 'returns']},
    'archived': {'$ne': True}
}
print(filter)

from qdrant_client.models import Filter, FieldCondition, MatchValue

filter = Filter(must=[
    FieldCondition(key='tenant_id', match=MatchValue(value='acme')),
    FieldCondition(key='language', match=MatchValue(value='en'))
])

results = client.search(
    collection_name='docs',
    query_vector=query_vec,
    query_filter=filter,
    limit=5
)

def rrf(vec_results, bm25_results, k=60):
    scores = defaultdict(float)
    for rank, doc in enumerate(vec_results):
        scores[doc.id] += 1 / (k + rank)
    for rank, doc in enumerate(bm25_results):
        scores[doc.id] += 1 / (k + rank)
    return sorted(scores.items(), key=lambda x: -x[1])

def search(query, tenant_id, top_k=5):
    return index.query(
        vector=embed(query),
        top_k=top_k,
        filter={'tenant_id': tenant_id}
    )

metadata = {
    'visibility': 'public',         # or 'internal', 'restricted'
    'department': 'engineering',
    'allowed_roles': ['engineer', 'manager']
}

# At query time:
filter = {'allowed_roles': {'$contains': current_user_role}}

candidates = index.query(vector=query_vec, top_k=50)
scored = [
    (c.score * recency_factor(c.metadata['updated_at']), c)
    for c in candidates
]
scored.sort(reverse=True)
final = scored[:5]