A vector search operation that retrieves all vectors within a specified distance threshold from the query vector, rather than a fixed number of nearest neighbors. Useful for finding all similar items above a quality threshold.
더 불러오는 중......
이 페이지에서
Range Search
Range Search retrieves all vectors within a specified distance/similarity threshold from a query, instead of returning a fixed k-nearest neighbors. Returns variable number of results based on similarity criteria.
"Find 10 nearest neighbors" → Always returns 10 results
"Find all vectors with similarity > 0.8" → Returns 0 to N results
# Qdrant
results = client.search(
collection_name="my_collection",
query_vector=query_embedding,
score_threshold=0.8, # Only results with score > 0.8
)
# May return 0, 5, 100, or any number of results
Not applicable (query type supported by most vector databases).
이와 관련된 다른 항목을 둘러보세요