[Bug]: RangeSearch result not as expected #34199
Assignees
Labels
kind/bug
Issues or changes related a bug
triage/accepted
Indicates an issue or PR is ready to be actively worked on.
Comments
cydrain
added
kind/bug
|
/assign |
1 task
yanliang567
added
triage/accepted
|
|
The IVF range search param "max_empty_result_buckets" is introduced in knowhere v2.3.0 (zilliztech/knowhere#455) |
|
/close |
|
@cydrain: Closing this issue. In response to this:
Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Is there an existing issue for this?
Environment
Current Behavior
Expected Behavior
should be able to get the result with "id=1613"
Steps To Reproduce
run this script: import random from pymilvus import ( connections, FieldSchema, CollectionSchema, DataType, Collection, utility ) _HOST = '127.0.0.1' _PORT = '19530' # Const names _COLLECTION_NAME = 'demo' _ID_FIELD_NAME = 'id_field' _VECTOR_FIELD_NAME = 'float_vector_field' # Vector parameters _BATCH = 100000 _ROWS = 10000 _DIM = 128 _INDEX_FILE_SIZE = 32 # max file size of stored index _NQ = 1 # Index parameters _METRIC_TYPE = 'COSINE' _INDEX_TYPE = 'IVF_SQ8' _NLIST = 1024 _NPROBE = 16 _TOPK = 10 # Create a Milvus connection def create_connection(): print(f"\nCreate connection...") connections.connect(host=_HOST, port=_PORT) print(f"\nList connections:") print(connections.list_connections()) # Create a collection named 'demo' def create_collection(name, id_field, vector_field): field1 = FieldSchema(name=id_field, dtype=DataType.INT64, description="int64", is_primary=True) field2 = FieldSchema(name=vector_field, dtype=DataType.FLOAT_VECTOR, description="float vector", dim=_DIM, is_primary=False) schema = CollectionSchema(fields=[field1, field2], description="collection description") collection = Collection(name=name, data=None, schema=schema, properties={"collection.ttl.seconds": 15}) print("\ncollection created:", name) return collection def has_collection(name): return utility.has_collection(name) # Drop a collection in Milvus def drop_collection(name): collection = Collection(name) collection.drop() print("\nDrop collection: {}".format(name)) # List all collections in Milvus def list_collections(): print("\nlist collections:") print(utility.list_collections()) def insert(collection, num, dim): data_idx = [i for i in range(num)] data_vec = [[random.random() for _ in range(dim)] for _ in range(num)] if num <= _BATCH: collection.insert([data_idx, data_vec]) else: i = 0 while i < num: n = min(_BATCH, num - i) collection.insert([data_idx[i:i+n], data_vec[i:i+n]]) i += n return data_vec def get_entity_num(collection): print("\nThe number of entity:") print(collection.num_entities) def create_index(collection, filed_name): index_param = { "index_type": _INDEX_TYPE, "params": {"nlist": _NLIST, "efConstruction": _EFC, "M": _M}, "metric_type": _METRIC_TYPE} collection.create_index(filed_name, index_param) print("\nCreated index:\n{}".format(collection.index().params)) def drop_index(collection): collection.drop_index() print("\nDrop index sucessfully") def load_collection(collection): collection.load() def release_collection(collection): collection.release() def search(collection, vector_field, id_field, search_vectors): search_param = { "data": search_vectors, "anns_field": vector_field, "param": {"metric_type": _METRIC_TYPE, "params": {"nprobe": _NPROBE, "radius": 0.8, "range_filter": 1.0, "max_empty_result_buckets": 65000}}, "limit": _TOPK, "expr": "id_field >= 0"} results = collection.search(**search_param) # results = collection.query(expr="id_field >= 0") for i, result in enumerate(results): print("\nSearch result for {}th vector: ".format(i)) for j, res in enumerate(result): print("Top {}: {}".format(j, res)) def set_properties(collection): collection.set_properties(properties={"collection.ttl.seconds": 1800}) def main(): # create a connection create_connection() # drop collection if the collection exists if has_collection(_COLLECTION_NAME): drop_collection(_COLLECTION_NAME) # create collection collection = create_collection(_COLLECTION_NAME, _ID_FIELD_NAME, _VECTOR_FIELD_NAME) # alter ttl properties of collection level set_properties(collection) # show collections list_collections() # insert 10000 vectors with 128 dimension vectors = insert(collection, _ROWS, _DIM) collection.flush() # get the number of entities get_entity_num(collection) # create index create_index(collection, _VECTOR_FIELD_NAME) # load data to memory load_collection(collection) # search query_vec = [[i + j for i in range(_DIM)] for j in range(_NQ)] search(collection, _VECTOR_FIELD_NAME, _ID_FIELD_NAME, query_vec) # release memory # release_collection(collection) # drop collection index # drop_index(collection) # drop collection # drop_collection(_COLLECTION_NAME) if __name__ == '__main__': main()Milvus Log
No response
Anything else?
No response
The text was updated successfully, but these errors were encountered: