milvus-client
copied
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Readme
Files and versions
1.2 KiB
1.2 KiB
ANN Search Operator: Milvus
author: junjie.jiangjjj
Desription
Search embedding in Milvus, please make sure you have inserted data to Milvus Collection.
Code Example
Please make sure you have inserted data into Milvus, refer to ann_insert.milvus_client and load the collection to memory.
from towhee.dc2 import pipe, ops
p = pipe.input('vec') \
.map('vec', ('id', 'score'), ops.ann_insert.milvus_client(host='127.0.0.1', port='19530', collection_name='textdb')) \
.output('id', 'score')
# call pipeline
p(vec_data)
from towhee.dc2 import pipe, ops
# search additional info url:
p = pipe.input('vec') \
.map('vec', ('id', 'score', 'url'), ops.ann_insert.milvus_client(host='127.0.0.1', port='19530', collection_name='textdb', output_fields=['url'])) \
.output('id', 'score', 'url')
Factory Constructor
Create the operator via the following factory method:
ann_search.milvus_client(host='127.0.0.1', port='19530', collection_name='textdb')
1.2 KiB
1.2 KiB
ANN Search Operator: Milvus
author: junjie.jiangjjj
Desription
Search embedding in Milvus, please make sure you have inserted data to Milvus Collection.
Code Example
Please make sure you have inserted data into Milvus, refer to ann_insert.milvus_client and load the collection to memory.
from towhee.dc2 import pipe, ops
p = pipe.input('vec') \
.map('vec', ('id', 'score'), ops.ann_insert.milvus_client(host='127.0.0.1', port='19530', collection_name='textdb')) \
.output('id', 'score')
# call pipeline
p(vec_data)
from towhee.dc2 import pipe, ops
# search additional info url:
p = pipe.input('vec') \
.map('vec', ('id', 'score', 'url'), ops.ann_insert.milvus_client(host='127.0.0.1', port='19530', collection_name='textdb', output_fields=['url'])) \
.output('id', 'score', 'url')
Factory Constructor
Create the operator via the following factory method:
ann_search.milvus_client(host='127.0.0.1', port='19530', collection_name='textdb')