基于向量数据相似度检索

import tcvectordb
from tcvectordb.model.enum import FieldType, IndexType, MetricType, ReadConsistency
from tcvectordb.model.index import Index, VectorIndex, FilterIndex, HNSWParams
from tcvectordb.model.document import Document, Filter, SearchParams

#create a database cleint object
client = tcvectordb.VectorDBClient(url='http://10.0.X.X', username='root', key='eC4bLRy2va******************************', read_consistency=ReadConsistency.EVENTUAL_CONSISTENCY, timeout=30)

db = client.database('db-test')
coll = db.collection('book-vector')

# search topn similary documents with filter
# vectors 指定了检索的向量数据
# filter 指定了过滤条件
# params 指定索引类型对应的查询参数，HNSW 类型需要设置 ef，指定查询的遍历范围;IVF 系列需要设置 nprobe,指定查询的单位数量
# retrieve_vector 指定是否输出向量字段
# limit 指定返回最相似的 Top K 条结果。如果插入的数据不足 K 条，则返回实际插入的 Document 数量。
# output_fields 指定输出字段       
doc_lists = coll.search(
            vectors=[[0.3123, 0.43, 0.213],[0.315, 0.4, 0.216],[0.40, 0.38, 0.26]],
            filter=Filter(Filter.In("bookName",["三国演义", "西游记"]) and Filter.Include ("tags",["曹操", "孙悟空"])),
            params=SearchParams(ef=200),
            retrieve_vector=True,
            limit=3,
            output_fields=['bookName','author']
        )        
        
for i, docs in enumerate(doc_lists):
                print(i)
                for doc in docs:
                        print(doc)


{'id': '0001', 'vector': [0.21230000257492065, 0.23000000417232513, 0.21299999952316284], 'score': 0.971423, 'bookName': '三国演义', 'author': '罗贯中'}
{'id': '0002', 'vector': [0.21230000257492065, 0.2199999988079071, 0.21299999952316284], 'score': 0.966884, 'bookName': '西游记', 'author': '吴承恩'}
1
{'id': '0001', 'vector': [0.21230000257492065, 0.23000000417232513, 0.21299999952316284], 'score': 0.978463, 'author': '罗贯中', 'bookName': '三国演义'}
{'id': '0002', 'vector': [0.21230000257492065, 0.2199999988079071, 0.21299999952316284], 'score': 0.974783, 'author': '吴承恩', 'bookName': '西游记'}
2
{'id': '0001', 'vector': [0.21230000257492065, 0.23000000417232513, 0.21299999952316284], 'score': 0.986069, 'bookName': '三国演义', 'author': '罗贯中'}
{'id': '0002', 'vector': [0.21230000257492065, 0.2199999988079071, 0.21299999952316284], 'score': 0.985201, 'bookName': '西游记', 'author': '吴承恩'}