smart vector db
Project description
安装
pip install smart_vector
使用方法
from smart_vector import SmartVectorDB, Text2VecEmbeddingFunction
# 定义向量转化函数
text_vector = Text2VecEmbeddingFunction()
# 数据库连接
connect_dict = {
'host': 'xxx',
'port': 9030,
'user': 'xxxx',
'password': 'xxx',
'db': 'smartdb'
}
mydb = SmartVectorDB(db_config=connect_dict, load_host='xxx', text_vector=text_vector)
# 插入数据
mydb.add(collection='test', sr='测试', documents=['中国有一个北京', '北京在中国', '台湾是中国的'])
mydb.add(collection='test', sr='测试', documents=['中国有一个北京1', '北京在中国1'],
categorys=['A1', 'A1'], metadatas=[{'s': 's1'}, {'s': 's2'}])
# 查询
query = """天安门\ncollection='test' and sr = '测试' and document like '%北京%'\ndocument,sr,c,get_json_string(m, 'ans') as answer\n3"""
print(mydb.get(query))
#[['document', 'sr', 'c', 'distance'], ('中国有一个北京1', '测试', 'A1', 272.8261536366944), ('中国有一个北京', '测试', '', 272.8261536366944), ('中国有一个北京', '测试', '', 272.8261536366944)]
部署
pip install -r requirements.txt
python3 manage.py makemigrations
python3 manage.py migrate
python3 manage.py createsuperuser
#启动数据
python3 manage.py runserver 0.0.0.0:8000
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
smart_vector-1.1.4.tar.gz
(10.9 MB
view details)
Built Distribution
File details
Details for the file smart_vector-1.1.4.tar.gz
.
File metadata
- Download URL: smart_vector-1.1.4.tar.gz
- Upload date:
- Size: 10.9 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.0
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | a2d6bd34c6b355ca0838b8122e91a6b45337619afad0119e53e0c5bb71557f98 |
|
MD5 | a3ee1701e53a904f7392f3127f619824 |
|
BLAKE2b-256 | 34f933ff6c11a9f2637134f76dcd053ca74b8f08b5aa687a1de676fa903e118c |
File details
Details for the file smart_vector-1.1.4-py3-none-any.whl
.
File metadata
- Download URL: smart_vector-1.1.4-py3-none-any.whl
- Upload date:
- Size: 5.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.0
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 47b657f7d51317c0b5ccc74dd1a6671de19292df8fdeed4c6a7364abc9190738 |
|
MD5 | d6ec2befe439e9d0d0c05c3bee5d5d18 |
|
BLAKE2b-256 | 5be466896f35cf720660e99ac68363176ea811204d02d59602c849c456b4876a |