通过Jina Embeddings模型将文本转换为向量

from dashvector import Client
import requests
from typing import List
# 调用Jina Embeddings v2模型，将文本embedding为向量
def generate_embeddings(texts: List[str]):
    headers = {
      'Content-Type': 'application/json',
      'Authorization': 'Bearer {your-jina-api-key}'
    }
    data = {'input': texts, 'model': 'jina-embeddings-v2-base-zh'}
    response = requests.post('https://api.jina.ai/v1/embeddings', headers=headers, json=data)
    return [record["embedding"] for record in response.json()["data"]]
    
# 创建DashVector Client
client = Client(
    api_key='{your-dashvector-api-key}',
    endpoint='{your-dashvector-cluster-endpoint}'
)
# 创建DashVector Collection
rsp = client.create('jina-text-embedding', 768)
assert rsp
collection = client.get('jina-text-embedding')
assert collection
# 向量入库DashVector
collection.insert(
    ('ID1', generate_embeddings(['阿里云向量检索服务DashVector是性能、性价比具佳的向量数据库之一'])[0])
)
# 向量检索
docs = collection.query(
    generate_embeddings(['The best vector database'])[0]
)
print(docs)