通過百川智能向量化模型將文本轉換為向量

from dashvector import Client
import requests
from typing import List


# 調用百川智能向量化模型服務，將文本embedding為向量
def generate_embeddings(texts: List[str]):
    headers = {
      'Content-Type': 'application/json',
      'Authorization': 'Bearer {your-baichuan-api-key}'
    }
    data = {'input': texts, 'model': 'Baichuan-Text-Embedding'}
    response = requests.post('http://api.baichuan-ai.com/v1/embeddings', headers=headers, json=data)
    return [record["embedding"] for record in response.json()["data"]]


# 建立DashVector Client
client = Client(
    api_key='{your-dashvector-api-key}',
    endpoint='{your-dashvector-cluster-endpoint}'
)

# 建立DashVector Collection
rsp = client.create('baichuan-text-embedding', 1024)
assert rsp
collection = client.get('baichuan-text-embedding')
assert collection

# 向量入庫DashVector
collection.insert(
    ('ID1', generate_embeddings(['阿里雲向量檢索服務DashVector是效能、性價比具佳的向量資料庫之一'])[0])
)

# 向量檢索
docs = collection.query(
    generate_embeddings(['The best vector database'])[0]
)
print(docs)