qingdan/Qdembedding.py

import pymongo
import pandas
import json
from pymongo import MongoClient
import os
import re
import time
from openai import OpenAI
import numpy as np
client = MongoClient()
db = client["dinge"]
collection = db["de-collection"]
from subdir import service
##print(collection.find_one({"DEBH": "3-94"}))




client_ = OpenAI(
    api_key='sk-7c7be9c8dda84cb98901c98e0c74a2d8',  # 如果您没有配置环境变量，请在此处用您的API Key进行替换
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"  # 百炼服务的base_url
)

array1 = np.array([])
array2 = np.array([])
array3 = np.array([])
array4 = np.zeros((1,1024))

count = 0
qd = pandas.read_csv("JD_QingDanXM_parent.csv")
for i in range(len(qd)):
    row = qd.iloc[i] 
    if row['fbcch'].item() == 4:
   
        array1 = np.append(array1, row['qdbh'])
        array2 = np.append(array2, row['xmmc'])
        array3 = np.append(array3, row['parent'])
   
        completion = client_.embeddings.create(
    model="text-embedding-v4",
    input='类别： ' + row['parent'] + ", 内容：" + row["xmmc"],
    dimensions=1024, # 指定向量维度（仅 text-embedding-v3及 text-embedding-v4支持该参数）
    encoding_format="float"
   )
   ##print(completion.data[0].embedding)
        array4 = np.vstack((array4, [completion.data[0].embedding]))
        count = count + 1
        print(count)
        time.sleep(0.5)
   

con = np.stack((array1, array2, array3))
con = np.transpose(con)
np.save('qd_content.npy', con)
np.save('qd_embedding.npy', array4[1:])