探索向量空间

使用 OpenAI API 的 Embeddings 入门

Emmanuel Pire

Senior Software Engineer, DataCamp

示例：为标题生成嵌入

articles = [
    {"headline": "Economic Growth Continues Amid Global Uncertainty", "topic": "Business"},
    {"headline": "Interest rates fall to historic lows", "topic": "Business"},
    {"headline": "Scientists Make Breakthrough Discovery in Renewable Energy", "topic": "Science"},
    {"headline": "India Successfully Lands Near Moon's South Pole", "topic": "Science"},
    {"headline": "New Particle Discovered at CERN", "topic": "Science"},
    {"headline": "Tech Company Launches Innovative Product to Improve Online Accessibility", "topic": "Tech"},
    {"headline": "Tech Giant Buys 49% Stake In AI Startup", "topic": "Tech"},
    {"headline": "New Social Media Platform Has Everyone Talking!", "topic": "Tech"},
    {"headline": "The Blues get promoted on the final day of the season!", "topic": "Sport"},
    {"headline": "1.5 Billion Tune-in to the World Cup Final", "topic": "Sport"}
]

示例：为标题生成嵌入

包含标题及其嵌入的字典列表。

为多个输入生成嵌入

headline_text = [article['headline'] for article in articles]
headline_text

["Economic Growth Continues Amid Global Uncertainty",
 ...,
 "1.5 Billion Tune-in to the World Cup Final"]

response = client.embeddings.create(
  model="text-embedding-3-small",
  input=headline_text
)
response_dict = response.model_dump()

批量处理比多次 API 调用更高效

[...]

'data': [
    {
      "embedding": [-0.017142612487077713, ..., -0.0012911480152979493],
      "index": 0,
      "object": "embedding"
    },
    {
      "embedding": [-0.032995883375406265, ..., -0.0028605300467461348],
      "index": 1,
      "object": "embedding"
    },
    ...
  ]

[...]

为多个输入生成嵌入

articles = [
    {"headline": "Economic Growth Continues Amid Global Uncertainty", "topic": "Business"},
     ...
]

for i, article in enumerate(articles):

    article['embedding'] = response_dict['data'][i]['embedding']


print(articles[:2])

[{'headline': 'Economic Growth Continues Amid Global Uncertainty',
  'topic': 'Business',
  'embedding': [-0.017142612487077713, ..., -0.0012911480152979493]}
 {'headline': 'Interest rates fall to historic lows',
  'topic': 'Business',
  'embedding': [-0.032995883375406265, ..., -0.0028605300467461348]}]

嵌入向量有多长？

"在全球不确定性中，经济增长持续"

len(articles[0]['embedding'])

"科技公司推出创新产品以提升可访问性"

len(articles[5]['embedding'])

始终返回 1536 个数！

降维与 t-SNE

多种技术可用于_降维_
t-SNE（t 分布随机邻域嵌入）

¹ https://www.datacamp.com/tutorial/introduction-t-sne

实现 t-SNE

from sklearn.manifold import TSNE
import numpy as np


embeddings = [article['embedding'] for article in articles]


tsne = TSNE(n_components=2, perplexity=5)

embeddings_2d = tsne.fit_transform(np.array(embeddings))

n_components：输出维度数
perplexity：算法参数，须小于数据点数量
会产生信息损失

¹ https://www.datacamp.com/tutorial/introduction-t-sne

可视化嵌入

import matplotlib.pyplot as plt

plt.scatter(embeddings_2d[:, 0], embeddings_2d[:, 1])


topics = [article['topic'] for article in articles]
for i, topic in enumerate(topics):
    plt.annotate(topic, (embeddings_2d[i, 0], embeddings_2d[i, 1]))

plt.show()

可视化嵌入

_相似_文章会聚在一起！
模型捕捉到_语义_含义

接下来：计算相似度

一个二维向量空间图，显示同一情感和主题的评论在向量空间中更接近。

开始练习吧！

使用 OpenAI API 的 Embeddings 入门