向量 embeddings 入门：理解 AI 的数据表示

# 文本转向量
text = "Hello, world!"
embedding = [0.1, -0.3, 0.5, ...]  # 1536 维向量

import numpy as np

def cosine_similarity(a, b):
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

# 相似文本
similarity = cosine_similarity(embedding1, embedding2)

from openai import OpenAI

client = OpenAI()

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="Hello, world!"
)

embedding = response.data[0].embedding
print(len(embedding))  # 1536

# sentence-transformers
from sentence_transformers import SentenceTransformer

model = SentenceTransformer('all-MiniLM-L6-v2')
embedding = model.encode("Hello, world!")