本笔记本包含一些有用的代码片段，可用于通过OpenAI API使用text-embedding-3-small模型嵌入文本。
from openai import OpenAI
client = OpenAI()
embedding = client.embeddings.create(
input="Your text goes here", model="text-embedding-3-small"
).data[0].embedding
len(embedding)
1536
建议使用'tenacity'包或其他指数退避实现来更好地管理API速率限制，因为过快过多地调用API可能会触发速率限制。使用以下函数可确保您尽可能快地获取嵌入向量。
# Negative example (slow and rate-limited)
from openai import OpenAI
client = OpenAI()
num_embeddings = 10000 # Some large number
for i in range(num_embeddings):
embedding = client.embeddings.create(
input="Your text goes here", model="text-embedding-3-small"
).data[0].embedding
print(len(embedding))# Best practice
from tenacity import retry, wait_random_exponential, stop_after_attempt
from openai import OpenAI
client = OpenAI()
# Retry up to 6 times with exponential backoff, starting at 1 second and maxing out at 20 seconds delay
@retry(wait=wait_random_exponential(min=1, max=20), stop=stop_after_attempt(6))
def get_embedding(text: str, model="text-embedding-3-small") -> list[float]:
return client.embeddings.create(input=[text], model=model).data[0].embedding
embedding = get_embedding("Your text goes here", model="text-embedding-3-small")
print(len(embedding))1536