题意:Azure OpenAI 嵌入与 OpenAI 嵌入的比较
问题背景:
Is anyone getting different results from Azure OpenAI embeddings deployment using text-embedding-ada-002 than the ones from OpenAI? Same text, same model, and the results are considerably far in the vector space.
是否有人在使用Azure OpenAI部署的text-embedding-ada-002模型进行嵌入时,得到的结果与直接使用OpenAI得到的结果不同?即使是相同的文本和相同的模型,结果在向量空间中的差异也相当大。
What's recommended for embeddings? 嵌入(embeddings)的推荐是什么?
问题解决:
Current AOAI's text-embedding-ada-002 is somewhat different from OAI's. Our model currently supports only 2K tokens, while OAI can support 8K tokens.
当前AOAI的text-embedding-ada-002模型与OAI的有所不同。我们的模型目前仅支持2000个词元(tokens),而OAI可以支持8000个词元。
Azure OpenAI doesn’t allow batched embeddings. You need to use multiple simultaneous requests. If you hit the maximum req/min, you will need to ask Azure a quota increase.
Azure OpenAI 不允许批量嵌入。您需要使用多个同时请求。如果您达到每分钟最大请求数限制,您需要向Azure申请配额增加。