题意：Azure OpenAI 嵌入与 OpenAI 嵌入
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 的 text-embedding-ada-002 模型进行嵌入部署时，得到的结果与直接使用 OpenAI 的结果不同？即使文本相同、模型相同，但在向量空间中，两者的结果却相差甚远。
What's recommended for embeddings?
对于嵌入（embeddings）有什么建议？
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
标签：嵌入,Embeddings,text,OpenAI,ada,Azure,embeddings From： https://blog.csdn.net/suiusoar/article/details/143639367