I have a dataset with over 80k random text messages and I embedded each of the messages with ‘text-embedding-ada-002’. When I pick a message at random, and find the top 10 messages close (+1 dot prodoct), far away (-1 dot product) and orthogonal (0 dot product), all I get are embeddings that are at…

Expected Angular Differences in Embedding Random Text?

Topic		Replies	Views
Question on text-embedding-ada-002 API	12	6485	December 24, 2023
Embedding Results Scale Seems Off API embeddings , ada	8	5232	December 24, 2023
Embeddings and Cosine Similarity API	20	14867	February 25, 2024
Fine-tuning or update embedding of a String Community embeddings	8	1857	August 14, 2023
Splitting text into chunks versus reducing the text API embeddings , ada	9	2952	April 5, 2024