Hello, community. I am trying to compare Add 002’s embeddings against other common vectorizers, and while Ada 002 does seem to be better than the other metrics against which I’ve tested it (e.g., TF-IDF, Euclidean Distance, Jaccard Distance, and various BERT embedding models), the scale seems odd t…

Embedding Results Scale Seems Off

Foxalabs June 25, 2023, 9:26pm 2

If you are seeing values from +/- 0.1 then you’re not renormalising back to unit vectors, see this post Some questions about text-embedding-ada-002’s embedding - #41 by curt.kennedy

Topic		Replies	Views
Embeddings and Cosine Similarity API	20	13481	February 25, 2024
Question on text-embedding-ada-002 API	12	6185	December 24, 2023
Quality of embeddings using davinci-001 embeddings model vs. ada-002 model API embeddings	15	3639	April 9, 2024
Semantic Textual Similarity - undifferentiated similarities API embeddings , semantic-search	5	1422	December 24, 2023
Transitioning to the new embeddings models from ada API embeddings	8	4884	January 27, 2024