Show HN: An interactive visualization of a semantic cache (semanticcachehit.com)

2 points by interbolt_colin 2y ago ↗ HN

This uses the new text-embedding-3-large model from OpenAI and UMAP for the clustering. All the prompts in the visual were generated using GPT-4.

1 comment

[ 3.1 ms ] story [ 11.6 ms ] thread

shouche 2y ago ↗

Hey. Its a good practical application, especially to reduce cost. But at about 0.6 similarity, I get some cache hit. Maybe with more examples and for a high use app, the cache hit would increase based on a higher similarity scores.

Still early days on this I guess, but any observations that can help improve the hit rates?