Live data from Hacker News

Show HN: An interactive visualization of a semantic cache

1–2 of 2 posts

Show HN: An interactive visualization of a semantic cache

Post by interbolt_colin » Fri, Feb 02, 2024, 9:22 PM UTC

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.

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

Re: Show HN: An interactive visualization of a semantic cache

Post by shouche » Sun, Feb 04, 2024, 7:50 AM UTC

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?

Post reply on HN