Author(s): Gao Dalie (高達烈)

Originally published on Towards AI.

if you are creating an advanced bot or automation with Open AI, you will likely need to check how similar two or more pieces of text are. using embedding helps us do this.

at the end of the Post, you will be able to understand how to use text-embedding-3 and demonstrate how text-embedding-3 improved the performance as well as some hands-on experience by building out a project that uses text-embeddings-3 to make sure you understand at the end of this Post

If you like this topic and you want to support me:

Clap my article 50 times; that will really help me out.U+1F44FFollow me on Medium and subscribe to get my latest articleU+1FAF6

Open AI has Announced a new embedding model called text-embedding-3. This model includes two new embedding models:

text-embedding-3-small: small and efficienttext-embedding-3-large: Larger and more powerful

“text-embedding-3-small” has an average score of 31.4% to 44.0% on the multilingual search benchmark (MIRACL) compared to the previous model “text-embedding-ada-002”, a benchmark for English tasks. (MTEB) improved from 61.0% to 62.3%.

Also, “text-embedding-3-large” is a new large model that creates embeddings of up to 3072 dimensions, with an average score of 54.9% from 31.4% on MIRACL and 64.6% from 61.0% on MTEB. has improved.

the price is also 5… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI