Switch to the recommended model (text-embedding-ada-002)

[bkowshik]

NOTE: NLP newbie here, happy to take any feedback; have written about my thought-process for this change below.

---

Was looking at the documentation for embedding model in Python. Then, when I had a sample working, the length of the embedding at 12,288 was too long to what the current trend is and made me look into this in a little more detail. Then came across relevant blog posts and documentation based on which I think this is the right change.

Ref: https://openai.com/blog/new-and-improved-embedding-model

The new model, text-embedding-ada-002, replaces five separate models for text search, text similarity, and code search, and outperforms our previous most capable model, Davinci, at most tasks, while being priced 99.8% lower.

Ref: https://platform.openai.com/docs/guides/embeddings/what-are-embeddings

We recommend using text-embedding-ada-002 for nearly all use cases. It’s better, cheaper, and simpler to use. Read the blog post announcement.

[logankilpatrick]

Thanks for flagging this, I made a new PR and will push this change through there!