You probably shouldn't use OpenAI's embeddings

3 years ago (iamnotarobot.substack.com)

Is someone doing embeddings<>embeddings mapping?

For example, mapping embeddings of Llama to GPT-3?

That way you can see how similar the models “understand the world”.

  • I'm curious about this as well. There are potentially many different versions of embedding models used in production and correlating different versions together could be very important.

  • I’d be interested to see this as well. I guess you can make a test and see what happens. Ping me if you do!

Could anyone point me towards a relatively beginner-friendly guide to do something like

>download all my tweets (about 20k) and build a semantic searcher on top ?

How can utilize 3rd party embeddings with OpenAI's LLM API? Am I correct to understand from this article that this is possible?

I've done some quick-and-dirty testing with OpenAI's embedding API + Zilliz Cloud. The 1st gen embeddings leave something to be desired (https://medium.com/@nils_reimers/openai-gpt-3-text-embedding...), but the 2nd gen embeddings are actually fairly performant relative to many open source models with MLM loss.

I'll have to dig out the notebook that I created for this, but I'll try to post it here once I find it.

  • Please do and thanks in advance for any insights you can provide -- it would be great to understand any benchmarking improvement with ada-002 from your previous findings, and whether you tested the specific OpenAI text-search-*-{query,doc} models as a comparison for large document search.

Very interested in this - I've been using embeddings / semantic search doing information retrieval from PDFs, using ada-002, and have been impressed by the results in testing.

The reasons the article listed, namely a) lock-in and b) cost, have given me pause with embedding our whole corpus of data. I'd much rather use an open model but don't have much experience in evaluating these embedding models and search performance - still very new to me.

Like what you did with ada-002 vs Instruct XL, has there been any papers or prior work done evaluating the different embedding models?

It’s fine to use their embeddings for a proof of concept, but since you don’t own it, you probably shouldn’t rely on it because it could go away at any time.

  • Couldn’t you make that argument against all SaaS?

    • Well some SaaS purists may believe that to be true about Microsoft Office 365. Hence we have, Microsoft Office 2021.

      (Although there is a lot more advantages to just having Office 2021 like the flat fee)

    • Yes and no. Sometimes you get contracts that require “source code escrow” so that companies can run your source if you ever go out of business.