You probably shouldn't use OpenAI's embeddings
iamnotarobot.substack.com
You probably shouldn't use OpenAI's embeddings
1–10 of 31 posts
Re: You probably shouldn't use OpenAI's embeddings
#2Is someone doing embeddingsembeddings mapping?
For example, mapping embeddings of Llama to GPT-3?
That way you can see how similar the models “understand the world”.
Re: You probably shouldn't use OpenAI's embeddings
#3Could 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?
Re: You probably shouldn't use OpenAI's embeddings
#4The heat map of availability time, 98.58 (Jan), 99.07 (Feb), and 99.71 (Mar) trends upwards.
Re: You probably shouldn't use OpenAI's embeddings
#5Could 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?
That's exactly what I did here. https://github.com/dbasch/semantic-search-tweets
Re: You probably shouldn't use OpenAI's embeddings
#6Very 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?
Re: You probably shouldn't use OpenAI's embeddings
#7Could 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?
langchain and llama-index are two big opensource projects which are great for buildign this type of thing.
https://github.com/mayooear/gpt4-pdf-chatbot-langchain for example
Re: You probably shouldn't use OpenAI's embeddings
#8Could 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?
That's exactly what I did here. https://github.com/dbasch/semantic-search-tweets
Thank you! Comparing this and the link the other commenter posted, what handles the actual search querying? Does instructor-xl include an LLM in addition to the embeddings? The other commenter's repo uses Pinecone for the embeddings and OpenAI for the LLM.
My apologies if I am completely mangling the vocabulary here - I have an, at best, rudimentary understanding of this stuff that I am trying to hack my education on.
Edit: If you're at the SF meetup tomorrow, I'd happily buy you a beverage in return for this explanation :)
Re: You probably shouldn't use OpenAI's embeddings
#9Could 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?
langchain and llama-index are two big opensource projects which are great for buildign this type of thing. https://github.com/mayooear/gpt4-pdf-chatbot-langchain for example
Cheers, thank you!
Re: You probably shouldn't use OpenAI's embeddings
#10It’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.