Yesterday I wanted to find a conversation snippet in ChatGPT of a conversation I had maybe 1 or 2 weeks ago. Searching for a single keyword would have been enough to find it.
How is it possible that there's still no way to search through your conversations?
Check out https://recurse.chat (I'm the dev). You can import ChatGPT messages. It has almost instant full text search over thousands of chat sessions. Also supports llama.cpp, local embedding / RAG, and most recently bookmarks and nested folders.
Why they won't enable search for their main web user crowd is beyond me.
Perhaps they are just afraid of scale. With all their might, it's still possible that they can't estimate the scale and complexity of queries they might receive.
A user's personal data really does not have that much scale. Worst case they can cache everything locally. I've imported thousands of chat sessions into a local AI chat app's database, total storage is under 30MB. Full text search (with highlights and all) is almost instant.
They did staged rollouts for almost every recent feature.
I think it might be in their interest if you just ask the LLM again? Old answers might not be up to their current standards and they don't gain feedback from you looking at old answers
There are lots of ways to search through your conversations, just not through OpenAI's web interface. If you don't want to explore alternatives because you don't want to lose access to your conversations, I would argue you've just demonstrated to yourself why you should avoid proactively avoid vendor lock-in.
How is it possible that there's still no way to search through your conversations?