Karl Jensen

I ran into this as well. Had to add a `pages/.keep` for deployment.

I use https://github.com/dqbd/tiktoken for our production application. I've noticed that it gets very slow as the number of tokens you are counting goes up, so if you try and count...

Update: I have done some testing using the `ai-chatbot` project deployed to Vercel with some logging. Tokens are not generated on the server, in the background, after cancellation. ----- I...

There are a lot of moving pieces, but I have successfully cancelled the request using both Deno and Fastify with Node 20. I have my own Open AI API account...

It looks like this was released today. https://github.com/vercel-labs/ai-chatbot It has a stop-generating button https://chat.vercel.ai/ which makes sense since the SDK has a stop API through the hooks. I guess my...

I was able to spend some time testing this tonight. I deployed a version of the ai-chatbot application with some additional logging. I am confident the cancellation works as intended...

Thank you for all of your work on this @jridgewell. This closes a long-standing support ticket I opened in April and allows me to give my client some options.

Thank you for taking a look. I didn't imagine anything was being done specifically with types. Round trips sounds like a good path to investigate since I noticed adding 1...

I had a bit of time to point my development instance of supavisor to an eu-west-2 supabase DB. These are the logs from the same query with three different column...

I have been able to reproduce this with PgBouncer now so it is seeming more likely that this has to do with CITEXT and transaction mode that we use for...