Getting function invocation timeout in serverless function streaming about ai HOT 10 CLOSED

Can we have a separate documentation for serverless functions too?

from ai.

@Sahas can you

• Check how long your function takes to run
• Check the free tier how long serveless funcitons run (normally 10s)
• Check paid tier how long serveless functions run (normally 60s)

from ai.

@peterokwara I've tried using calling same function with and without edge.

1. With edge, the stream started in 2s & stream ended in 20s.
2. With serverless, I'm not getting any response as the function invocation is getting timedout

from ai.

I'm guessing this is because of #97 ("Stream never closes with LangChainStream using postman"). Can you try one of the workarounds in that issue and see if that solves this problem? (You could also check in your dev console if the request is stuck open, even after new messages stop arriving).

from ai.

Will check, but any idea why it impacts only serverless functions and not edge function?

from ai.

@jaredpalmer / @shuding can you look into this issue please

from ai.

any idea why it impacts only serverless functions and not edge function?

No, but I'm less familiar with the edge stuff. I thought perhaps because of the different limits and runtimes, the above issue could possibly express itself this way.

from ai.

I think there are two issues here:

1. Streaming langchain is broken for certain models (see #205)
2. You are encountering a timeout. On the hobby tier of Vercel, serverless functions timeout after only 10 seconds.

closing as a duplicate, please reply back if you think I missed something.

from ai.

@MaxLeiter

1. Why is it breaking only for serverless functions and not edge functions?
2. I'm using vercel pro account, so the timeout is 60s.

from ai.

I've used this code

https://github.com/e-roy/openai-functions-with-langchain/blob/main/src/app/api/news-langchain/route.ts

But then i removed

export const runtime = "edge"; i think this means I am not using edge

And I don't get the same issues.
I am using vercel pro. I am using gpt-3.5-turbo-0613

from ai.