OpenAI - Response not received in 25 seconds.

[chuchi]

Hello.

I am having some problems using Open AI. From time to time I get the error Response not received in 25 seconds. Learn more: https://forum.pabbly.com/threads/pa...rror-response-not-received-in-25-seconds.855/. This is because in 25 seconds sometimes Open AI doesn't have time to write all the content. How can I solve this? How can I leave it longer than 25 seconds?

Thank you very much.

 

[Pabblymember11]

Hey @chuchi

In Pabbly, 15 seconds is the maximum timeout that can be used. For the time being, we output a message for a maximum of 15 seconds.

As of right now, we are extending the 15-second soft response time restriction for your APIs by an extra 10-second buffer for everyone. For your request to react and execute, you will have a total of 25 seconds.

In that case, we cut off the connection for that action step and display the message "Response not received in 15 seconds." If the response takes longer than the allotted 25 seconds, we close the connection.

 

[chuchi]

Hello @Supreme

And how could I increase that time? It is necessary for OpenAI to work properly.

Thanks!

 

[Pabblymember11]

Hey @chuchi

Currently, the 15-second response capturing works globally in Pabbly Connect and cannot be changed.

Perhaps you might be using the application extensively or the data you are passing couldn't process by the application itself under the time bracket.

 

[deepak9780097800]

I also wish to increase this time from 25 to 50 sec. How is it possible?

 

[Pabblymember11]

Hey @deepak9780097800

It is not possible to change the response time to capture the API response from the application.

We waited for 25 seconds for the response to be received from the external software before we outputted the "Response not received" message.

 

[Pabblynaut]

For OpenAI, the settings don't make sense.

In Pabbly, it says that "Enter the maximum number of tokens to generate the content. Max limit is up to 2048 tokens. Default value is 256."

But everything I have tried over 900 tokens consistently fails. Not every time, but like every other time.

Is this supposed to work? It seems to always time out

 

[Pabblymember11]

Hey @Pabblynaut

Could you please share the name of the workflow where you have tried the same API request?

 

[erez]

Same is happening for me,
Can ask for Tokens from open AI of more than 500tokens
cause it's more than 25 sec

PLEASE OPEN OPENAI to wait for atleast 50 sec

 

[Pabblymember11]

Hey @erez

The application's API response time cannot be changed in order to collect responses from the server.

Before outputting the "Response not received" message, we waited for the external software to respond for 25 seconds.

 

[omp]

I have the same issue. You can try using it at https://beta.openai.com/playground
it normally takes more than 25 seconds for a long article.
As openAI become more popular, more user will face the same issue.
Please consider finding a solution, thanks.

 

[Pabblymember11]

Hey @omp @erez

Please check the limit of tokens from the Open AI end and if that amount of tokens were executable from their end then it will also be processed accordingly.

Since the counting of tokens was different from their end, kindly check that once and then try again.

 

[erez]

Hey @erez

The application's API response time cannot be changed in order to collect responses from the server.

Before outputting the "Response not received" message, we waited for the external software to respond for 25 seconds.

Hello,
I think you sould extend the time to atleast 40-50 second.
Like omp mention, it's will be worst with time, and we cant relay on this service.
I have checked as well with zapier, and they allow for OPENAI 60 second, so i think you sould allow at least for this app more wating time, other wise there is now use for it, on a larger scale

 

[Pabblynaut]

It is not true that if a request works in the Playground, it will automatically work in Pabbly. Maybe the reason is that the load on OpenAI servers varies throughout the day, so sometimes what should take 15 seconds takes 30 seconds? Anyhow, I think you should do like Zapier and allow for 60 seconds for OpenAI, so we can build integrations with it that can be trusted.

 

[erez]

yes, maybe you need to charge differntly for the OPENAI app, since, it the reason why many clinets join Pabbly, i dont care the price. it's just need to work

 

[erez]

Maybe another option, since we know it's take time, so after sending the request to open AI,
You can add a option to add a delay, like this if the token is long, we can add 10-15 delay, before wating to the response.
Hope this is clear,
But in this way, if you creat long Token, we can wait even 30 sec before starting the wating,

 

[PabblyMember4]

We are checking with the technical team and we will get back to you with more updates.

 

[smugo]

We are checking with the technical team and we will get back to you with more updates.

Any news here?
The whole process and all your tutorials about auto blogging really make no sense at all if we can only produce 100 words output...

 

[PabblyMember4]

Hey @smugo

We have checked the issue from the team and got a response that they will consider the decision to fetch the response from OpenAI in 25 seconds and will try to implement a bigger time frame. As of now, there is no ETA for this. We will keep you updated on the status of this conversation.

 

[Pabblynaut]

It would be great if Pabbly had an option to yes/no auto-retry task x times before continuing a flow. This way, if for example Openai step times out, it would auto-retry and hopefully succeed before continuing the rest of the flow