OpenAI - Response not received in 25 seconds.

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/pabbly-connect-timeout-limit-error-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.

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.

Hello @Supreme

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

Thanks!

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.

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

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.

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

Hey @Pabblynaut

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

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

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.

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.

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.

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.

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.

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

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,

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

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

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.

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

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.

Thanks for your reply.
An ETA would be really great. And I'm talking about hours or 1-2 days here, since the whole process is really useless otherwise. You have many tutorials online about auto generating content and publishing it with OpenAI. How did you guys do it then?

What is the prompt that you are using to generate the output?

In most cases the 25 seconds limit works perfectly fine unless you are generating a very complex response.

I would have to say that currently we won't be able to wait more than 25 seconds for the response to arrive from an external application.

We have also written a guide on how to better handle the wait time for external application that you can recommend to OpenAI team.

We talked internally to the tech team today itself and somehow the limit of 25 seconds is not planned to be increased for now.

What is the prompt that you are using to generate the output?

In most cases the 25 seconds limit works perfectly fine unless you are generating a very complex response.

I would have to say that currently we won't be able to wait more than 25 seconds for the response to arrive from an external application.

We have also written a guide on how to better handle the wait time for external application that you can recommend to OpenAI team.

We talked internally to the tech team today itself and somehow the limit of 25 seconds is not planned to be increased for now.

I don't think that the prompt is too complex. But for sure it's more than "keyword". Because that returns pretty useless random text.

It's not true that it works just fine in most cases, as you can tell from the various report here in the forum. Also just imaginge for example a prompt like this:

"create 5 social media posts on about . Use emotional adjectives, don't make any health promises. Add 3 trending hashtags to the end"
It will end up in 25 second timeouts. It's really not much text to generate... Maybe like 500 tokens. And this would be one of the very easy prompts...

You should really consider increasing the timeout to align with Zapier and other competitors. The whole OpenAI topic is otherwise not useful in Pabbly. Also, why wouldn't you? What's the big deal for Pabbly in increasing it?

I don't think that the prompt is too complex. But for sure it's more than "keyword". Because that returns pretty useless random text.

It's not true that it works just fine in most cases, as you can tell from the various report here in the forum. Also just imaginge for example a prompt like this:

"create 5 social media posts on about . Use emotional adjectives, don't make any health promises. Add 3 trending hashtags to the end"
It will end up in 25 second timeouts. It's really not much text to generate... Maybe like 500 tokens. And this would be one of the very easy prompts...

You should really consider increasing the timeout to align with Zapier and other competitors. The whole OpenAI topic is otherwise not useful in Pabbly. Also, why wouldn't you? What's the big deal for Pabbly in increasing it?

We have written to OpenAI Team today. We will update the thread as soon as we hear back on the way to optimize the way to use their API.

Hello Team,

I hope this email finds you well.

I am writing to inquire about the possibility of optimizing the response time of your API. We have noticed that the API can take more than 25 seconds to respond in some cases, which makes it difficult for users to run it in automation.

Is it possible to send the request ID immediately in the response when the API is fired so that we can use that request ID to fetch the final response with some delay?

This would allow us to better manage the wait time for our users and improve their experience with our API. Thank you for your time and I look forward to hearing back from you.

Best regards,

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.

Hello,
any progress? I simplified the prompt down to a minimum of "write an article about " and 1000 tokens and it still returns a 35 seconds timeout. Very frustrating...

We have written to OpenAI Team today. We will update the thread as soon as we hear back on the way to optimize the way to use their API.

We have written to OpenAI Team today. We will update the thread as soon as we hear back on the way to optimize the way to use their API.

For a limited time, we have increased the Timeout window for OpenAI Generate Content to 40 seconds. Although this is not an ideal thing to do.

Please note Zapier has the timeout limit of 30 seconds for OpenAI and similar issues are been faced by the users across different platforms.

The ideal way to handle this use-case is something that we have informed to the OpenAI team. We have sent the email but haven't received any reply back from them.

The message sent to the OpenAI team is below. I would recommend users to also send the message below from their end.

Hello Team,

I hope this email finds you well.

I am writing to inquire about the possibility of optimizing the response time of your API. We have noticed that the API can take more than 25 seconds to respond in some cases, which makes it difficult for users to run it in automation.

Is it possible to send the request ID immediately in the response when the API is fired so that we can use that request ID to fetch the final response with some delay?

This would allow us to better manage the wait time for our users and improve their experience with our API. Thank you for your time and I look forward to hearing back from you.

Best regards,

One of the main reason we use zapier is the connection with openAI and the fact that it retries automatically after a failed API call. Right now OpenAI integration in Pabbly is unusable as I cant get a response. We need a workaround or bye bye pabbly.

If the Zapier can do it, so can Pabbly? :-)

Temporarily, the Timeout window for OpenAI Generate Content has been increased to 40 seconds, although this is not the preferred solution. It is important to note that Zapier has a timeout limit of 30 seconds for OpenAI and other platforms are encountering similar issues.

We have informed the OpenAI team about the ideal solution for this, but have not received a response.

Temporarily, the Timeout window for OpenAI Generate Content has been increased to 40 seconds, although this is not the preferred solution. It is important to note that Zapier has a timeout limit of 30 seconds for OpenAI and other platforms are encountering similar issues.

We have informed the OpenAI team about the ideal solution for this, but have not received a response.

We have taken note of your concern and will attempt to address it on the platform soon.

We have taken note of your concern and will attempt to address it on the platform soon.

Unfortunately, we are unable to provide you with an ETA because it takes several checks to be completed before making any modifications. Following the submission of a specific integration request, you will receive an email notification.

Can you use the DELAY module - but I guess if "no response from OPENAI/CHATGPT - then there is no id to link to after waiting
Does anyone have a workaround for OPENAI- Timing out - or are we stuck until PABBLY comes up with a solution?

Can you use the DELAY module - but I guess if "no response from OPENAI/CHATGPT - then there is no id to link to after waiting
Does anyone have a workaround for OPENAI- Timing out - or are we stuck until PABBLY comes up with a solution?

hey everyone, I started having the same issue for a very simple query: "extract the email", so I am not sure if this is an issue on OpenAI's side or Pabbly's.

Hey @Oleksandr

Have you tried the "Text Formatter by Pabbly: Text (Basic Formatting)" action step to extract the email address?

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,

To be fair you shouldnt even offer the automation if it is unlikely to work

I understand your concern with the OpenAI integration on Pabbly Connect and feel that it is unlikely to work. I apologize for any inconvenience that this has caused you.

However, I want to assure you that the majority of our users are successfully using the OpenAI integration without any issues. We continuously work to improve our integrations to ensure that they work seamlessly for all users, and we are committed to resolving any problems that you may be experiencing.

I would be more than happy to assist you in troubleshooting any issues you are experiencing with the OpenAI integration.

Dear Pabbly folks,

Realistically, you'd need to increase your OpenAI timeout to 300 seconds. Their models routinely get overloaded, and they are slow. It often takes up to 5 minutes to output a long text. This doesn't mean there's an error on their side; they are just slow. OpenAI modules will likely be some of the most requested within Pabbly. And I know the timeout limit is much lower for most other APIs. But this is a new reality. Having OpenAI error out because you're timing the module out after 25 seconds will cause A LOT of user frustration. Hence, for OpenAI, I'd jack up the timeout to 300 seconds (at least).

Also, we desperately need auto-retry conditions. This could be useful for other modules, but for OpenAI it's essential. Their endpoints error out routinely when their models are over-run. And having to stop and re-enable the entire scenario because their modules error out is a huge waste of operations. Hence, we need to build robust automation scenarios with OpenAI where we can set something like "auto-retry three times in case of errors".

Eugene

Hey @bandelero

Thank you for your feedback regarding the OpenAI timeout. We understand the potential case caused by longer response times from OpenAI's models. Unfortunately, we are unable to increase the timeout limit at this time for such instances. We apologize for any inconvenience this may cause. We appreciate your understanding and will continue to work on optimizing our platform within the existing constraints.

Further, we have forwarded your request for the functionality of retrying the execution of the failed task in the system.

Hey @Supreme,

Thanks for letting us know.

What's preventing Pabbly from increasing the timeout?

Eugene

The timeout limit is influenced by technical considerations and system performance. Making changes to the timeout duration would require significant architectural modifications and may impact the overall resource of our platform.

While we understand the potential benefits of a longer timeout, we have carefully balanced responsiveness and system reliability in our current configuration whereas 40 seconds timeout is a larger processing time. Factors such as network conditions and external API performance can also affect the execution time of API requests.

We appreciate your understanding as we continue to improve our platform within the existing limitations.

Is there any update on this yet or are we still stuck at 25 secs timeout?

Using POE rather than OpenAI and need to do a load of research prior to generating the output, therefore requires far more than 25 seconds before timing out.

Is there any update on this yet or are we still stuck at 25 secs timeout?

Using POE rather than OpenAI and need to do a load of research prior to generating the output, therefore requires far more than 25 seconds before timing out.

Thanks, not what I was hoping for but better than nothing.

I'll have to use a different integrator for this then.