Continue generating past chatgpts response limit

How can I use bardeen to continually follow a prompt until its completion?

E.g. Write a 10,000 word essay on {topic}.

Once gpt starts it will need to continue a few times as additional prompts to complete the request.

Can bardeen be used to automatically just keep prompting it to continue until the response finishes?

Hi @hoebing,

We don’t have such an action yet. If you use “Create customized text generated by OpenAI”, you can specify the output length, but that’s limited to what the model can generate in one go (approx. 3000 words, minus the space for the prompt).
We could consider adding this action in the future, or extending the action so it continues generating if asked to produce longer text.

In the meantime, you might be able to use multiple calls to “Get custom prompt generated by OpenAI” in sequence in a single playbook, passing the prompts and a summary of the previous text. I’m not sure how easy it will be to get it to generate coherent text though, and you’ll have to make sure each prompt fits within the space of one model (4096 tokens).

Hope this helps!

This topic was automatically closed 10 days after the last reply. New replies are no longer allowed.