Hi,
I am stuck with the module on Perplexity that is telling me: “[400] Messages have 16865 tokens, which exceeds the max limit of 8192 tokens.”
I think it’s because it’s picking up a message/text/news which is super long.
How can I solve this?
Hi @BlackCube,
Have you set a Max Tokens value? Do you have the same behavior with different models? Also, is the request very long? Those are all factors that can affect the output.
If you use the same prompt in the perplexity app, do you get very long answes also?
L
If you are scraping a webpage, you can use the Dumpling AI “Scrape URL” module, which “cleans” – removes unnecessary data from the website like headers and footers, and returning only useful content on the page. This is very handy if you want to reduce the amount of characters/tokens you are passing into another AI module for analysis.
For more information on the different methods of web scraping, see Overview of Different Web Scraping Techniques in Make 🌐
Hope this helps! Let me know if there are any further questions or issues.
— @samliew
P.S.: Did you know, the concepts of about 70% of questions asked on this forum are already covered in the Make Academy. Investing some effort into it will save you lots of time and frustration using Make later!
3 Likes