I have asked the model to help me generate a very detailed summary of a book.
The length of the book is 440K tokens. I tried many times, and the results are:
“An internal error has occurred” always appear if the generation time over 600 seconds, and the summary is unfinished. The length of the unfinished summary is around 32 tokens, with the content of first few chapters of the book.
The name of the model is Gemini 2.5 Pro Preview 05-06. The output length setting is 65536.
Hey @ai-studio , are you still facing the issue? I checked with a similar file size and it worked fine.
Hi,
Did it run >= 600 seconds? I rerun the same prompt many times; sometimes it can be done if the shorter summary is generated within 600 seconds, but sometimes it cannot.
Once the 600 seconds is over, “An internal error has occurred” must appear.
It took less than 300 seconds. Do you mind sharing your sample PDF? I would like to test it on my end.
Thanks.
The file you shared, the processing took less than 200 seconds. By the way, can you check with the new 2.5-pro-preview-06-05 version?
Could be caused by the system instruction, I run it again today by 2.5-pro-preview-05-06, the same problem still there.
Therefore, I sent you the share prompt link.
The 2.5-pro-preview-06-05 seems without this issue, but the book summary quality is worse. 
