Knowledge file upload limitations

GPT builders
1

What is the file upload limitations for custom GPTs? Specifically for Enterprise but any information is helpful.

I have found the following information related to non-GPT file limitations:
ChatGPT Enterprise uses models with a maximum context window of 110k tokens (roughly 200 pages of text)
For a single document exceeding 110k tokens, only the first 110k tokens will be included, starting from the beginning, approximately 350 pages of mixed text and images will fully utilize the 110k token context window. The remainder will only be sent to the private search index. If multiple documents are uploaded and their combined total exceeds 110k tokens, ChatGPT Enterprise uses a two-step process to balance document representation:

  1. Extract up to 55k tokens, divided evenly among the uploaded documents.
  • For example, if 10 documents are uploaded, 5.5k tokens are extracted from the beginning of each.
  1. For documents not fully represented in the first step, allocate the remaining 55k tokens proportionally based on the tokens left in each document.
  • For example, if Document A has 10k tokens remaining and Document B has 90k tokens remaining, an additional 5.5k tokens are extracted from Document A ( (10k / 100k) * 55k ), and an additional 49.5k tokens are extracted from Document B ( (90k / 100k) * 55k ).
  1. Any remaining tokens are only sent to the private search index.
2

Hi, welcome to the community!

Following links are about limitation of files on GPTs, but it does not mention about “Enteprise”. I think it works same for Plus, Pro, or Enterprise.

https://help.openai.com/en/articles/8983703-how-many-files-can-i-upload-at-once-per-gpt

https://help.openai.com/en/articles/8983719-what-are-the-file-upload-size-restrictions

1 Like
3

Thanks! Yes this is along the line of information I was looking for.

Is there guidance on token limitations?
I found this to be a good source for file uploading: https://help.openai.com/en/articles/10029836-optimizing-file-uploads-in-chatgpt-enterprise
“For a single document exceeding 110k tokens, only the first 110k tokens will be included, starting from the beginning. The remainder will only be sent to the private search index.”

My goal is to limit the use of a private search index, ensuring all the documents included in the knowledge are fully processed.

1 Like
4

I did not see any other docs about it.

To get accurate answer you may ask to support team on help.openai.com clicking on message widget on right down side.

Because you are Enterprise, probably they may reply faster.

5

ChatGPT Enterprise can process up to 110k tokens from uploaded documents in the context window. If you upload one or more documents with a combined total of less than 110k tokens, the full content will be included.

I think this answers your question.

Also note:

This feature is under active development. As such, the following details are subject to change without notice.

I suggest to regularly check up on the help page you linked.