Is uploading PDF file to o1 supported?

API
1

Hi! Is there currently a way to upload a PDF when using the o1 model? I have tried everything I can think of and nothing seems to work.

I tried uploading the file and using the “file_search” tool, but that doesn’t seem to be enabled for o1 yet.

I tried adding the base64 encoded url to “image_url” and that seems to only support jpeg or png images.

I even tried adding the base64 encoded data directly to my prompt and that didn’t work either.

Am I missing something here, or is this not yet available through the API?

Thank you!

2

The ChatGPT version can, but the API version still has these docs:

The latest o1 model supports both text and image inputs, and produces text outputs (including Structured Outputs). o1-mini currently only supports text inputs and outputs.

3

Thank you for confirming this.

Great that it can accept image inputs. I put together a solution that seems to be working pretty well as a service that can take a pdf and return base64 encoded images of each page of the PDF that can then be fed in as an image_url: github/kgn/pdf2imgs

4

This topic was automatically closed 2 days after the last reply. New replies are no longer allowed.