Support for File Inputs In Azure OpenAI

[gqoew]

Confirm this is a feature request for the Python library and not the underlying OpenAI API.

• This is a feature request for the Python library

Describe the feature or improvement you're requesting

Hi,

I’m trying to make a prompt with an attached file using Azure OpenAI.

I followed the official OpenAI File Inputs tutorial since this part is not clearly documented on Azure docs: https://platform.openai.com/docs/guides/pdf-files?api-mode=responses&lang=python

I didn’t manage to reproduce this with AzureOpenAI client. Is File Inputs prompts supported in Azure OpenAI? If yes, is there an exemple code block somewhere?

Thanks

Additional context

No response

[ahmedmoorsy]

any updates on this?

[trrwilson]

Apologies for the slow response here, @ahmedmoorsy, and thanks to @RobertCraigie for the tag!

Azure OpenAI parity support for these embedded PDF input_file content parts isn't yet available. It's in progress now, but no ETA harder than "soon, and as soon as possible."

In the interim, although it's much more cumbersome, the functionality can be approximated by uploading the file (with a purpose of assistants, as the new user_data is also coming soon together with input_file parts) and providing a vector store ID with that file to a file_search tool configuration.

[lgibelli]

+1 to implement this

[jake-ch]

+1

[mateusz-ona]

+1, file upload is a core functionality of LLMs right now

[davidames]

Another +1, * 10,000.

This is a gap that you can't bridge with vector search.

[iristap]

+1