API for Extracting Content from Various File Formats?

joaquintorroba · 2024-08-07T23:21:16.715Z

Hi everyone,

I’m looking for an API to which I can send any document and it returns the extracted content. The formats I need to support include:

Does anyone have a recommendation for such an API that can handle these formats and return the extracted content?

Thanks in advance!

Zeroic · 2024-08-08T08:15:10.880Z

Hi! You can use OpenAI’s Assistants API to do this

joaquintorroba · 2024-08-08T12:51:46.181Z

Can you ellaborate?

Zeroic · 2024-08-08T12:56:38.094Z

Upload your files to the vector store
Create an assistant with the prompt to give you the extracted content from the document
Create a thread and pass the message to it
Create a run and pass the assistant ID to it

You should get the result

joaquintorroba · 2024-08-08T13:01:48.212Z

Very interesting, thanks!
I should be able to test this in open-ai’s playground to see if this works, right?

Zeroic · 2024-08-08T13:06:47.517Z

Yes

system · 2024-10-16T23:21:31.231Z

This topic was automatically closed after 70 days. New replies are no longer allowed.