Update to showcase multi-page document with signature detection - Githubissues

Azure-Samples / azure-openai-gpt-4-vision-pdf-extraction-sample

This sample demonstrates how to use GPT-4o with Vision to extract structured JSON data from PDF documents, such as invoices, using the Azure OpenAI Service.

MIT License

56 stars 16 forks source link

Update to showcase multi-page document with signature detection #2

Closed jamesmcroft closed 8 months ago

jamesmcroft commented 8 months ago

Purpose

Changes have been made to introduce the following new capabilities in the sample:

Add multi-page invoice document with signatures
Update sample to support stitching together multiple pages into a single image for data extraction
Update guidance on how to handle documents with multiple pages
Update system prompt to ensure that valid JSON is returned and not a code block
Update user prompt to provide structure to the JSON response

Does this introduce a breaking change?

[ ] Yes
[x] No

Pull Request Type

What kind of change does this Pull Request introduce?

[ ] Bugfix
[x] Feature
[ ] Code style update (formatting, local variables)
[ ] Refactoring (no functional changes, no api changes)
[ ] Documentation content changes
[ ] Other... Please describe:

Other Information