Inspiration
We already have a ChatGPT plugin for OCR called ChatOCR. We thought plugins might be dead with the launch of GPTs, but then we realized that GPTs are just more advanced plugins!
What it does
OCR-GPT is an assistant that helps the user OCR their documents and process the results by fixing typos, formatting the text, answering questions, etc.
How we built it
GPT Builder
Challenges we ran into
GPT-4 doesn't always follow the instructions given :( User must manually click allow for every plugin request GPTs do NOT show the user what the plugin returned
What we learned
There are some challenges specific to using GPTs. We'll need to do some more work to better optimize the user experience.
What's next for OCR GPT
Instructions that better handle the behaviors of GPTs
Built With
- gpt
- pluginlab
- python
Log in or sign up for Devpost to join the conversation.