Creating gpts is restricted due to not having the ability to add missing modules or files to gpts. For example for translating images the GPTs says missing the japanese data file for ocr. If would be nice to have a formal process to add files or python libraries to our gpts.
#adding libraries, files, and other modules to the gpt environment
minor solstice
livid gobletBOT
Hi @minor solstice. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Based on the information provided in the extracts, it appears that you can add extra knowledge to your custom GPTs by uploading documents. This is done within the custom GPT configure tab. However, it's important to note that the content from the files that are uploaded could be included in the output (source (https://help.openai.com/en/articles/8554397-creating-a-gpt#h_9fdf0ceaf0)).
As for adding Python libraries or other modules, the extracts do not provide specific information on this. However, you can make third-party APIs available to your GPT by providing details about the endpoints, parameters, and a description about how the model should use it. Actions for GPTs can also be imported from an OpenAPI schema (source (https://help.openai.com/en/articles/8554397-creating-a-gpt#h_9fdf0ceaf0)).
If you're experiencing issues with adding files, it's possible that the files you're trying to add are not in line with the Terms of Service, and the functionality is being restricted without a proper message. In such cases, it's recommended to try using some other files that will definitely be okay to use (source (https://community.openai.com/t/585582)).