The GPT-Plus and GPT-Team plans from OpenAI offer plug-ins that allow web browsing and access to scientific papers. There are tools that allow for import of PDFs also. I read that plug-ins are going away. What is the best way to reference specific documentation when chatting with the GPT-4 models?
#Accessing data using web browsing and PDF Importing
craggy hazel
magic merlinBOT
Hi @craggy hazel. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
As of November 2023, ChatGPT Plus supports a variety of features without the need to switch models. This includes DALL·E, browsing, and data analysis. You can also attach files to let ChatGPT search PDFs and other document types. This means you can reference specific documentation by attaching the relevant PDFs or other document types during your chat session with the GPT-4 models. This feature is also available in the ChatGPT Team plan.
However, it's important to note that GPT-4 is an inference model and does not have direct access to the internet. Any access to other systems, including uploaded documents, has to be implemented by the services that drive this model. If you use GPT-4 through the API, you’re responsible for providing those services as appropriate.
For more information, you can refer to the following sources:
- How do I access Advanced Data Analysis (formerly code interpreter)? (https://help.openai.com/en/articles/7183286-how-to-access-plugins-beta#h_729cfd023a)
- Does GPT-4 API Have Access to the internet? (https://community.openai.com/t/468615)