I uploaded a book and it gave me: "I'm sorry, I cannot summarize the 10 key points as the document(s) provided are not specified. Please provide more information or context so I can assist you better." I gave it the title and asked if it had it indexed. Here is the response: "As an AI language model, I do not have access to your uploaded document or any external database. I apologize for the inconvenience. Is there anything else I can assist you with?" I then asked for the title and it said: "I'm sorry, but based on the extracted parts of the document provided, I cannot determine the title of the document. The parts provided only show that there are several pages intentionally left blank. Please provide more information or context so I can assist you better." I asked for the page numbers of the blank pages. It gave those to me which was perplexing since I had assumed up until this point that the document did not load. I then told it that the title of the document was a book title on 5 different pages, which included the first 2 pages. It then confirmed that it could find the title. I asked why it did not find it initially and it gave the following response: "I apologize for any confusion. I may have misunderstood your initial question. If the document you were referring to is a book titled "XYZ" then I can confirm that I do not have it indexed or stored in my database. As an AI language model, I do not have access to external databases or documents unless they are provided to me by the use". So it's clear that the pinecone or other vector database code missed big time. By the way, this product idea is out there in spades in the open source arena. Not sure it's worth $99 for the Google Collab and Pinecone costs. Let me know your thoughts.
