PDF.ai

Wanted to build with PDF.ai, but they didn't keep what they promised. So I decided to cancel the free plan before it extends. Turns out, there is no option to cancel the trial online on the website. They don't even give you an option to adjust the plan etc. It's only possible to upgrade. Of course they don't have any option to contact them other than an email in their privacy policy. I contacted them so they cancel for me. They didn't and the trial extended. Now I have to deal with Mastercards chargeback flow. This is absolute unacceptable behaviour and definitely by design. Stay away from them!

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.

I used this product, and it is fast. But it gives wrong results. That is a problem as it can mislead the user. Maybe because it uses a cheaper embedding to save cost? I think this needs to be fixed before launching it widely. Lifetime pricing is nice but the product should work properly. It is not disclosed if this uses Open AI and which version. I wish I could rate it better but it needs improvement before you sell it. All the best, Amir

I purchase the lifetime subscription and I'm not happy. I've been struggling for quite some time to get some help with a few documents and the responses have been mostly useless. I've tried to simplify my requests to the most simple questions I can think of, such as how many questions are on a page and it doesn't seam to even understand what a question is. This image should demonstrate how frustrating this is: https://prnt.sc/Mqw7epWzP6Us.

I paid for the ability to chat all pdfs. It can't even do something basic like list the titles of less than 10 pdfs uploaded, but will tell you the title if you chat one at a time. Pretty hard to have faith in what it can do on that alone. I've had zero help response and noticed youtube media strongly promoting it's chat all function which in my experience does not work at all. I can't emphasise strongly enough to avoid this product sadly.

I don't know which model you have been using. The responses are really bad. Can't even tell company name from it's financial report. Also, on another note if you are using gpt-3.5 turbo. I am wondering how you will be able to sustain recurring openAI charges with a 99$ lifetime pdf.ai plan.