#UPLOAD DOCUMENT IN GPT4
1 messages · Page 1 of 1 (latest)
You cannot upload it tidrectly to a call to the LLM like chatcompletions/completions, but instead you can upload it as a file for your Assistant using the Assistants API
cool , can you please guide me what would be the best model for me to use , gpt4 / turbo or the latest one ! what is a good cost to get started with it , my project revolves around uploading a document and chatting with it @topaz jacinth
yeah stick with gpt-4 turbo the latest one (gpt-4-1106-preview)
it is the best performance for a pretty cheap cost right now
just a doubt that , do i need to pay for gpt plus also , or can i just go on with lets just say $10 credits for gpt4 turbo @topaz jacinth
You don't have to pay for gpt plus you can just go for the API credits only
ok cool , i have one more doubt like - can you tell me that is it possible to upload multiple documents (PDFs) and then chat with it to get relevant input , or is it like one input a time ?
@topaz jacinth
I think you can using the assistants API, PDF, Text etc
I was able to add multiple file and types using the web ui of gpt assistants. My issue is how to turn off the general knowledge from the user questions. Basically, I want the response to only be about the files data and nothing else. So if the user ask what is 2+2? The assistant should answer that information is not in your file, etc. can anyone advise on how to set this up? I tried adding instructions but it doesn’t work!
I try to solve the same problem atm, are u still clueless or any update? I haven’t been able to turn off the basic knowledge yet, but I could ensure to use the data of my knowledge and answer me if it was from my knowledge only or from other sources as well…