Vector Databases with large files, without an asstant | OpenAI | Page 1

Hi there currently I am have setup a openai vector database to store files, however it works with an assistant, however I do not want an assistant.
Basically I have uploaded 100 files and I want to try to create some questions and answers from all the files.
If I use the assistant it displays it in a very HUMAN format,

I basically want it like this

let completion = await openai.chat.completions.create({
              model: 'gpt-3.5-turbo-0125',
              // max_tokens: 4000,
              messages: messages,
              temperature: 0,
              functions: functions
            });

const messages = [
              { role: 'system', content: 'Generate questions and answers in the form on an array'},

            ];

Basically that is exactly what I want to do if I just had 1 file however in this case I have 100 files in a vector database, so I basically need to fix it so I can use the vector database with the chat completion but I am not sure how to do it.

Please help thank you

Overall the reason why I am doing this is because I have 250+ pdf documents and I want to upload all of them and generate questions, answers, summary and a bunch of otherstuff and I can not just upload it through chat compleiton because it will go over the token limit many times over.

#Vector Databases with large files, without an asstant