I cant access the uploaded file through the assistant (OpenAI) in subsequent operations

I would like to upload files (JSON) to OpenAI and use them in the assistant:

I read here that it’s only possible to make OpenAI read and access files this way, OpenAI - Upload a file(openai) and have the next step(Create a completion - openai) to access the file - #4 by Casey_Magee

It works for one operation most of the time, in the second operation I receive a response, along the line: “I cant access or read your file”

Anybody found a way to get OpenAI to acces files consistently?

It is definitely possible. I’ve created a Telegram assistant bot with GPT-4-turbo that can read uploaded files. Not only that, it can retrieve relevant previously-uploaded files to the assistant, based on keywords in the chat message (Make filter).

Screenshot_2024-04-02_220445

Here is an example of it in action:

Screenshot_2024-04-02_220423

For more information, see

3 Likes

That’s amazing!
Its possible to do it with gpt 3.5?

ahh yes the retrieve knowledge option, didnt have that selected :sweat_smile:

2 Likes

No problem, glad I could help!

1. If you have a new question in the future, please start a new thread. This makes it easier for others with the same problem to search for the answers to specific questions, and you are more likely to receive help since newer questions are monitored closely.

2. The Make Community guidelines encourages users to try to mark helpful replies as solutions to help keep the Community organized.

This marks the topic as solved, so that:

others can save time when catching up with the latest activity here, and

  • allows others to quickly jump to the solution if they come across the same problem

To do this, simply click the checkbox at the bottom of the post that answers your question:
Screenshot_2023-10-04_161049

3. Don’t forget to like and bookmark this topic so you can get back to it easily in future!

2 Likes