No access to my assistant with API

API Bugs
1

I created an assistant which works fine in playground, but can’t be called with the API, this error returns: “{ “error”: { “message”: “The model asst_NCwjfco9w3wegUA7JZzH6P6Q does not exist or you do not have access to it.”, “type”: “invalid_request_error”, “param”: null, “code”: “model_not_found” } }”. Anyone any idea’s?. This is the code that was suggested to use bij ChatGPT:

import openai
import os

Verkrijg de API-sleutel uit de omgevingsvariabele

openai.api_key = os.getenv(‘OPENAI_API_KEY’)

Gebruik de juiste assistant ID voor je eigen gemaakte assistant

response = openai.ChatCompletion.create(
model=“asst_NCwjfco9w3wegUA7JZzH6P6Q”, # Je eigen assistant ID
messages=[
{“role”: “system”, “content”: “You are a healthcare professional making suggestions to improve or support the quality of life.”},
{“role”: “user”, “content”: “Hoe kan ik de OpenAI API gebruiken?”}
]
)

Toon de response in de terminal

print(“Response from MyFirstAssistant:”, response[‘choices’][0][‘message’][‘content’])

5

It’ seems like you might be mixing up the model name with an assistant ID? Can you share a bigger code snippet?

2 Likes
7

or trying to send their new “model” to chat completions.

8

Please see my edit, thnx for helping.

9

Hi,
asst_… is the unique identifier for an API assistant, none related to a chat completion or a model name. Instead of this, try with a string like gpt-4o or gpt-4o-mini for the model.

10

You will not be able to ask any OpenAI model how to use the assistants endpoint. The training cutoff is before that existed.

Instead, Assistants needs you to read the long coding procedures not meant for beginners (on an endpoint that doesn’t meet the needs of experts). https://platform.openai.com/docs/assistants/overview

Instead, your “custom AI” can just be system message instructions, with Chat Completions - written properly.

from openai import OpenAI
client = OpenAI()

response = client.chat.completions.create(
  model="gpt-4o-mini",
  messages=[
    {
      "role": "system",
      "content": "You are a creative writer"
    },
    {
      "role": "user",
      "content": "Hi!"  # This shows sending past turns again
    }
    {
      "role": "assistant",   # and the past AI response gives "memory"
      "content": "Hello there! I’m your friendly creative writer bot."
    }
    {
      "role": "user",
      "content": "Produce a short poem. Subject: turtles."
    }
  ],
  temperature=.8, top_p=.8, max_completion_tokens=1000
)
print(response.choices[0].message.content)

…and then receive your requested output.

In emerald shells, they slowly glide,
Through sunlit waves, where secrets hide.
Ancient travelers, wise and slow,
With stories whispered in ebb and flow.
…

11

Jay, thnx for you response, I had the feeling that I was mixing things up… I found a good YT-video on this topic which I will study first.

12

Can someone help me how to resolve this issue. I created a custom assistant and it works fine in playground. But it fails when I am trying to call it from API. The error message is below:

“The model ‘asst_****’ does not exist or you do not have access to it.”

I checked all prelim check list to confirm I am calling the right one. And all are good. Except I am failing to call it from API.

Try to reach the support, still waiting on their reply. ( I felt it is live support. But unfortunately it is not and slow in responding;()

Can someone help please.

R

13

Check that your key is for the the same project. And that your key has the right rights.
You might have different accounts / projects. Check the drop down in the top left?

14

Thanks for responding.
I did check that and it looks good. But I have a solution from another thread that we should make API calls to consume custom assistants differently unlike models.

Let me share that here
THanks

15

https://platform.openai.com/docs/assistants/overview