How to beginner · 3 min read

OpenAI Assistants API Python SDK example

Q: OpenAI Assistants API Python SDK example

Use the OpenAI Python SDK to interact with the assistants endpoint by creating a client with your API key and calling client.assistants.chat.completions.create() with the assistant ID and messages. This enables building AI assistants with simple, clean Python code.

Quick answer

Use the OpenAI Python SDK to interact with the assistants endpoint by creating a client with your API key and calling client.assistants.chat.completions.create() with the assistant ID and messages. This enables building AI assistants with simple, clean Python code.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install openai>=1.0

Setup

Install the official openai Python SDK version 1.0 or higher and set your OpenAI API key as an environment variable.

Install SDK: pip install openai>=1.0
Set environment variable in your shell: export OPENAI_API_KEY='your_api_key_here'

bash

pip install openai>=1.0

Step by step

This example shows how to create a chat completion using the OpenAI Assistants API with the Python SDK. Replace your-assistant-id with your actual assistant ID.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

response = client.assistants.chat.completions.create(
    assistant_id="your-assistant-id",
    messages=[{"role": "user", "content": "Hello, how can you assist me today?"}]
)

print(response.choices[0].message.content)

output

Hello! I'm here to help you with any questions or tasks you have. What would you like to do today?

Common variations

You can customize the assistant interaction by:

Changing the assistant_id to target different assistants.
Adding multiple messages for context.
Using different models if supported by your assistant.
Implementing asynchronous calls with asyncio and await (requires Python 3.7+).

python

import asyncio
import os
from openai import OpenAI

async def main():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    response = await client.assistants.chat.completions.acreate(
        assistant_id="your-assistant-id",
        messages=[{"role": "user", "content": "Can you provide a summary of today's news?"}]
    )
    print(response.choices[0].message.content)

asyncio.run(main())

output

Here's a summary of today's top news stories: ...

Troubleshooting

If you encounter authentication errors, verify your OPENAI_API_KEY environment variable is set correctly. For assistant_id errors, confirm the ID is valid and you have access to that assistant. Network issues may require retry logic or checking your internet connection.

✅

Key Takeaways

Use client.assistants.chat.completions.create() with assistant_id to interact with OpenAI Assistants.
Always load your API key from os.environ to keep credentials secure.
Async calls are supported for scalable assistant interactions.
Verify your assistant ID and API key if you encounter errors.
The OpenAI Python SDK v1+ is required for this integration.

Verified 2026-04 · gpt-4o, gpt-4o-mini

Verify ↗