> ## Documentation Index
> Fetch the complete documentation index at: https://notes.kodekloud.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Creating an Assistant

> This tutorial guides building, configuring, and testing a custom AI assistant using the OpenAI Assistants API and Assistant Playground.

Welcome to the OpenAI Assistants API guide. In this tutorial, we’ll walk through how to build, configure, and test a custom AI assistant using both the Assistant Playground and the OpenAI API.

## Overview of the Assistants API

The Assistants API (currently in beta) provides a simple way to register and interact with AI assistants. Before you begin, review the official [Assistants API documentation][docs] and explore the [Assistant Playground][playground] for a no-code experience.

<Frame>
  ![The image shows a webpage from OpenAI's platform documentation, specifically detailing the Assistants API overview and how it works, with a sidebar menu for navigation.](https://kodekloud.com/kk-media/image/upload/v1752879207/notes-assets/images/Introduction-to-OpenAI-Creating-an-Assistant/openai-assistants-api-overview-docs.jpg)
</Frame>

<Callout icon="triangle-alert" color="#FF6B6B">
  The Assistants API is in **beta**. Endpoints and parameters may change as we improve functionality. Keep your integration up to date by regularly checking the [documentation][docs].
</Callout>

## Using the Assistant Playground

The [Assistant Playground][playground] offers an interactive UI to:

* Configure models and tools
* Set system instructions
* Name your assistant
* Run quick tests

You can instantly see how requests and responses are structured, making it ideal for prototyping before coding.

## Creating an Assistant with Python

To get started programmatically, install the OpenAI Python package and initialize the client:

```bash theme={null}
pip install openai
```

```python theme={null}
from openai import OpenAI

client = OpenAI()
```

Next, register a new assistant:

```python theme={null}
assistant = client.beta.assistants.create(
    name="Math Tutor",
    instructions="You are a personal math tutor. Write and run Python code to solve math problems step by step.",
    tools={"type": "code_interpreter"},
    model="gpt-4"
)
```

| Parameter    | Description                               | Example                              |
| ------------ | ----------------------------------------- | ------------------------------------ |
| name         | Friendly assistant name                   | `"Math Tutor"`                       |
| instructions | System-level prompt guiding the assistant | `"You are a personal math tutor..."` |
| model        | OpenAI model to power the assistant       | `"gpt-4"`                            |
| tools        | Enabled integrations or plugins           | `{"type": "code_interpreter"}`       |

## Handling Streaming Responses

For real-time output, subclass `AssistantEventHandler` and override event methods:

```python theme={null}
from typing_extensions import override
from openai import AssistantEventHandler

class EventHandler(AssistantEventHandler):
    @override
    def on_text_created(self, text) -> None:
        print(text, end="", flush=True)

    @override
    def on_text_del(self, delta, snapshot):
        print(delta.value, end="", flush=True)

    @override
    def on_tool_call_created(self, tool_call):
        print(f"Tool call: {tool_call.type}", flush=True)

    @override
    def on_tool_call_del(self, delta, snapshot):
        if delta.type == "code_interpreter":
            if delta.code_interpreter.input:
                print(delta.code_interpreter.input, end="", flush=True)
            if delta.code_interpreter.outputs:
                print("\n\noutput>", end=" ")
                for output in delta.code_interpreter.outputs:
                    if output.type == "logs":
                        print(f"\noutput.logs = {True}")
```

<Callout icon="lightbulb" color="#1CB2FE">
  You can run this handler in any IDE (e.g., [Visual Studio Code][vscode]). Streaming makes the assistant feel more interactive by printing results as they arrive.
</Callout>

## Testing Your Assistant

Let’s test the “Math Tutor” with a sample expression in the Playground or via API calls:

> What is 13 times 5 divided by 6, times 5, plus 100 times 4 to the power of 2?

<Frame>
  ![The image shows a user interface for a math tutor assistant using a GPT-4 model, with a math expression input for evaluation.](https://kodekloud.com/kk-media/image/upload/v1752879207/notes-assets/images/Introduction-to-OpenAI-Creating-an-Assistant/math-tutor-assistant-gpt4-interface.jpg)
</Frame>

The assistant uses the code interpreter to compute and returns the result (approximately **1654.17**).

## Links and References

* [Assistants API Guide][docs]
* [Assistant Playground][playground]
* [API Quickstart Guide][quickstart]
* [Visual Studio Code][vscode]

[docs]: https://platform.openai.com/docs/guides/assistants-api

[playground]: https://platform.openai.com/playground

[quickstart]: https://platform.openai.com/docs/quickstart

[vscode]: https://code.visualstudio.com/

<CardGroup>
  <Card title="Watch Video" icon="video" cta="Learn more" href="https://learn.kodekloud.com/user/courses/introduction-to-openai/module/b6b7bec7-ed21-47d5-afbb-663df59f5e97/lesson/726bc20c-5d5a-4825-943e-05bbe12318b5" />
</CardGroup>