mem0/docs/get-started/openai-assistant.mdx

---
title: '🤖 OpenAI Assistant'
---

<img src="https://blogs.swarthmore.edu/its/wp-content/uploads/2022/05/openai.jpg"  align="center" width="500" alt="OpenAI Logo"/>

Embedchain now supports [OpenAI Assistants API](https://platform.openai.com/docs/assistants/overview) which allows you to build AI assistants within your own applications. An Assistant has instructions and can leverage models, tools, and knowledge to respond to user queries.

At a high level, an integration of the Assistants API has the following flow:

1. Create an Assistant in the API by defining it custom instructions and picking a model
2. Create a Thread when a user starts a conversation
3. Add Messages to the Thread as the user ask questions
4. Run the Assistant on the Thread to trigger responses. This automatically calls the relevant tools.

Creating an OpenAI Assistant using Embedchain is very simple 3 step process.

## Step 1: Create OpenAI Assistant

Make sure that you have `OPENAI_API_KEY` set in the environment variable.

```python
from embedchain.store.assistants import OpenAIAssistant

assistant = OpenAIAssistant(
    name="OpenAI DevDay Assistant",
    instructions="You are an organizer of OpenAI DevDay",
)
```

### Arguments

<ResponseField name="assistant_id" type="string" required>
  Load existing OpenAI Assistant. If you pass this, you don't have to pass other arguments
</ResponseField>

<ResponseField name="thread_id" type="string">
  Existing OpenAI thread id if exists
</ResponseField>

<ResponseField name="model" type="str" default="gpt-4-1106-preview">
  OpenAI model to use
</ResponseField>

<ResponseField name="tools" type="list">
  OpenAI tools to use. Default set to `[{"type": "retrieval"}]`
</ResponseField>

<ResponseField name="data_sources" type="list" default="[]">
  Add data sources to your assistant. You can add in the following format: `[{"source": "https://example.com", "data_type": "web_page"}]`
</ResponseField>

## Step-2: Add data to thread

You can add any custom data source that is supported by Embedchain. Else, you can directly pass the file path on your local system and Embedchain propagates it to OpenAI Assistant.
```python
assistant.add("/path/to/file.pdf")
assistant.add("https://www.youtube.com/watch?v=U9mJuUkhUzk", data_type="youtube_video")
assistant.add("https://openai.com/blog/new-models-and-developer-products-announced-at-devday")
```

## Step-3: Chat with your Assistant
```python
assistant.chat("How much OpenAI credits were offered to attendees during OpenAI DevDay?")
# Response: 'Every attendee of OpenAI DevDay 2023 was offered $500 in OpenAI credits.'
```

You can try it out yourself using the following Google Colab notebook:

<a href="https://colab.research.google.com/drive/1BKlXZYSl6AFRgiHZ5XIzXrXC_24kDYHQ?usp=sharing">
    <img src="https://camo.githubusercontent.com/84f0493939e0c4de4e6dbe113251b4bfb5353e57134ffd9fcab6b8714514d4d1/68747470733a2f2f636f6c61622e72657365617263682e676f6f676c652e636f6d2f6173736574732f636f6c61622d62616467652e737667" alt="Open in Colab" />
</a>