# Creating a simple LLM app

To create your first LLM app, you'll need 3 things:  credential, one LLM Node and one LLM Chain node.

For the sake of this example, we'll make an app that uses ChatGPT.&#x20;

### 1. Create New Chatbot

Open the main menu and click on "Chatbots" -> "Create new chatbot"

<figure><img src="/files/ENmutWncuet74mFRjQje" alt=""><figcaption><p>Create new chatbot</p></figcaption></figure>

### 2. Give it a name

<figure><img src="/files/BfoDRmS5mrlcanKAh4UT" alt=""><figcaption><p>Give a name</p></figcaption></figure>

### 3. Add a new node "ChatOpenAI"

Click on the green floating button to add a new node, and search for "ChatOpenAI". Then, drag and drop it on the editor pane:

<figure><img src="/files/tG3cWIZOeOkN0sxyu5K6" alt=""><figcaption><p>Add ChatOpenAI Node</p></figcaption></figure>

### 4. Set the credentials

Click on "Change Parameters" button. It'll open the node's details where you will search for the [credentials you've created](/getting-started/adding-credentials.md) earlier. Then **Save Node Parameters**

<figure><img src="/files/iL67RhMUAVpNoIinndsb" alt=""><figcaption><p>Here you can also configure other parameters if you want</p></figcaption></figure>

### 5. Add a "LLM Chain" node

Click on the green floating button to add a new node, and search for "LLM Chain". Then, drag and drop it on the editor pane:

<figure><img src="/files/YIlM13oMzca2Xc3PcBF9" alt=""><figcaption><p>Add LLM Chain node</p></figcaption></figure>

### 6. Connect the dots

<figure><img src="/files/mq83Nr0QH8g55loL1HiL" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.gaiahub.ai/creating-a-simple-llm-app.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
