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

# Quickstart

> Start Calling Your AI pipelines

## Setup Your Pipeline's API

Sign up for <a href="www.jetski.ai">jetski.ai</a> and then fill out the form to deploy your own AI. No instructions needed!

### Call Your API

Copy your autogenerated API endpoint and make a POST request with the following JSON payload:

```json theme={null}
{
 "parameters" : 
 {
   "example_param" : "example_value"
 },
 "messages":
 [
 {
 "type" : "human",
 "content" : "who in the right mind jetski's in shark water?"
 },
 {
 "type" : "assistant",
 "content" : "Someone who lives life on the fin!"
 }
 ]
}
```

This JSON structure is unversal for all AI configurations through our deployment form.

<Tabs>
  <Tab title="curl">
    ```bash theme={null}
    curl -H 'Content-Type: application/json' \\
        -d '{ \n "parameters": 
        {
        
        },
        "messages": [
                {
                  "type" : "type of message ("human" or "assistant")",
                  "content" : "content of message"
                },
                 {
                  "type" : "type of message ("human" or "assistant")",
                  "content" : "content of message"
                },
              ]}' \\
        -X POST \\
        <your endpoint goes here>
    ```
  </Tab>

  <Tab title="python">
    ```python theme={null}
    import requests

    # The URL you want to make a POST request to
    url = <your endpoint goes here>

    # Data you want to send in JSON format
    data = { "parameters": 
    {

    }, "messages": [
               {
                 "type" : "type of message ('human' or 'assistant')",
                 "content" : "content of message"
               },
                {
                 "type" : "type of message ('human' or 'assistant')",
                 "content" : "content of message"
               },
             ]}

    # Optional: Custom headers
    headers = {
     'Content-Type': 'application/json'
    }

    # Make the POST request
    response = requests.post(url, json=data, headers=headers)

    # Check if the request was successful
    if response.status_code == 200:
     print('Success!')
     # Process the response if necessary
     print(response.json())
    else:
     print('An error occurred:', response.text)

    ```
  </Tab>

  <Tab title="javascript">
    ```javascript theme={null}
    // The URL you want to make a POST request to
    const url = <your endpoint goes here>;

    // Data you want to send in JSON format
    const data = { parameters: 
    {

    } , messages: [
              {
                "type" : "type of message ("human" or "assistant")",
                "content" : "content of message"
              },
               {
                "type" : "type of message ("human" or "assistant")",
                "content" : "content of message"
              },
            ]};

    // Create an options object that includes method, headers, and body
    const options = {
    method: 'POST', // Specify the request method
    headers: {
        Content-Type: 'application/json' // Specify the content type of the request
    },
    body: JSON.stringify(data) // Convert the JavaScript object to a JSON string
    };

    // Use the fetch API to make the POST request
    fetch(url, options)
    .then(response => {
        if (!response.ok) {
            // If the response is not ok, throw an error
            throw new Error('Network response was not ok');
        }
        return response.json(); // Parse the response as JSON
    })
    .then(data => {
        console.log('Success:', data); // Log the data on success
    })
    .catch(error => {
        console.error('Error:', error); // Log any errors
    });

    ```
  </Tab>
</Tabs>