# Quick Start

Let's write a version of the code for chatting with a character

First of all, we need to import the library and write the startup code

{% tabs %}
{% tab title="Sync" %}

```python
from characterai import PyCAI

client = PyCAI('TOKEN')

# CODE
```

{% endtab %}

{% tab title="Async" %}

```python
import asyncio
from characterai import PyAsyncCAI

async def main():
    client = PyAsyncCAI('TOKEN')
    
    # CODE

asyncio.run(main())
```

{% endtab %}
{% endtabs %}

Now we have to take the necessary chat information to send the message

{% tabs %}
{% tab title="Sync" %}

```python
char = input('Enter CHAR: ')

chat = client.chat.get_chat(char)

participants = chat['participants']

if not participants[0]['is_human']:
    tgt = participants[0]['user']['username']
else:
    tgt = participants[1]['user']['username']
```

{% endtab %}

{% tab title="Async" %}

```python
char = input('Enter CHAR: ')

chat = await client.chat.get_chat(char)

participants = chat['participants']

if not participants[0]['is_human']:
    tgt = participants[0]['user']['username']
else:
    tgt = participants[1]['user']['username']
```

{% endtab %}
{% endtabs %}

And now let's make a cycle in which there will be a chat

{% tabs %}
{% tab title="Sync" %}

```python
while True:
    message = input('You: ')

    data = client.chat.send_message(
        chat['external_id'], tgt, message
    )

    name = data['src_char']['participant']['name']
    text = data['replies'][0]['text']

    print(f"{name}: {text}")
```

{% endtab %}

{% tab title="Async" %}

```python
while True:
    message = input('You: ')

    data = await client.chat.send_message(
        chat['external_id'], tgt, message
    )

    name = data['src_char']['participant']['name']
    text = data['replies'][0]['text']

    print(f"{name}: {text}")
```

{% endtab %}
{% endtabs %}

The full code is available in the "Examples" folder


---

# 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://pycai.gitbook.io/welcome/quick-start.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.