Chat

Chat quickstart

Build your first text-based conversation with a Vapi assistant in 5 minutes

Overview

Build a customer service chat bot that can handle text-based conversations through your application. Perfect for adding AI chat to websites, mobile apps, or messaging platforms.

What You’ll Build:

  • A working chat integration that responds to user messages
  • Context-aware conversations that remember previous messages
  • Both one-shot and multi-turn conversation patterns

Agent Capabilities:

  • Instant text responses without voice processing
  • Maintains conversation context across multiple messages
  • Compatible with existing OpenAI workflows

Prerequisites

  • A Vapi account
  • An existing assistant or willingness to create one
  • Basic knowledge of making API requests

Scenario

We’ll create a customer support chat for “TechFlow”, a software company that wants to handle common questions via text chat before escalating to human agents.

1. Get Your API Credentials

1

Open the Vapi Dashboard

Go to dashboard.vapi.ai and log in to your account.

3

Copy your API key

Copy your Private API Key. You’ll need this for all chat requests.

Keep this key secure - never expose it in client-side code.

2. Create or Select an Assistant

2

Create a new assistant (or use existing)

  • Click Create Assistant if you need a new one
  • Select Blank Template as your starting point
  • Name it TechFlow Support
  • Set the first message to: Hello! I'm here to help with TechFlow questions. What can I assist you with today?
3

Configure the system prompt

Update the system prompt to:

System Prompt
You are a helpful customer support agent for TechFlow, a software company. 
Your role:
- Answer common questions about our products
- Help troubleshoot basic issues  
- Escalate complex problems to human agents
Keep responses concise and helpful. Always maintain a friendly, professional tone.
4

Copy the Assistant ID

After publishing, copy the Assistant ID from the URL or assistant details. You’ll need this for API calls.

3. Send Your First Chat Message

1

Test with curl

Replace YOUR_API_KEY and your-assistant-id with your actual values:

First Chat Request
$curl -X POST https://api.vapi.ai/chat \
>  -H "Authorization: Bearer YOUR_API_KEY" \
>  -H "Content-Type: application/json" \
>  -d '{
>    "assistantId": "your-assistant-id",
>    "input": "Hi, I need help with my TechFlow account"
>  }'
2

Verify the response

You should receive a JSON response like:

Chat Response
1{
2  "id": "chat_abc123",
3  "assistantId": "your-assistant-id",
4  "messages": [
5    {
6      "role": "user",
7      "content": "Hi, I need help with my TechFlow account"
8    }
9  ],
10  "output": [
11    {
12      "role": "assistant",
13      "content": "I'd be happy to help with your TechFlow account! What specific issue are you experiencing?"
14    }
15  ],
16  "createdAt": "2024-01-15T09:30:00Z",
17  "updatedAt": "2024-01-15T09:30:00Z"
18}

4. Build a Multi-Turn Conversation

1

Continue the conversation

Use the previousChatId from the first response to maintain context:

Follow-up Message
$curl -X POST https://api.vapi.ai/chat \
>  -H "Authorization: Bearer YOUR_API_KEY" \
>  -H "Content-Type: application/json" \
>  -d '{
>    "assistantId": "your-assistant-id",
>    "previousChatId": "chat_abc123",
>    "input": "I forgot my password and can't log in"
>  }'
2

Test context awareness

Send another message to verify the assistant remembers the conversation:

Context Test
$curl -X POST https://api.vapi.ai/chat \
>  -H "Authorization: Bearer YOUR_API_KEY" \
>  -H "Content-Type: application/json" \
>  -d '{
>    "assistantId": "your-assistant-id", 
>    "previousChatId": "chat_abc123",
>    "input": "What was my original question?"
>  }'

5. Pass Dynamic Variables

1

Configure variables in your assistant

In your assistant’s system prompt, you can reference dynamic variables using {{variableName}} syntax:

System Prompt with Variables
You are a helpful customer support agent for {{companyName}}.
Your role:
- Answer questions about {{companyName}}'s products
- Help customers with their {{serviceType}} needs
- Escalate to human agents when needed
Current customer tier: {{customerTier}}
2

Pass variables in your chat request

Use assistantOverrides.variableValues to pass dynamic data:

Chat Request with Variables
$curl -X POST https://api.vapi.ai/chat \
>  -H "Authorization: Bearer YOUR_API_KEY" \
>  -H "Content-Type: application/json" \
>  -d '{
>    "assistantId": "your-assistant-id",
>    "input": "I need help with my account",
>    "assistantOverrides": {
>      "variableValues": {
>        "companyName": "TechFlow Solutions",
>        "serviceType": "software",
>        "customerTier": "Premium"
>      }
>    }
>  }'

6. Integrate with TypeScript

1

Create a simple chat function

Here’s a TypeScript function you can use in your application:

chat.ts
1interface ChatMessage {
2  role: 'user' | 'assistant';
3  content: string;
4}
5
6interface ChatApiResponse {
7  id: string;
8  assistantId: string;
9  messages: ChatMessage[];
10  output: ChatMessage[];
11  createdAt: string;
12  updatedAt: string;
13  orgId?: string;
14  sessionId?: string;
15  name?: string;
16}
17
18interface ChatResponse {
19  chatId: string;
20  response: string;
21  fullData: ChatApiResponse;
22}
23
24async function sendChatMessage(
25  message: string, 
26  previousChatId?: string
27): Promise<ChatResponse> {
28  const response = await fetch('https://api.vapi.ai/chat', {
29    method: 'POST',
30    headers: {
31      'Authorization': 'Bearer YOUR_API_KEY',
32      'Content-Type': 'application/json'
33    },
34    body: JSON.stringify({
35      assistantId: 'your-assistant-id',
36      input: message,
37      ...(previousChatId && { previousChatId })
38    })
39  });
40
41  if (!response.ok) {
42    throw new Error(`HTTP error! status: ${response.status}`);
43  }
44
45  const chat: ChatApiResponse = await response.json();
46  return {
47    chatId: chat.id,
48    response: chat.output[0].content,
49    fullData: chat
50  };
51}
52
53// Usage example
54const firstMessage = await sendChatMessage("Hello, I need help");
55console.log(firstMessage.response);
56
57const followUp = await sendChatMessage("Tell me more", firstMessage.chatId);
58console.log(followUp.response);
2

Test your integration

Run your TypeScript code to verify the chat integration works correctly.

7. Test Your Chat Bot

1

Test various scenarios

Try these test cases to ensure your chat bot works correctly:

Test Case 1: General Question
$curl -X POST https://api.vapi.ai/chat \
>  -H "Authorization: Bearer YOUR_API_KEY" \
>  -H "Content-Type: application/json" \
>  -d '{
>    "assistantId": "your-assistant-id",
>    "input": "What are your business hours?"
>  }'
Test Case 2: Technical Issue
$curl -X POST https://api.vapi.ai/chat \
>  -H "Authorization: Bearer YOUR_API_KEY" \
>  -H "Content-Type: application/json" \
>  -d '{
>    "assistantId": "your-assistant-id",
>    "input": "My app keeps crashing when I try to export data"
>  }'
2

Verify conversation memory

Send follow-up messages using previousChatId to ensure context is maintained.

Limitations

Current chat functionality limitations:

  • “Query” tool for knowledge-base searches is not yet supported
  • Server webhook events (status updates, end-of-call reports, etc.) are not supported

Webhook Support

The chat API supports the following webhook events through server messaging:

  • chat.created - Triggered when a new chat conversation is initiated
  • chat.deleted - Triggered when a chat conversation is deleted

To receive these webhooks, go to your Assistant page in the Dashboard and navigate to “Server Messaging” and select the events you want to receive.

These webhooks are useful for tracking conversation analytics, maintaining conversation history in your own database, and triggering follow-up actions.

Next Steps

Take your chat bot to the next level:

Need help? Chat with the team on our Discord or mention us on X/Twitter.