Chat Interface (Part B)

Your Chat Interface is where users interact with your agent. It calls Daemo's HTTP API and can be any frontend — website, mobile app, Slack bot, or API integration.

Note

This is separate from your Functions Service. Your chat UI can live in a completely different repo, different tech stack, different deployment.

---

Quick Start

Call the HTTP Query API from anywhere:

curl -X POST https://api.daemo.ai/agents/{agent_id}/query \
  -H "Content-Type: application/json" \
  -H "X-API-Key: daemo_live_your_key" \
  -d '{"query": "Show me all users"}'

That's it. Your functions service executes the query and returns a response.

---

Integration Examples

Next.js / React

app/api/chat/route.ts

export async function POST(req: Request) {
  const { message, threadId } = await req.json();
  
  const response = await fetch(
    `https://api.daemo.ai/agents/${process.env.DAEMO_AGENT_ID}/query`,
    {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'X-API-Key': process.env.DAEMO_API_KEY!,
      },
      body: JSON.stringify({
        query: message,
        threadId,
      }),
    }
  );
  
  return response;
}

Python / FastAPI

main.py

import httpx
from fastapi import FastAPI

app = FastAPI()

@app.post("/chat")
async def chat(message: str, thread_id: str = None):
    async with httpx.AsyncClient() as client:
        response = await client.post(
            f"https://api.daemo.ai/agents/{AGENT_ID}/query",
            headers={
                "Content-Type": "application/json",
                "X-API-Key": DAEMO_API_KEY,
            },
            json={
                "query": message,
                "threadId": thread_id,
            },
        )
    return response.json()

Node.js / Express

server.js

app.post('/chat', async (req, res) => {
  const { message, threadId } = req.body;
  
  const response = await fetch(
    `https://api.daemo.ai/agents/${process.env.DAEMO_AGENT_ID}/query`,
    {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'X-API-Key': process.env.DAEMO_API_KEY,
      },
      body: JSON.stringify({
        query: message,
        threadId,
      }),
    }
  );
  
  res.json(await response.json());
});

---

Multiple Interfaces

One of Daemo's strengths: deploy your functions once, integrate everywhere.

🌐Website

📱Mobile App

💼Admin Portal

💬Slack Bot

All calling the sameHTTP Query API↓Your Functions Service

---

Common Patterns

Monorepo

Everything in one repo — simple for small projects.

my-app/
├── functions/          ← Part A (deploy separately)
│   └── src/
└── web/                ← Part B (your frontend)
    └── app/

Separate Repos (Recommended)

Better for teams and multiple interfaces.

# Functions Service (Part A)
my-agent/
├── src/functions/
└── package.json

# Website (Part B)
my-website/
└── components/ChatWidget.tsx

# Mobile App (Part B)
my-mobile/
└── screens/ChatScreen.tsx

---

API Reference

See the full HTTP Query API documentation → for:

• Request/response formats
• Streaming support
• Thread management
• Error handling

---

Deploying Your Chat Interface

Your chat interface deploys like any other frontend:

Platform	Good For
Vercel	Next.js, React
Netlify	Static sites, React
AWS Amplify	Full-stack AWS
App Store	iOS apps
Play Store	Android apps

Tip

The key insight: Your chat interface doesn't need the Daemo SDK. It just makes HTTP requests to the Query API.