Merge pull request #784 from pipecat-ai/mb/simple-bot-client

Update the simple-chatbot demo to have JS and React clients
This commit is contained in:
Mark Backman
2024-12-05 08:34:33 -05:00
committed by GitHub
60 changed files with 6209 additions and 302 deletions

View File

@@ -58,6 +58,9 @@ async def on_audio_data(processor, audio, sample_rate, num_channels):
- Updated the `FireworksLLMService` to use the `OpenAILLMService`. Updated the
default model to `accounts/fireworks/models/firefunction-v2`.
- Updated the `simple-chatbot` example to include a Javascript and React client
example, using RTVI JS and React.
### Removed
- Removed `AppFrame`. This was used as a special user custom frame, but there's

View File

@@ -1,161 +1,51 @@
# Byte-compiled / optimized / DLL files
# Python
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.pytest_cache/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
.pybuilder/
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# poetry
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
#poetry.lock
# pdm
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
# in version control.
# https://pdm.fming.dev/#use-with-ide
.pdm.toml
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# JavaScript/Node.js
node_modules/
dist/
dist-ssr/
*.local
.env.local
.env.development.local
.env.test.local
.env.production.local
# pytype static type analyzer
.pytype/
# Logs
logs/
*.log
npm-debug.log*
yarn-debug.log*
yarn-error.log*
pnpm-debug.log*
# Cython debug symbols
cython_debug/
# Editor/IDE
.vscode/*
!.vscode/extensions.json
.idea/
*.swp
*.swo
.DS_Store
# PyCharm
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
#.idea/
runpod.toml
# Project specific
runpod.toml

View File

@@ -2,36 +2,79 @@
<img src="image.png" width="420px">
This app connects you to a chatbot powered by GPT-4, complete with animations generated by Stable Video Diffusion.
This repository demonstrates a simple AI chatbot with real-time audio/video interaction, implemented in three different ways. The bot server remains the same, but you can connect to it using three different client approaches.
See a video of it in action: https://x.com/kwindla/status/1778628911817183509
## Three Ways to Connect
And a quick video walkthrough of the code: https://www.loom.com/share/13df1967161f4d24ade054e7f8753416
1. **Daily Prebuilt** (Simplest)
The first time, things might take extra time to get started since VAD (Voice Activity Detection) model needs to be downloaded.
- Direct connection through a Daily Prebuilt room
- For demo purposes only; handy for quick testing
## Get started
2. **JavaScript**
```python
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
- Basic implementation using RTVI JavaScript SDK
- No framework dependencies
- Good for learning the fundamentals
cp env.example .env # and add your credentials
3. **React**
- Basic impelmentation using RTVI React SDK
- Demonstrates the basic client principles with RTVI React
## Quick Start
### First, start the bot server:
1. Navigate to the server directory:
```bash
cd server
```
2. Create and activate a virtual environment:
```bash
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
```
3. Install requirements:
```bash
pip install -r requirements.txt
```
4. Copy env.example to .env and add your credentials
5. Start the server:
```bash
python server.py
```
### Next, connect using your preferred client app:
- [Daily Prebuilt](examples/prebuilt/README.md)
- [Vanilla JavaScript Guide](examples/javascript/README.md)
- [React Guide](examples/react/README.md)
## Important Note
The bot server must be running for any of the client implementations to work. Start the server first before trying any of the client apps.
## Requirements
- Python 3.10+
- Node.js 16+ (for JavaScript and React implementations)
- Daily API key
- OpenAI API key
- Cartesia API key
- Modern web browser with WebRTC support
## Project Structure
```
## Run the server
```bash
python server.py
```
Then, visit `http://localhost:7860/` in your browser to start a chatbot session.
## Build and test the Docker image
```
docker build -t chatbot .
docker run --env-file .env -p 7860:7860 chatbot
simple-chatbot-full-stack/
├── server/ # Bot server implementation
│ ├── bot.py # Bot logic and media handling
│ ├── runner.py # Server runner utilities
│ ├── server.py # FastAPI server
│ └── requirements.txt
└── examples/ # Client implementations
├── prebuilt/ # Daily Prebuilt connection
├── javascript/ # JavaScript RTVI client
└── react/ # React RTVI client
```

View File

@@ -0,0 +1,27 @@
# JavaScript Implementation
Basic implementation using the RTVI JavaScript SDK.
## Setup
1. Run the bot server; see [README](../../README).
2. Navigate to the `examples/javascript` directory:
```bash
cd examples/javascript
```
3. Install dependencies:
```bash
npm install
```
4. Run the client app:
```
npm run dev
```
5. Visit http://localhost:5173 in your browser.

View File

@@ -0,0 +1,40 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>AI Chatbot</title>
</head>
<body>
<div class="container">
<div class="status-bar">
<div class="status">
Status: <span id="connection-status">Disconnected</span>
</div>
<div class="controls">
<button id="connect-btn">Connect</button>
<button id="disconnect-btn" disabled>Disconnect</button>
</div>
</div>
<div class="main-content">
<div class="bot-container">
<div id="bot-video-container">
</div>
<audio id="bot-audio" autoplay></audio>
</div>
</div>
<div class="debug-panel">
<h3>Debug Info</h3>
<div id="debug-log"></div>
</div>
</div>
<script type="module" src="/src/app.js"></script>
<link rel="stylesheet" href="/src/style.css">
</body>
</html>

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,21 @@
{
"name": "client",
"version": "1.0.0",
"main": "index.js",
"scripts": {
"dev": "vite",
"build": "vite build",
"preview": "vite preview"
},
"keywords": [],
"author": "",
"license": "ISC",
"description": "",
"dependencies": {
"@daily-co/realtime-ai-daily": "^0.2.1",
"realtime-ai": "^0.2.1"
},
"devDependencies": {
"vite": "^6.0.2"
}
}

View File

@@ -0,0 +1,289 @@
/**
* Copyright (c) 2024, Daily
*
* SPDX-License-Identifier: BSD 2-Clause License
*/
/**
* RTVI Client Implementation
*
* This client connects to an RTVI-compatible bot server using WebRTC (via Daily).
* It handles audio/video streaming and manages the connection lifecycle.
*
* Requirements:
* - A running RTVI bot server (defaults to http://localhost:7860)
* - The server must implement the /connect endpoint that returns Daily.co room credentials
* - Browser with WebRTC support
*/
import { RTVIClient, RTVIEvent } from 'realtime-ai';
import { DailyTransport } from '@daily-co/realtime-ai-daily';
/**
* ChatbotClient handles the connection and media management for a real-time
* voice and video interaction with an AI bot.
*/
class ChatbotClient {
constructor() {
// Initialize client state
this.rtviClient = null;
this.setupDOMElements();
this.setupEventListeners();
}
/**
* Set up references to DOM elements and create necessary media elements
*/
setupDOMElements() {
// Get references to UI control elements
this.connectBtn = document.getElementById('connect-btn');
this.disconnectBtn = document.getElementById('disconnect-btn');
this.statusSpan = document.getElementById('connection-status');
this.debugLog = document.getElementById('debug-log');
this.botVideoContainer = document.getElementById('bot-video-container');
// Create an audio element for bot's voice output
this.botAudio = document.createElement('audio');
this.botAudio.autoplay = true;
this.botAudio.playsInline = true;
document.body.appendChild(this.botAudio);
}
/**
* Set up event listeners for connect/disconnect buttons
*/
setupEventListeners() {
this.connectBtn.addEventListener('click', () => this.connect());
this.disconnectBtn.addEventListener('click', () => this.disconnect());
}
/**
* Add a timestamped message to the debug log
*/
log(message) {
const entry = document.createElement('div');
entry.textContent = `${new Date().toISOString()} - ${message}`;
this.debugLog.appendChild(entry);
this.debugLog.scrollTop = this.debugLog.scrollHeight;
console.log(message);
}
/**
* Update the connection status display
*/
updateStatus(status) {
this.statusSpan.textContent = status;
this.log(`Status: ${status}`);
}
/**
* Check for available media tracks and set them up if present
* This is called when the bot is ready or when the transport state changes to ready
*/
setupMediaTracks() {
if (!this.rtviClient) return;
// Get current tracks from the client
const tracks = this.rtviClient.tracks();
// Set up any available bot tracks
if (tracks.bot?.audio) {
this.setupAudioTrack(tracks.bot.audio);
}
if (tracks.bot?.video) {
this.setupVideoTrack(tracks.bot.video);
}
}
/**
* Set up listeners for track events (start/stop)
* This handles new tracks being added during the session
*/
setupTrackListeners() {
if (!this.rtviClient) return;
// Listen for new tracks starting
this.rtviClient.on(RTVIEvent.TrackStarted, (track, participant) => {
// Only handle non-local (bot) tracks
if (!participant?.local) {
if (track.kind === 'audio') {
this.setupAudioTrack(track);
} else if (track.kind === 'video') {
this.setupVideoTrack(track);
}
}
});
// Listen for tracks stopping
this.rtviClient.on(RTVIEvent.TrackStopped, (track, participant) => {
this.log(
`Track stopped event: ${track.kind} from ${
participant?.name || 'unknown'
}`
);
});
}
/**
* Set up an audio track for playback
* Handles both initial setup and track updates
*/
setupAudioTrack(track) {
this.log('Setting up audio track');
// Check if we're already playing this track
if (this.botAudio.srcObject) {
const oldTrack = this.botAudio.srcObject.getAudioTracks()[0];
if (oldTrack?.id === track.id) return;
}
// Create a new MediaStream with the track and set it as the audio source
this.botAudio.srcObject = new MediaStream([track]);
}
/**
* Set up a video track for display
* Handles both initial setup and track updates
*/
setupVideoTrack(track) {
this.log('Setting up video track');
const videoEl = document.createElement('video');
videoEl.autoplay = true;
videoEl.playsInline = true;
videoEl.muted = true;
videoEl.style.width = '100%';
videoEl.style.height = '100%';
videoEl.style.objectFit = 'cover';
// Check if we're already displaying this track
if (this.botVideoContainer.querySelector('video')?.srcObject) {
const oldTrack = this.botVideoContainer
.querySelector('video')
.srcObject.getVideoTracks()[0];
if (oldTrack?.id === track.id) return;
}
// Create a new MediaStream with the track and set it as the video source
videoEl.srcObject = new MediaStream([track]);
this.botVideoContainer.innerHTML = '';
this.botVideoContainer.appendChild(videoEl);
}
/**
* Initialize and connect to the bot
* This sets up the RTVI client, initializes devices, and establishes the connection
*/
async connect() {
try {
// Create a new Daily transport for WebRTC communication
const transport = new DailyTransport();
// Initialize the RTVI client with our configuration
this.rtviClient = new RTVIClient({
transport,
params: {
// The baseURL and endpoint of your bot server that the client will connect to
baseUrl: 'http://localhost:7860',
endpoints: {
connect: '/connect',
},
},
enableMic: true, // Enable microphone for user input
enableCam: false,
callbacks: {
// Handle connection state changes
onConnected: () => {
this.updateStatus('Connected');
this.connectBtn.disabled = true;
this.disconnectBtn.disabled = false;
this.log('Client connected');
},
onDisconnected: () => {
this.updateStatus('Disconnected');
this.connectBtn.disabled = false;
this.disconnectBtn.disabled = true;
this.log('Client disconnected');
},
// Handle transport state changes
onTransportStateChanged: (state) => {
this.updateStatus(`Transport: ${state}`);
this.log(`Transport state changed: ${state}`);
if (state === 'ready') {
this.setupMediaTracks();
}
},
// Handle bot connection events
onBotConnected: (participant) => {
this.log(`Bot connected: ${JSON.stringify(participant)}`);
},
onBotDisconnected: (participant) => {
this.log(`Bot disconnected: ${JSON.stringify(participant)}`);
},
onBotReady: (data) => {
this.log(`Bot ready: ${JSON.stringify(data)}`);
this.setupMediaTracks();
},
},
});
// Set up listeners for media track events
this.setupTrackListeners();
// Initialize audio/video devices
this.log('Initializing devices...');
await this.rtviClient.initDevices();
// Connect to the bot
this.log('Connecting to bot...');
await this.rtviClient.connect();
this.log('Connection complete');
} catch (error) {
// Handle any errors during connection
this.log(`Error connecting: ${error.message}`);
this.log(`Error stack: ${error.stack}`);
this.updateStatus('Error');
// Clean up if there's an error
if (this.rtviClient) {
try {
await this.rtviClient.disconnect();
} catch (disconnectError) {
this.log(`Error during disconnect: ${disconnectError.message}`);
}
}
}
}
/**
* Disconnect from the bot and clean up media resources
*/
async disconnect() {
if (this.rtviClient) {
try {
// Disconnect the RTVI client
await this.rtviClient.disconnect();
this.rtviClient = null;
// Clean up audio
if (this.botAudio.srcObject) {
this.botAudio.srcObject.getTracks().forEach((track) => track.stop());
this.botAudio.srcObject = null;
}
// Clean up video
if (this.botVideoContainer.querySelector('video')?.srcObject) {
const video = this.botVideoContainer.querySelector('video');
video.srcObject.getTracks().forEach((track) => track.stop());
video.srcObject = null;
}
this.botVideoContainer.innerHTML = '';
} catch (error) {
this.log(`Error disconnecting: ${error.message}`);
}
}
}
}
// Initialize the client when the page loads
window.addEventListener('DOMContentLoaded', () => {
new ChatbotClient();
});

View File

@@ -0,0 +1,90 @@
body {
margin: 0;
padding: 20px;
font-family: Arial, sans-serif;
background-color: #f0f0f0;
}
.container {
max-width: 1200px;
margin: 0 auto;
}
.status-bar {
display: flex;
justify-content: space-between;
align-items: center;
padding: 10px;
background-color: #fff;
border-radius: 8px;
margin-bottom: 20px;
}
.controls button {
padding: 8px 16px;
margin-left: 10px;
border: none;
border-radius: 4px;
cursor: pointer;
}
#connect-btn {
background-color: #4caf50;
color: white;
}
#disconnect-btn {
background-color: #f44336;
color: white;
}
button:disabled {
opacity: 0.5;
cursor: not-allowed;
}
.main-content {
background-color: #fff;
border-radius: 8px;
padding: 20px;
margin-bottom: 20px;
}
.bot-container {
display: flex;
flex-direction: column;
align-items: center;
}
#bot-video-container {
width: 640px;
height: 360px;
background-color: #e0e0e0;
border-radius: 8px;
margin: 20px auto;
overflow: hidden;
display: flex;
align-items: center;
justify-content: center;
}
#bot-video-container video {
width: 100%;
height: 100%;
object-fit: cover;
}
.debug-panel {
background-color: #fff;
border-radius: 8px;
padding: 20px;
}
#debug-log {
height: 200px;
overflow-y: auto;
background-color: #f8f8f8;
padding: 10px;
border-radius: 4px;
font-family: monospace;
}

View File

@@ -0,0 +1,15 @@
# Daily Prebuilt Connection
The simplest way to connect to the chatbot using Daily's Prebuilt UI.
1. Start the bot server
```bash
python server/server.py
```
2. Visit http://localhost:7860
3. Allow microphone access when prompted
4. Start talking with the bot

View File

@@ -0,0 +1,24 @@
# Logs
logs
*.log
npm-debug.log*
yarn-debug.log*
yarn-error.log*
pnpm-debug.log*
lerna-debug.log*
node_modules
dist
dist-ssr
*.local
# Editor directories and files
.vscode/*
!.vscode/extensions.json
.idea
.DS_Store
*.suo
*.ntvs*
*.njsproj
*.sln
*.sw?

View File

@@ -0,0 +1,27 @@
# React Implementation
Basic implementation using the RTVI React SDK.
## Setup
1. Run the bot server; see [README](../../README).
2. Navigate to the `examples/react` directory:
```bash
cd examples/react
```
3. Install dependencies:
```bash
npm install
```
4. Run the client app:
```
npm run dev
```
5. Visit http://localhost:5173 in your browser.

View File

@@ -0,0 +1,28 @@
import js from '@eslint/js'
import globals from 'globals'
import reactHooks from 'eslint-plugin-react-hooks'
import reactRefresh from 'eslint-plugin-react-refresh'
import tseslint from 'typescript-eslint'
export default tseslint.config(
{ ignores: ['dist'] },
{
extends: [js.configs.recommended, ...tseslint.configs.recommended],
files: ['**/*.{ts,tsx}'],
languageOptions: {
ecmaVersion: 2020,
globals: globals.browser,
},
plugins: {
'react-hooks': reactHooks,
'react-refresh': reactRefresh,
},
rules: {
...reactHooks.configs.recommended.rules,
'react-refresh/only-export-components': [
'warn',
{ allowConstantExport: true },
],
},
},
)

View File

@@ -0,0 +1,15 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>RTVI React Client</title>
</head>
<body>
<div id="root"></div>
<script type="module" src="/src/main.tsx"></script>
</body>
</html>

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,32 @@
{
"name": "react",
"private": true,
"version": "0.0.0",
"type": "module",
"scripts": {
"dev": "vite",
"build": "tsc && vite build",
"lint": "eslint .",
"preview": "vite preview"
},
"dependencies": {
"@daily-co/realtime-ai-daily": "^0.2.1",
"react": "^18.3.1",
"react-dom": "^18.3.1",
"realtime-ai": "^0.2.1",
"realtime-ai-react": "^0.2.1"
},
"devDependencies": {
"@eslint/js": "^9.15.0",
"@types/react": "^18.3.12",
"@types/react-dom": "^18.3.1",
"@vitejs/plugin-react": "^4.3.4",
"eslint": "^9.15.0",
"eslint-plugin-react-hooks": "^5.0.0",
"eslint-plugin-react-refresh": "^0.4.14",
"globals": "^15.12.0",
"typescript": "~5.6.2",
"typescript-eslint": "^8.15.0",
"vite": "^6.0.1"
}
}

View File

@@ -0,0 +1,82 @@
body {
margin: 0;
padding: 20px;
font-family: Arial, sans-serif;
background-color: #f0f0f0;
}
.app {
max-width: 1200px;
margin: 0 auto;
}
.status-bar {
display: flex;
justify-content: space-between;
align-items: center;
padding: 10px;
background-color: #fff;
border-radius: 8px;
margin-bottom: 20px;
}
.controls button {
padding: 8px 16px;
margin-left: 10px;
border: none;
border-radius: 4px;
cursor: pointer;
}
button:disabled {
opacity: 0.5;
cursor: not-allowed;
}
.connect-btn {
background-color: #4caf50;
color: white;
}
.disconnect-btn {
background-color: #f44336;
color: white;
}
.main-content {
background-color: #fff;
border-radius: 8px;
padding: 20px;
margin-bottom: 20px;
}
.bot-container {
display: flex;
flex-direction: column;
align-items: center;
}
.video-container {
width: 640px;
height: 360px;
background-color: #ddd;
margin-bottom: 20px;
border-radius: 8px;
overflow: hidden;
}
.video-container video {
width: 100%;
height: 100%;
object-fit: cover;
}
.mic-enabled {
background-color: #4caf50;
color: white;
}
.mic-disabled {
background-color: #f44336;
color: white;
}

View File

@@ -0,0 +1,51 @@
import {
RTVIClientAudio,
RTVIClientVideo,
useRTVIClientTransportState,
} from 'realtime-ai-react';
import { RTVIProvider } from './providers/RTVIProvider';
import { ConnectButton } from './components/ConnectButton';
import { StatusDisplay } from './components/StatusDisplay';
import { DebugDisplay } from './components/DebugDisplay';
import './App.css';
function BotVideo() {
const transportState = useRTVIClientTransportState();
const isConnected = transportState !== 'disconnected';
return (
<div className="bot-container">
<div className="video-container">
{isConnected && <RTVIClientVideo participant="bot" fit="cover" />}
</div>
</div>
);
}
function AppContent() {
return (
<div className="app">
<div className="status-bar">
<StatusDisplay />
<ConnectButton />
</div>
<div className="main-content">
<BotVideo />
</div>
<DebugDisplay />
<RTVIClientAudio />
</div>
);
}
function App() {
return (
<RTVIProvider>
<AppContent />
</RTVIProvider>
);
}
export default App;

View File

@@ -0,0 +1,37 @@
import { useRTVIClient, useRTVIClientTransportState } from 'realtime-ai-react';
export function ConnectButton() {
const client = useRTVIClient();
const transportState = useRTVIClientTransportState();
const isConnected = ['connected', 'ready'].includes(transportState);
const handleClick = async () => {
if (!client) {
console.error('RTVI client is not initialized');
return;
}
try {
if (isConnected) {
await client.disconnect();
} else {
await client.connect();
}
} catch (error) {
console.error('Connection error:', error);
}
};
return (
<div className="controls">
<button
className={isConnected ? 'disconnect-btn' : 'connect-btn'}
onClick={handleClick}
disabled={
!client || ['connecting', 'disconnecting'].includes(transportState)
}>
{isConnected ? 'Disconnect' : 'Connect'}
</button>
</div>
);
}

View File

@@ -0,0 +1,26 @@
.debug-panel {
background-color: #fff;
border-radius: 8px;
padding: 20px;
}
.debug-panel h3 {
margin: 0 0 10px 0;
font-size: 16px;
font-weight: bold;
}
.debug-log {
height: 200px;
overflow-y: auto;
background-color: #f8f8f8;
padding: 10px;
border-radius: 4px;
font-family: monospace;
font-size: 12px;
line-height: 1.4;
}
.debug-log div {
margin-bottom: 4px;
}

View File

@@ -0,0 +1,106 @@
import { useRef, useCallback } from 'react';
import { Participant, RTVIEvent, TransportState } from 'realtime-ai';
import { useRTVIClient, useRTVIClientEvent } from 'realtime-ai-react';
import './DebugDisplay.css';
export function DebugDisplay() {
const debugLogRef = useRef<HTMLDivElement>(null);
const client = useRTVIClient();
const log = useCallback((message: string) => {
if (!debugLogRef.current) return;
const entry = document.createElement('div');
entry.textContent = `${new Date().toISOString()} - ${message}`;
debugLogRef.current.appendChild(entry);
debugLogRef.current.scrollTop = debugLogRef.current.scrollHeight;
}, []);
// Log transport state changes
useRTVIClientEvent(
RTVIEvent.TransportStateChanged,
useCallback(
(state: TransportState) => {
log(`Transport state changed: ${state}`);
},
[log]
)
);
// Log bot connection events
useRTVIClientEvent(
RTVIEvent.BotConnected,
useCallback(
(participant?: Participant) => {
log(`Bot connected: ${JSON.stringify(participant)}`);
},
[log]
)
);
useRTVIClientEvent(
RTVIEvent.BotDisconnected,
useCallback(
(participant?: Participant) => {
log(`Bot disconnected: ${JSON.stringify(participant)}`);
},
[log]
)
);
// Log track events
useRTVIClientEvent(
RTVIEvent.TrackStarted,
useCallback(
(track: MediaStreamTrack, participant?: Participant) => {
log(
`Track started: ${track.kind} from ${participant?.name || 'unknown'}`
);
},
[log]
)
);
useRTVIClientEvent(
RTVIEvent.TrackedStopped,
useCallback(
(track: MediaStreamTrack, participant?: Participant) => {
log(
`Track stopped: ${track.kind} from ${participant?.name || 'unknown'}`
);
},
[log]
)
);
// Log bot ready state and check tracks
useRTVIClientEvent(
RTVIEvent.BotReady,
useCallback(() => {
log(`Bot ready`);
if (!client) return;
const tracks = client.tracks();
log(
`Available tracks: ${JSON.stringify({
local: {
audio: !!tracks.local.audio,
video: !!tracks.local.video,
},
bot: {
audio: !!tracks.bot?.audio,
video: !!tracks.bot?.video,
},
})}`
);
}, [client, log])
);
return (
<div className="debug-panel">
<h3>Debug Info</h3>
<div ref={debugLogRef} className="debug-log" />
</div>
);
}

View File

@@ -0,0 +1,11 @@
import { useRTVIClientTransportState } from 'realtime-ai-react';
export function StatusDisplay() {
const transportState = useRTVIClientTransportState();
return (
<div className="status">
Status: <span>{transportState}</span>
</div>
);
}

View File

@@ -0,0 +1,9 @@
import React from 'react';
import ReactDOM from 'react-dom/client';
import App from './App';
ReactDOM.createRoot(document.getElementById('root')!).render(
<React.StrictMode>
<App />
</React.StrictMode>
);

View File

@@ -0,0 +1,22 @@
import { type PropsWithChildren } from 'react';
import { RTVIClient } from 'realtime-ai';
import { DailyTransport } from '@daily-co/realtime-ai-daily';
import { RTVIClientProvider } from 'realtime-ai-react';
const transport = new DailyTransport();
const client = new RTVIClient({
transport,
params: {
baseUrl: 'http://localhost:7860',
endpoints: {
connect: '/connect',
},
},
enableMic: true,
enableCam: false,
});
export function RTVIProvider({ children }: PropsWithChildren) {
return <RTVIClientProvider client={client}>{children}</RTVIClientProvider>;
}

View File

@@ -0,0 +1,25 @@
{
"compilerOptions": {
"target": "ES2020",
"useDefineForClassFields": true,
"lib": ["ES2020", "DOM", "DOM.Iterable"],
"module": "ESNext",
"skipLibCheck": true,
/* Bundler mode */
"moduleResolution": "bundler",
"allowImportingTsExtensions": true,
"resolveJsonModule": true,
"isolatedModules": true,
"noEmit": true,
"jsx": "react-jsx",
/* Linting */
"strict": true,
"noUnusedLocals": true,
"noUnusedParameters": true,
"noFallthroughCasesInSwitch": true
},
"include": ["src"],
"references": [{ "path": "./tsconfig.node.json" }]
}

View File

@@ -0,0 +1,10 @@
{
"compilerOptions": {
"composite": true,
"skipLibCheck": true,
"module": "ESNext",
"moduleResolution": "bundler",
"allowSyntheticDefaultImports": true
},
"include": ["vite.config.ts"]
}

View File

@@ -0,0 +1,7 @@
import { defineConfig } from 'vite'
import react from '@vitejs/plugin-react'
// https://vite.dev/config/
export default defineConfig({
plugins: [react()],
})

View File

@@ -1,141 +0,0 @@
#
# Copyright (c) 2024, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import aiohttp
import os
import argparse
import subprocess
from contextlib import asynccontextmanager
from fastapi import FastAPI, Request, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import JSONResponse, RedirectResponse
from pipecat.transports.services.helpers.daily_rest import DailyRESTHelper, DailyRoomParams
from dotenv import load_dotenv
load_dotenv(override=True)
MAX_BOTS_PER_ROOM = 1
# Bot sub-process dict for status reporting and concurrency control
bot_procs = {}
daily_helpers = {}
def cleanup():
# Clean up function, just to be extra safe
for entry in bot_procs.values():
proc = entry[0]
proc.terminate()
proc.wait()
@asynccontextmanager
async def lifespan(app: FastAPI):
aiohttp_session = aiohttp.ClientSession()
daily_helpers["rest"] = DailyRESTHelper(
daily_api_key=os.getenv("DAILY_API_KEY", ""),
daily_api_url=os.getenv("DAILY_API_URL", "https://api.daily.co/v1"),
aiohttp_session=aiohttp_session,
)
yield
await aiohttp_session.close()
cleanup()
app = FastAPI(lifespan=lifespan)
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
@app.get("/")
async def start_agent(request: Request):
print(f"!!! Creating room")
room = await daily_helpers["rest"].create_room(DailyRoomParams())
print(f"!!! Room URL: {room.url}")
# Ensure the room property is present
if not room.url:
raise HTTPException(
status_code=500,
detail="Missing 'room' property in request data. Cannot start agent without a target room!",
)
# Check if there is already an existing process running in this room
num_bots_in_room = sum(
1 for proc in bot_procs.values() if proc[1] == room.url and proc[0].poll() is None
)
if num_bots_in_room >= MAX_BOTS_PER_ROOM:
raise HTTPException(status_code=500, detail=f"Max bot limited reach for room: {room.url}")
# Get the token for the room
token = await daily_helpers["rest"].get_token(room.url)
if not token:
raise HTTPException(status_code=500, detail=f"Failed to get token for room: {room.url}")
# Spawn a new agent, and join the user session
# Note: this is mostly for demonstration purposes (refer to 'deployment' in README)
try:
proc = subprocess.Popen(
[f"python3 -m bot -u {room.url} -t {token}"],
shell=True,
bufsize=1,
cwd=os.path.dirname(os.path.abspath(__file__)),
)
bot_procs[proc.pid] = (proc, room.url)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Failed to start subprocess: {e}")
return RedirectResponse(room.url)
@app.get("/status/{pid}")
def get_status(pid: int):
# Look up the subprocess
proc = bot_procs.get(pid)
# If the subprocess doesn't exist, return an error
if not proc:
raise HTTPException(status_code=404, detail=f"Bot with process id: {pid} not found")
# Check the status of the subprocess
if proc[0].poll() is None:
status = "running"
else:
status = "finished"
return JSONResponse({"bot_id": pid, "status": status})
if __name__ == "__main__":
import uvicorn
default_host = os.getenv("HOST", "0.0.0.0")
default_port = int(os.getenv("FAST_API_PORT", "7860"))
parser = argparse.ArgumentParser(description="Daily Storyteller FastAPI server")
parser.add_argument("--host", type=str, default=default_host, help="Host address")
parser.add_argument("--port", type=int, default=default_port, help="Port number")
parser.add_argument("--reload", action="store_true", help="Reload code on change")
config = parser.parse_args()
uvicorn.run(
"server:app",
host=config.host,
port=config.port,
reload=config.reload,
)

View File

@@ -0,0 +1,43 @@
# Simple Chatbot Server
A FastAPI server that manages bot instances and provides endpoints for both Daily Prebuilt and RTVI client connections.
## Endpoints
- `GET /` - Direct browser access, redirects to a Daily Prebuilt room
- `POST /connect` - RTVI client connection endpoint
- `GET /status/{pid}` - Get status of a specific bot process
## Environment Variables
Copy `env.example` to `.env` and configure:
```ini
DAILY_API_KEY= # Your Daily API key
DAILY_API_URL= # Optional: Daily API URL (defaults to https://api.daily.co/v1)
OPENAI_API_KEY= # Your OpenAI API key
CARTESIA_API_KEY= # Your Cartesia API key
HOST= # Optional: Host address (defaults to 0.0.0.0)
FAST_API_PORT= # Optional: Port number (defaults to 7860)
```
## Running the Server
Set up and activate your virtual environment:
```bash
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
```
Install dependencies:
```bash
pip install -r requirements.txt
```
Run the server:
```bash
python server.py
```

View File

Before

Width:  |  Height:  |  Size: 759 KiB

After

Width:  |  Height:  |  Size: 759 KiB

View File

Before

Width:  |  Height:  |  Size: 884 KiB

After

Width:  |  Height:  |  Size: 884 KiB

View File

Before

Width:  |  Height:  |  Size: 876 KiB

After

Width:  |  Height:  |  Size: 876 KiB

View File

Before

Width:  |  Height:  |  Size: 881 KiB

After

Width:  |  Height:  |  Size: 881 KiB

View File

Before

Width:  |  Height:  |  Size: 866 KiB

After

Width:  |  Height:  |  Size: 866 KiB

View File

Before

Width:  |  Height:  |  Size: 874 KiB

After

Width:  |  Height:  |  Size: 874 KiB

View File

Before

Width:  |  Height:  |  Size: 882 KiB

After

Width:  |  Height:  |  Size: 882 KiB

View File

Before

Width:  |  Height:  |  Size: 885 KiB

After

Width:  |  Height:  |  Size: 885 KiB

View File

Before

Width:  |  Height:  |  Size: 888 KiB

After

Width:  |  Height:  |  Size: 888 KiB

View File

Before

Width:  |  Height:  |  Size: 890 KiB

After

Width:  |  Height:  |  Size: 890 KiB

View File

Before

Width:  |  Height:  |  Size: 898 KiB

After

Width:  |  Height:  |  Size: 898 KiB

View File

Before

Width:  |  Height:  |  Size: 836 KiB

After

Width:  |  Height:  |  Size: 836 KiB

View File

Before

Width:  |  Height:  |  Size: 903 KiB

After

Width:  |  Height:  |  Size: 903 KiB

View File

Before

Width:  |  Height:  |  Size: 908 KiB

After

Width:  |  Height:  |  Size: 908 KiB

View File

Before

Width:  |  Height:  |  Size: 908 KiB

After

Width:  |  Height:  |  Size: 908 KiB

View File

Before

Width:  |  Height:  |  Size: 905 KiB

After

Width:  |  Height:  |  Size: 905 KiB

View File

Before

Width:  |  Height:  |  Size: 903 KiB

After

Width:  |  Height:  |  Size: 903 KiB

View File

Before

Width:  |  Height:  |  Size: 866 KiB

After

Width:  |  Height:  |  Size: 866 KiB

View File

Before

Width:  |  Height:  |  Size: 849 KiB

After

Width:  |  Height:  |  Size: 849 KiB

View File

Before

Width:  |  Height:  |  Size: 866 KiB

After

Width:  |  Height:  |  Size: 866 KiB

View File

Before

Width:  |  Height:  |  Size: 866 KiB

After

Width:  |  Height:  |  Size: 866 KiB

View File

Before

Width:  |  Height:  |  Size: 864 KiB

After

Width:  |  Height:  |  Size: 864 KiB

View File

Before

Width:  |  Height:  |  Size: 858 KiB

After

Width:  |  Height:  |  Size: 858 KiB

View File

Before

Width:  |  Height:  |  Size: 875 KiB

After

Width:  |  Height:  |  Size: 875 KiB

View File

Before

Width:  |  Height:  |  Size: 881 KiB

After

Width:  |  Height:  |  Size: 881 KiB

View File

@@ -18,6 +18,7 @@ from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import (
BotStartedSpeakingFrame,
BotStoppedSpeakingFrame,
EndFrame,
Frame,
LLMMessagesFrame,
OutputImageRawFrame,
@@ -162,6 +163,11 @@ async def main():
await transport.capture_participant_transcription(participant["id"])
await task.queue_frames([LLMMessagesFrame(messages)])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
print(f"Participant left: {participant}")
await task.queue_frame(EndFrame())
runner = PipelineRunner()
await runner.run(task)

View File

@@ -0,0 +1,231 @@
#
# Copyright (c) 2024, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
"""
RTVI Bot Server Implementation
This FastAPI server manages RTVI bot instances and provides endpoints for both
direct browser access and RTVI client connections. It handles:
- Creating Daily rooms
- Managing bot processes
- Providing connection credentials
- Monitoring bot status
Requirements:
- Daily API key (set in .env file)
- Python 3.10+
- FastAPI
- Running bot implementation
"""
import argparse
import os
import subprocess
from contextlib import asynccontextmanager
from typing import Any, Dict
import aiohttp
from dotenv import load_dotenv
from fastapi import FastAPI, HTTPException, Request
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import JSONResponse, RedirectResponse
from pipecat.transports.services.helpers.daily_rest import DailyRESTHelper, DailyRoomParams
# Load environment variables from .env file
load_dotenv(override=True)
# Maximum number of bot instances allowed per room
MAX_BOTS_PER_ROOM = 1
# Dictionary to track bot processes: {pid: (process, room_url)}
bot_procs = {}
# Store Daily API helpers
daily_helpers = {}
def cleanup():
"""
Cleanup function to terminate all bot processes.
Called during server shutdown.
"""
for entry in bot_procs.values():
proc = entry[0]
proc.terminate()
proc.wait()
@asynccontextmanager
async def lifespan(app: FastAPI):
"""
FastAPI lifespan manager that handles startup and shutdown tasks:
- Creates aiohttp session
- Initializes Daily API helper
- Cleans up resources on shutdown
"""
aiohttp_session = aiohttp.ClientSession()
daily_helpers["rest"] = DailyRESTHelper(
daily_api_key=os.getenv("DAILY_API_KEY", ""),
daily_api_url=os.getenv("DAILY_API_URL", "https://api.daily.co/v1"),
aiohttp_session=aiohttp_session,
)
yield
await aiohttp_session.close()
cleanup()
# Initialize FastAPI app with lifespan manager
app = FastAPI(lifespan=lifespan)
# Configure CORS to allow requests from any origin
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
async def create_room_and_token() -> tuple[str, str]:
"""
Helper function to create a Daily room and generate an access token.
Returns:
tuple[str, str]: A tuple containing (room_url, token)
Raises:
HTTPException: If room creation or token generation fails
"""
room = await daily_helpers["rest"].create_room(DailyRoomParams())
if not room.url:
raise HTTPException(status_code=500, detail="Failed to create room")
token = await daily_helpers["rest"].get_token(room.url)
if not token:
raise HTTPException(status_code=500, detail=f"Failed to get token for room: {room.url}")
return room.url, token
@app.get("/")
async def start_agent(request: Request):
"""
Endpoint for direct browser access to the bot.
Creates a room, starts a bot instance, and redirects to the Daily room URL.
Returns:
RedirectResponse: Redirects to the Daily room URL
Raises:
HTTPException: If room creation, token generation, or bot startup fails
"""
print("Creating room")
room_url, token = await create_room_and_token()
print(f"Room URL: {room_url}")
# Check if there is already an existing process running in this room
num_bots_in_room = sum(
1 for proc in bot_procs.values() if proc[1] == room_url and proc[0].poll() is None
)
if num_bots_in_room >= MAX_BOTS_PER_ROOM:
raise HTTPException(status_code=500, detail=f"Max bot limit reached for room: {room_url}")
# Spawn a new bot process
try:
proc = subprocess.Popen(
[f"python3 -m bot -u {room_url} -t {token}"],
shell=True,
bufsize=1,
cwd=os.path.dirname(os.path.abspath(__file__)),
)
bot_procs[proc.pid] = (proc, room_url)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Failed to start subprocess: {e}")
return RedirectResponse(room_url)
@app.post("/connect")
async def rtvi_connect(request: Request) -> Dict[Any, Any]:
"""
RTVI connect endpoint that creates a room and returns connection credentials.
This endpoint is called by RTVI clients to establish a connection.
Returns:
Dict[Any, Any]: Authentication bundle containing room_url and token
Raises:
HTTPException: If room creation, token generation, or bot startup fails
"""
print("Creating room for RTVI connection")
room_url, token = await create_room_and_token()
print(f"Room URL: {room_url}")
# Start the bot process
try:
proc = subprocess.Popen(
[f"python3 -m bot -u {room_url} -t {token}"],
shell=True,
bufsize=1,
cwd=os.path.dirname(os.path.abspath(__file__)),
)
bot_procs[proc.pid] = (proc, room_url)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Failed to start subprocess: {e}")
# Return the authentication bundle in format expected by DailyTransport
return {"room_url": room_url, "token": token}
@app.get("/status/{pid}")
def get_status(pid: int):
"""
Get the status of a specific bot process.
Args:
pid (int): Process ID of the bot
Returns:
JSONResponse: Status information for the bot
Raises:
HTTPException: If the specified bot process is not found
"""
# Look up the subprocess
proc = bot_procs.get(pid)
# If the subprocess doesn't exist, return an error
if not proc:
raise HTTPException(status_code=404, detail=f"Bot with process id: {pid} not found")
# Check the status of the subprocess
status = "running" if proc[0].poll() is None else "finished"
return JSONResponse({"bot_id": pid, "status": status})
if __name__ == "__main__":
import uvicorn
# Parse command line arguments for server configuration
default_host = os.getenv("HOST", "0.0.0.0")
default_port = int(os.getenv("FAST_API_PORT", "7860"))
parser = argparse.ArgumentParser(description="Daily Storyteller FastAPI server")
parser.add_argument("--host", type=str, default=default_host, help="Host address")
parser.add_argument("--port", type=int, default=default_port, help="Port number")
parser.add_argument("--reload", action="store_true", help="Reload code on change")
config = parser.parse_args()
# Start the FastAPI server
uvicorn.run(
"server:app",
host=config.host,
port=config.port,
reload=config.reload,
)