mirror of
https://github.com/HumanAIGC-Engineering/gradio-webrtc.git
synced 2026-02-05 18:09:23 +08:00
[feat] update some feature
sync code of fastrtc, add text support through datachannel, fix safari connect problem support chat without camera or mic
This commit is contained in:
huangbinchao.hbc
15
demo/talk_to_openai/README.md
Normal file
15
demo/talk_to_openai/README.md
Normal file
@@ -0,0 +1,15 @@
|
||||
---
|
||||
title: Talk to OpenAI
|
||||
emoji: 🗣️
|
||||
colorFrom: purple
|
||||
colorTo: red
|
||||
sdk: gradio
|
||||
sdk_version: 5.16.0
|
||||
app_file: app.py
|
||||
pinned: false
|
||||
license: mit
|
||||
short_description: Talk to OpenAI using their multimodal API
|
||||
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|OPENAI_API_KEY]
|
||||
---
|
||||
|
||||
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
||||
15
demo/talk_to_openai/README_gradio.md
Normal file
15
demo/talk_to_openai/README_gradio.md
Normal file
@@ -0,0 +1,15 @@
|
||||
---
|
||||
title: Talk to OpenAI (Gradio UI)
|
||||
emoji: 🗣️
|
||||
colorFrom: purple
|
||||
colorTo: red
|
||||
sdk: gradio
|
||||
sdk_version: 5.16.0
|
||||
app_file: app.py
|
||||
pinned: false
|
||||
license: mit
|
||||
short_description: Talk to OpenAI (Gradio UI)
|
||||
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|OPENAI_API_KEY]
|
||||
---
|
||||
|
||||
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
||||
141
demo/talk_to_openai/app.py
Normal file
141
demo/talk_to_openai/app.py
Normal file
@@ -0,0 +1,141 @@
|
||||
import asyncio
|
||||
import base64
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
import gradio as gr
|
||||
import numpy as np
|
||||
import openai
|
||||
from dotenv import load_dotenv
|
||||
from fastapi import FastAPI
|
||||
from fastapi.responses import HTMLResponse, StreamingResponse
|
||||
from fastrtc import (
|
||||
AdditionalOutputs,
|
||||
AsyncStreamHandler,
|
||||
Stream,
|
||||
get_twilio_turn_credentials,
|
||||
wait_for_item,
|
||||
)
|
||||
from gradio.utils import get_space
|
||||
from openai.types.beta.realtime import ResponseAudioTranscriptDoneEvent
|
||||
|
||||
load_dotenv()
|
||||
|
||||
cur_dir = Path(__file__).parent
|
||||
|
||||
SAMPLE_RATE = 24000
|
||||
|
||||
|
||||
class OpenAIHandler(AsyncStreamHandler):
|
||||
def __init__(
|
||||
self,
|
||||
) -> None:
|
||||
super().__init__(
|
||||
expected_layout="mono",
|
||||
output_sample_rate=SAMPLE_RATE,
|
||||
output_frame_size=480,
|
||||
input_sample_rate=SAMPLE_RATE,
|
||||
)
|
||||
self.connection = None
|
||||
self.output_queue = asyncio.Queue()
|
||||
|
||||
def copy(self):
|
||||
return OpenAIHandler()
|
||||
|
||||
async def start_up(
|
||||
self,
|
||||
):
|
||||
"""Connect to realtime API. Run forever in separate thread to keep connection open."""
|
||||
self.client = openai.AsyncOpenAI()
|
||||
async with self.client.beta.realtime.connect(
|
||||
model="gpt-4o-mini-realtime-preview-2024-12-17"
|
||||
) as conn:
|
||||
await conn.session.update(
|
||||
session={"turn_detection": {"type": "server_vad"}}
|
||||
)
|
||||
self.connection = conn
|
||||
async for event in self.connection:
|
||||
if event.type == "response.audio_transcript.done":
|
||||
await self.output_queue.put(AdditionalOutputs(event))
|
||||
if event.type == "response.audio.delta":
|
||||
await self.output_queue.put(
|
||||
(
|
||||
self.output_sample_rate,
|
||||
np.frombuffer(
|
||||
base64.b64decode(event.delta), dtype=np.int16
|
||||
).reshape(1, -1),
|
||||
),
|
||||
)
|
||||
|
||||
async def receive(self, frame: tuple[int, np.ndarray]) -> None:
|
||||
if not self.connection:
|
||||
return
|
||||
_, array = frame
|
||||
array = array.squeeze()
|
||||
audio_message = base64.b64encode(array.tobytes()).decode("utf-8")
|
||||
await self.connection.input_audio_buffer.append(audio=audio_message) # type: ignore
|
||||
|
||||
async def emit(self) -> tuple[int, np.ndarray] | AdditionalOutputs | None:
|
||||
return await wait_for_item(self.output_queue)
|
||||
|
||||
async def shutdown(self) -> None:
|
||||
if self.connection:
|
||||
await self.connection.close()
|
||||
self.connection = None
|
||||
|
||||
|
||||
def update_chatbot(chatbot: list[dict], response: ResponseAudioTranscriptDoneEvent):
|
||||
chatbot.append({"role": "assistant", "content": response.transcript})
|
||||
return chatbot
|
||||
|
||||
|
||||
chatbot = gr.Chatbot(type="messages")
|
||||
latest_message = gr.Textbox(type="text", visible=False)
|
||||
stream = Stream(
|
||||
OpenAIHandler(),
|
||||
mode="send-receive",
|
||||
modality="audio",
|
||||
additional_inputs=[chatbot],
|
||||
additional_outputs=[chatbot],
|
||||
additional_outputs_handler=update_chatbot,
|
||||
rtc_configuration=get_twilio_turn_credentials() if get_space() else None,
|
||||
concurrency_limit=5 if get_space() else None,
|
||||
time_limit=90 if get_space() else None,
|
||||
)
|
||||
|
||||
app = FastAPI()
|
||||
|
||||
stream.mount(app)
|
||||
|
||||
|
||||
@app.get("/")
|
||||
async def _():
|
||||
rtc_config = get_twilio_turn_credentials() if get_space() else None
|
||||
html_content = (cur_dir / "index.html").read_text()
|
||||
html_content = html_content.replace("__RTC_CONFIGURATION__", json.dumps(rtc_config))
|
||||
return HTMLResponse(content=html_content)
|
||||
|
||||
|
||||
@app.get("/outputs")
|
||||
def _(webrtc_id: str):
|
||||
async def output_stream():
|
||||
import json
|
||||
|
||||
async for output in stream.output_stream(webrtc_id):
|
||||
s = json.dumps({"role": "assistant", "content": output.args[0].transcript})
|
||||
yield f"event: output\ndata: {s}\n\n"
|
||||
|
||||
return StreamingResponse(output_stream(), media_type="text/event-stream")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import os
|
||||
|
||||
if (mode := os.getenv("MODE")) == "UI":
|
||||
stream.ui.launch(server_port=7860)
|
||||
elif mode == "PHONE":
|
||||
stream.fastphone(host="0.0.0.0", port=7860)
|
||||
else:
|
||||
import uvicorn
|
||||
|
||||
uvicorn.run(app, host="0.0.0.0", port=7860)
|
||||
404
demo/talk_to_openai/index.html
Normal file
404
demo/talk_to_openai/index.html
Normal file
@@ -0,0 +1,404 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>OpenAI Real-Time Chat</title>
|
||||
<style>
|
||||
body {
|
||||
font-family: "SF Pro Display", -apple-system, BlinkMacSystemFont, sans-serif;
|
||||
background-color: #0a0a0a;
|
||||
color: #ffffff;
|
||||
margin: 0;
|
||||
padding: 20px;
|
||||
height: 100vh;
|
||||
box-sizing: border-box;
|
||||
}
|
||||
|
||||
.container {
|
||||
max-width: 800px;
|
||||
margin: 0 auto;
|
||||
height: calc(100% - 100px);
|
||||
}
|
||||
|
||||
.logo {
|
||||
text-align: center;
|
||||
margin-bottom: 40px;
|
||||
}
|
||||
|
||||
.chat-container {
|
||||
border: 1px solid #333;
|
||||
padding: 20px;
|
||||
height: 90%;
|
||||
box-sizing: border-box;
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
}
|
||||
|
||||
.chat-messages {
|
||||
flex-grow: 1;
|
||||
overflow-y: auto;
|
||||
margin-bottom: 20px;
|
||||
padding: 10px;
|
||||
}
|
||||
|
||||
.message {
|
||||
margin-bottom: 20px;
|
||||
padding: 12px;
|
||||
border-radius: 4px;
|
||||
font-size: 16px;
|
||||
line-height: 1.5;
|
||||
}
|
||||
|
||||
.message.user {
|
||||
background-color: #1a1a1a;
|
||||
margin-left: 20%;
|
||||
}
|
||||
|
||||
.message.assistant {
|
||||
background-color: #262626;
|
||||
margin-right: 20%;
|
||||
}
|
||||
|
||||
.controls {
|
||||
text-align: center;
|
||||
margin-top: 20px;
|
||||
}
|
||||
|
||||
button {
|
||||
background-color: transparent;
|
||||
color: #ffffff;
|
||||
border: 1px solid #ffffff;
|
||||
padding: 12px 24px;
|
||||
font-family: inherit;
|
||||
font-size: 16px;
|
||||
cursor: pointer;
|
||||
transition: all 0.3s;
|
||||
text-transform: uppercase;
|
||||
letter-spacing: 1px;
|
||||
}
|
||||
|
||||
button:hover {
|
||||
border-width: 2px;
|
||||
transform: scale(1.02);
|
||||
box-shadow: 0 0 10px rgba(255, 255, 255, 0.2);
|
||||
}
|
||||
|
||||
#audio-output {
|
||||
display: none;
|
||||
}
|
||||
|
||||
.icon-with-spinner {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
gap: 12px;
|
||||
min-width: 180px;
|
||||
}
|
||||
|
||||
.spinner {
|
||||
width: 20px;
|
||||
height: 20px;
|
||||
border: 2px solid #ffffff;
|
||||
border-top-color: transparent;
|
||||
border-radius: 50%;
|
||||
animation: spin 1s linear infinite;
|
||||
flex-shrink: 0;
|
||||
}
|
||||
|
||||
@keyframes spin {
|
||||
to {
|
||||
transform: rotate(360deg);
|
||||
}
|
||||
}
|
||||
|
||||
.pulse-container {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
gap: 12px;
|
||||
min-width: 180px;
|
||||
}
|
||||
|
||||
.pulse-circle {
|
||||
width: 20px;
|
||||
height: 20px;
|
||||
border-radius: 50%;
|
||||
background-color: #ffffff;
|
||||
opacity: 0.2;
|
||||
flex-shrink: 0;
|
||||
transform: translateX(-0%) scale(var(--audio-level, 1));
|
||||
transition: transform 0.1s ease;
|
||||
}
|
||||
|
||||
/* Add styles for toast notifications */
|
||||
.toast {
|
||||
position: fixed;
|
||||
top: 20px;
|
||||
left: 50%;
|
||||
transform: translateX(-50%);
|
||||
padding: 16px 24px;
|
||||
border-radius: 4px;
|
||||
font-size: 14px;
|
||||
z-index: 1000;
|
||||
display: none;
|
||||
box-shadow: 0 2px 5px rgba(0, 0, 0, 0.2);
|
||||
}
|
||||
|
||||
.toast.error {
|
||||
background-color: #f44336;
|
||||
color: white;
|
||||
}
|
||||
|
||||
.toast.warning {
|
||||
background-color: #ffd700;
|
||||
color: black;
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
|
||||
<body>
|
||||
<!-- Add toast element after body opening tag -->
|
||||
<div id="error-toast" class="toast"></div>
|
||||
<div class="container">
|
||||
<div class="logo">
|
||||
<h1>OpenAI Real-Time Chat</h1>
|
||||
</div>
|
||||
<div class="chat-container">
|
||||
<div class="chat-messages" id="chat-messages"></div>
|
||||
</div>
|
||||
<div class="controls">
|
||||
<button id="start-button">Start Conversation</button>
|
||||
</div>
|
||||
</div>
|
||||
<audio id="audio-output"></audio>
|
||||
|
||||
<script>
|
||||
let peerConnection;
|
||||
let webrtc_id;
|
||||
const audioOutput = document.getElementById('audio-output');
|
||||
const startButton = document.getElementById('start-button');
|
||||
const chatMessages = document.getElementById('chat-messages');
|
||||
|
||||
let audioLevel = 0;
|
||||
let animationFrame;
|
||||
let audioContext, analyser, audioSource;
|
||||
|
||||
function updateButtonState() {
|
||||
const button = document.getElementById('start-button');
|
||||
if (peerConnection && (peerConnection.connectionState === 'connecting' || peerConnection.connectionState === 'new')) {
|
||||
button.innerHTML = `
|
||||
<div class="icon-with-spinner">
|
||||
<div class="spinner"></div>
|
||||
<span>Connecting...</span>
|
||||
</div>
|
||||
`;
|
||||
} else if (peerConnection && peerConnection.connectionState === 'connected') {
|
||||
button.innerHTML = `
|
||||
<div class="pulse-container">
|
||||
<div class="pulse-circle"></div>
|
||||
<span>Stop Conversation</span>
|
||||
</div>
|
||||
`;
|
||||
} else {
|
||||
button.innerHTML = 'Start Conversation';
|
||||
}
|
||||
}
|
||||
|
||||
function setupAudioVisualization(stream) {
|
||||
audioContext = new (window.AudioContext || window.webkitAudioContext)();
|
||||
analyser = audioContext.createAnalyser();
|
||||
audioSource = audioContext.createMediaStreamSource(stream);
|
||||
audioSource.connect(analyser);
|
||||
analyser.fftSize = 64;
|
||||
const dataArray = new Uint8Array(analyser.frequencyBinCount);
|
||||
|
||||
function updateAudioLevel() {
|
||||
analyser.getByteFrequencyData(dataArray);
|
||||
const average = Array.from(dataArray).reduce((a, b) => a + b, 0) / dataArray.length;
|
||||
audioLevel = average / 255;
|
||||
|
||||
// Update CSS variable instead of rebuilding the button
|
||||
const pulseCircle = document.querySelector('.pulse-circle');
|
||||
if (pulseCircle) {
|
||||
pulseCircle.style.setProperty('--audio-level', 1 + audioLevel);
|
||||
}
|
||||
|
||||
animationFrame = requestAnimationFrame(updateAudioLevel);
|
||||
}
|
||||
updateAudioLevel();
|
||||
}
|
||||
|
||||
function showError(message) {
|
||||
const toast = document.getElementById('error-toast');
|
||||
toast.textContent = message;
|
||||
toast.style.display = 'block';
|
||||
|
||||
// Hide toast after 5 seconds
|
||||
setTimeout(() => {
|
||||
toast.style.display = 'none';
|
||||
}, 5000);
|
||||
}
|
||||
|
||||
async function setupWebRTC() {
|
||||
isConnecting = true;
|
||||
const config = __RTC_CONFIGURATION__;
|
||||
peerConnection = new RTCPeerConnection(config);
|
||||
|
||||
const timeoutId = setTimeout(() => {
|
||||
const toast = document.getElementById('error-toast');
|
||||
toast.textContent = "Connection is taking longer than usual. Are you on a VPN?";
|
||||
toast.className = 'toast warning';
|
||||
toast.style.display = 'block';
|
||||
|
||||
// Hide warning after 5 seconds
|
||||
setTimeout(() => {
|
||||
toast.style.display = 'none';
|
||||
}, 5000);
|
||||
}, 5000);
|
||||
|
||||
try {
|
||||
const stream = await navigator.mediaDevices.getUserMedia({
|
||||
audio: true
|
||||
});
|
||||
|
||||
setupAudioVisualization(stream);
|
||||
|
||||
stream.getTracks().forEach(track => {
|
||||
peerConnection.addTrack(track, stream);
|
||||
});
|
||||
|
||||
peerConnection.addEventListener('track', (evt) => {
|
||||
if (audioOutput.srcObject !== evt.streams[0]) {
|
||||
audioOutput.srcObject = evt.streams[0];
|
||||
audioOutput.play();
|
||||
}
|
||||
});
|
||||
|
||||
const dataChannel = peerConnection.createDataChannel('text');
|
||||
dataChannel.onmessage = (event) => {
|
||||
const eventJson = JSON.parse(event.data);
|
||||
if (eventJson.type === "error") {
|
||||
showError(eventJson.message);
|
||||
}
|
||||
};
|
||||
|
||||
const offer = await peerConnection.createOffer();
|
||||
await peerConnection.setLocalDescription(offer);
|
||||
|
||||
await new Promise((resolve) => {
|
||||
if (peerConnection.iceGatheringState === "complete") {
|
||||
resolve();
|
||||
} else {
|
||||
const checkState = () => {
|
||||
if (peerConnection.iceGatheringState === "complete") {
|
||||
peerConnection.removeEventListener("icegatheringstatechange", checkState);
|
||||
resolve();
|
||||
}
|
||||
};
|
||||
peerConnection.addEventListener("icegatheringstatechange", checkState);
|
||||
}
|
||||
});
|
||||
|
||||
peerConnection.addEventListener('connectionstatechange', () => {
|
||||
console.log('connectionstatechange', peerConnection.connectionState);
|
||||
if (peerConnection.connectionState === 'connected') {
|
||||
clearTimeout(timeoutId);
|
||||
const toast = document.getElementById('error-toast');
|
||||
toast.style.display = 'none';
|
||||
}
|
||||
updateButtonState();
|
||||
});
|
||||
|
||||
webrtc_id = Math.random().toString(36).substring(7);
|
||||
|
||||
const response = await fetch('/webrtc/offer', {
|
||||
method: 'POST',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify({
|
||||
sdp: peerConnection.localDescription.sdp,
|
||||
type: peerConnection.localDescription.type,
|
||||
webrtc_id: webrtc_id
|
||||
})
|
||||
});
|
||||
|
||||
const serverResponse = await response.json();
|
||||
|
||||
if (serverResponse.status === 'failed') {
|
||||
showError(serverResponse.meta.error === 'concurrency_limit_reached'
|
||||
? `Too many connections. Maximum limit is ${serverResponse.meta.limit}`
|
||||
: serverResponse.meta.error);
|
||||
stop();
|
||||
return;
|
||||
}
|
||||
|
||||
await peerConnection.setRemoteDescription(serverResponse);
|
||||
|
||||
const eventSource = new EventSource('/outputs?webrtc_id=' + webrtc_id);
|
||||
eventSource.addEventListener("output", (event) => {
|
||||
const eventJson = JSON.parse(event.data);
|
||||
addMessage("assistant", eventJson.content);
|
||||
|
||||
});
|
||||
} catch (err) {
|
||||
clearTimeout(timeoutId);
|
||||
console.error('Error setting up WebRTC:', err);
|
||||
showError('Failed to establish connection. Please try again.');
|
||||
stop();
|
||||
}
|
||||
}
|
||||
|
||||
function addMessage(role, content) {
|
||||
const messageDiv = document.createElement('div');
|
||||
messageDiv.classList.add('message', role);
|
||||
messageDiv.textContent = content;
|
||||
chatMessages.appendChild(messageDiv);
|
||||
chatMessages.scrollTop = chatMessages.scrollHeight;
|
||||
}
|
||||
|
||||
function stop() {
|
||||
if (animationFrame) {
|
||||
cancelAnimationFrame(animationFrame);
|
||||
}
|
||||
if (audioContext) {
|
||||
audioContext.close();
|
||||
audioContext = null;
|
||||
analyser = null;
|
||||
audioSource = null;
|
||||
}
|
||||
if (peerConnection) {
|
||||
if (peerConnection.getTransceivers) {
|
||||
peerConnection.getTransceivers().forEach(transceiver => {
|
||||
if (transceiver.stop) {
|
||||
transceiver.stop();
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
if (peerConnection.getSenders) {
|
||||
peerConnection.getSenders().forEach(sender => {
|
||||
if (sender.track && sender.track.stop) sender.track.stop();
|
||||
});
|
||||
}
|
||||
console.log('closing');
|
||||
peerConnection.close();
|
||||
}
|
||||
updateButtonState();
|
||||
audioLevel = 0;
|
||||
}
|
||||
|
||||
startButton.addEventListener('click', () => {
|
||||
console.log('clicked');
|
||||
console.log(peerConnection, peerConnection?.connectionState);
|
||||
if (!peerConnection || peerConnection.connectionState !== 'connected') {
|
||||
setupWebRTC();
|
||||
} else {
|
||||
console.log('stopping');
|
||||
stop();
|
||||
}
|
||||
});
|
||||
</script>
|
||||
</body>
|
||||
|
||||
</html>
|
||||
4
demo/talk_to_openai/requirements.txt
Normal file
4
demo/talk_to_openai/requirements.txt
Normal file
@@ -0,0 +1,4 @@
|
||||
fastrtc[vad]
|
||||
openai
|
||||
twilio
|
||||
python-dotenv
|
||||
Reference in New Issue
Block a user