wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'main' of github.com:pipecat-ai/pipecat

Browse Source
This commit is contained in:
Matej Marinko
2025-07-08 08:20:10 +02:00
parent c54084b7a4 a6de16f92f
commit 0f727248d2
482 changed files with 32975 additions and 7233 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples/bot-ready-signalling/client/react-native/package-lock.json generated
View File

@@ -4364,9 +4364,9 @@
}
},
"node_modules/brace-expansion": {
"version": "1.1.11",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
"integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==",
"version": "1.1.12",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
"integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
"dependencies": {
"balanced-match": "^1.0.0",
"concat-map": "0.0.1"
@@ -6081,9 +6081,9 @@
}
},
"node_modules/glob/node_modules/brace-expansion": {
"version": "2.0.1",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
"integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
"version": "2.0.2",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
"integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
"dependencies": {
"balanced-match": "^1.0.0"
}

3
examples/chatbot-audio-recording/bot.py
View File

@@ -133,7 +133,8 @@ async def main():
params=PipelineParams(
audio_in_sample_rate=16000,
audio_out_sample_rate=16000,
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)

2
examples/daily-custom-tracks/bot.py
View File

@@ -71,6 +71,8 @@ async def main():
params=PipelineParams(
audio_in_sample_rate=16000,
audio_out_sample_rate=16000,
enable_metrics=True,
enable_usage_metrics=True,
),
)

2
examples/daily-multi-translation/bot.py
View File

@@ -148,10 +148,8 @@ async def main():
params=PipelineParams(
audio_in_sample_rate=16000,
audio_out_sample_rate=16000,
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
observers=[TranscriptionLogObserver()],
)

2
examples/daily-multi-translation/requirements.txt
View File

@@ -2,4 +2,4 @@ aiofiles
python-dotenv
fastapi[all]
uvicorn
pipecat-ai[daily,deepgram,openai,silero,cartesia]
pipecat-ai[daily,deepgram,openai,silero,cartesia,soundfile]

8
examples/deployment/flyio-example/bot.py
View File

@@ -75,7 +75,13 @@ async def main(room_url: str, token: str):
]
)
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):

533
examples/deployment/modal-example/client/javascript/package-lock.json generated
View File

File diff suppressed because it is too large Load Diff

4
examples/deployment/modal-example/client/javascript/package.json
View File

@@ -15,7 +15,7 @@
"vite": "^6.3.5"
},
"dependencies": {
"@pipecat-ai/client-js": "^0.3.5",
"@pipecat-ai/daily-transport": "^0.3.10"
"@pipecat-ai/client-js": "^1.0.0",
"@pipecat-ai/daily-transport": "^1.0.0"
}
}

69
examples/deployment/modal-example/client/javascript/src/app.js
View File

@@ -5,7 +5,7 @@
*/
/**
* RTVI Client Implementation
* Pipecat 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.
@@ -16,7 +16,7 @@
* - Browser with WebRTC support
*/
import { RTVIClient, RTVIEvent } from '@pipecat-ai/client-js';
import { PipecatClient, RTVIEvent } from '@pipecat-ai/client-js';
import { DailyTransport } from '@pipecat-ai/daily-transport';
/**
@@ -26,7 +26,7 @@ import { DailyTransport } from '@pipecat-ai/daily-transport';
class ChatbotClient {
constructor() {
// Initialize client state
this.rtviClient = null;
this.pcClient = null;
this.setupDOMElements();
this.initializeClientAndTransport();
this.setupEventListeners();
@@ -59,7 +59,7 @@ class ChatbotClient {
this.disconnectBtn.addEventListener('click', () => this.disconnect());
// Populate device selector
this.rtviClient.getAllMics().then((mics) => {
this.pcClient.getAllMics().then((mics) => {
console.log('Available mics:', mics);
mics.forEach((device) => {
const option = document.createElement('option');
@@ -71,16 +71,16 @@ class ChatbotClient {
this.deviceSelector.addEventListener('change', (event) => {
const selectedDeviceId = event.target.value;
console.log('Selected device ID:', selectedDeviceId);
this.rtviClient.updateMic(selectedDeviceId);
this.pcClient.updateMic(selectedDeviceId);
});
// Handle mic mute/unmute toggle
const micToggleBtn = document.getElementById('mic-toggle-btn');
micToggleBtn.addEventListener('click', () => {
let micEnabled = this.rtviClient.isMicEnabled;
let micEnabled = this.pcClient.isMicEnabled;
micToggleBtn.textContent = micEnabled ? 'Unmute Mic' : 'Mute Mic';
this.rtviClient.enableMic(!micEnabled);
this.pcClient.enableMic(!micEnabled);
// Add logic to mute/unmute the mic
if (micEnabled) {
console.log('Mic muted');
@@ -93,23 +93,12 @@ class ChatbotClient {
}
/**
* Set up the RTVI client and Daily transport
* Set up the Pipecat client and Daily transport
*/
async initializeClientAndTransport() {
// Initialize the RTVI client with a DailyTransport and our configuration
this.rtviClient = new RTVIClient({
// Initialize the Pipecat client with a DailyTransport and our configuration
this.pcClient = new PipecatClient({
transport: new DailyTransport(),
params: {
// REPLACE WITH YOUR MODAL URL ENDPOINT
baseUrl:
'https://<Modal workspace>--pipecat-modal-bot-launcher.modal.run',
endpoints: {
connect: '/connect',
},
requestData: {
bot_name: 'openai',
},
},
enableMic: true, // Enable microphone for user input
enableCam: false,
callbacks: {
@@ -176,8 +165,8 @@ class ChatbotClient {
// Set up listeners for media track events
this.setupTrackListeners();
await this.rtviClient.initDevices();
window.client = this.rtviClient;
await this.pcClient.initDevices();
window.client = this.pcClient;
}
/**
@@ -212,10 +201,10 @@ class ChatbotClient {
* This is called when the bot is ready or when the transport state changes to ready
*/
setupMediaTracks() {
if (!this.rtviClient) return;
if (!this.pcClient) return;
// Get current tracks from the client
const tracks = this.rtviClient.tracks();
const tracks = this.pcClient.tracks();
// Set up any available bot tracks
if (tracks.bot?.audio) {
@@ -231,10 +220,10 @@ class ChatbotClient {
* This handles new tracks being added during the session
*/
setupTrackListeners() {
if (!this.rtviClient) return;
if (!this.pcClient) return;
// Listen for new tracks starting
this.rtviClient.on(RTVIEvent.TrackStarted, (track, participant) => {
this.pcClient.on(RTVIEvent.TrackStarted, (track, participant) => {
// Only handle non-local (bot) tracks
if (!participant?.local) {
if (track.kind === 'audio') {
@@ -253,7 +242,7 @@ class ChatbotClient {
});
// Listen for tracks stopping
this.rtviClient.on(RTVIEvent.TrackStopped, (track, participant) => {
this.pcClient.on(RTVIEvent.TrackStopped, (track, participant) => {
if (participant.local) {
this.log('Local mic muted');
return;
@@ -311,21 +300,27 @@ class ChatbotClient {
/**
* Initialize and connect to the bot
* This sets up the RTVI client, initializes devices, and establishes the connection
* This sets up the Pipecat client, initializes devices, and establishes the connection
*/
async connect() {
try {
const botSelector = document.getElementById('bot-selector');
const selectedBot = botSelector.value;
this.rtviClient.params.requestData.bot_name = selectedBot;
// Initialize audio/video devices
this.log('Initializing devices...');
await this.rtviClient.initDevices();
await this.pcClient.initDevices();
// Connect to the bot
this.log(`Connecting to bot: ${selectedBot}`);
await this.rtviClient.connect();
await this.pcClient.connect({
// REPLACE WITH YOUR MODAL URL ENDPOINT
endpoint:
'https://<your-workspace>--pipecat-modal-fastapi-app.modal.run/connect',
requestData: {
bot_name: selectedBot,
},
});
this.log('Connection complete');
} catch (error) {
@@ -336,9 +331,9 @@ class ChatbotClient {
this.updateStatus('Error');
// Clean up if there's an error
if (this.rtviClient) {
if (this.pcClient) {
try {
await this.rtviClient.disconnect();
await this.pcClient.disconnect();
} catch (disconnectError) {
this.log(`Error during disconnect: ${disconnectError.message}`);
}
@@ -350,10 +345,10 @@ class ChatbotClient {
* Disconnect from the bot and clean up media resources
*/
async disconnect() {
if (this.rtviClient) {
if (this.pcClient) {
try {
// Disconnect the RTVI client
await this.rtviClient.disconnect();
// Disconnect the Pipecat client
await this.pcClient.disconnect();
// Clean up audio
if (this.botAudio.srcObject) {

3
examples/deployment/modal-example/server/requirements.txt
View File

@@ -1,2 +1,3 @@
python-dotenv==1.0.1
modal==0.71.3
modal==1.0.5
fastapi[all]

1
examples/deployment/modal-example/server/src/bot_gemini.py
View File

@@ -170,7 +170,6 @@ async def run_bot(room_url: str, token: str):
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

1
examples/deployment/modal-example/server/src/bot_openai.py
View File

@@ -198,7 +198,6 @@ async def run_bot(room_url: str, token: str):
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

1
examples/deployment/modal-example/server/src/bot_vllm.py
View File

@@ -211,7 +211,6 @@ async def run_bot(room_url: str, token: str):
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

118
examples/deployment/pipecat-cloud-daily-pstn-server/nextjs-webhook-server/package-lock.json generated
View File

@@ -215,10 +215,9 @@
}
},
"node_modules/@next/env": {
"version": "14.2.26",
"resolved": "https://registry.npmjs.org/@next/env/-/env-14.2.26.tgz",
"integrity": "sha512-vO//GJ/YBco+H7xdQhzJxF7ub3SUwft76jwaeOyVVQFHCi5DCnkP16WHB+JBylo4vOKPoZBlR94Z8xBxNBdNJA==",
"license": "MIT"
"version": "14.2.30",
"resolved": "https://registry.npmjs.org/@next/env/-/env-14.2.30.tgz",
"integrity": "sha512-KBiBKrDY6kxTQWGzKjQB7QirL3PiiOkV7KW98leHFjtVRKtft76Ra5qSA/SL75xT44dp6hOcqiiJ6iievLOYug=="
},
"node_modules/@next/eslint-plugin-next": {
"version": "14.2.25",
@@ -231,13 +230,12 @@
}
},
"node_modules/@next/swc-darwin-arm64": {
"version": "14.2.26",
"resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-14.2.26.tgz",
"integrity": "sha512-zDJY8gsKEseGAxG+C2hTMT0w9Nk9N1Sk1qV7vXYz9MEiyRoF5ogQX2+vplyUMIfygnjn9/A04I6yrUTRTuRiyQ==",
"version": "14.2.30",
"resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-14.2.30.tgz",
"integrity": "sha512-EAqfOTb3bTGh9+ewpO/jC59uACadRHM6TSA9DdxJB/6gxOpyV+zrbqeXiFTDy9uV6bmipFDkfpAskeaDcO+7/g==",
"cpu": [
"arm64"
],
"license": "MIT",
"optional": true,
"os": [
"darwin"
@@ -247,13 +245,12 @@
}
},
"node_modules/@next/swc-darwin-x64": {
"version": "14.2.26",
"resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-14.2.26.tgz",
"integrity": "sha512-U0adH5ryLfmTDkahLwG9sUQG2L0a9rYux8crQeC92rPhi3jGQEY47nByQHrVrt3prZigadwj/2HZ1LUUimuSbg==",
"version": "14.2.30",
"resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-14.2.30.tgz",
"integrity": "sha512-TyO7Wz1IKE2kGv8dwQ0bmPL3s44EKVencOqwIY69myoS3rdpO1NPg5xPM5ymKu7nfX4oYJrpMxv8G9iqLsnL4A==",
"cpu": [
"x64"
],
"license": "MIT",
"optional": true,
"os": [
"darwin"
@@ -263,13 +260,12 @@
}
},
"node_modules/@next/swc-linux-arm64-gnu": {
"version": "14.2.26",
"resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-14.2.26.tgz",
"integrity": "sha512-SINMl1I7UhfHGM7SoRiw0AbwnLEMUnJ/3XXVmhyptzriHbWvPPbbm0OEVG24uUKhuS1t0nvN/DBvm5kz6ZIqpg==",
"version": "14.2.30",
"resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-14.2.30.tgz",
"integrity": "sha512-I5lg1fgPJ7I5dk6mr3qCH1hJYKJu1FsfKSiTKoYwcuUf53HWTrEkwmMI0t5ojFKeA6Vu+SfT2zVy5NS0QLXV4Q==",
"cpu": [
"arm64"
],
"license": "MIT",
"optional": true,
"os": [
"linux"
@@ -279,13 +275,12 @@
}
},
"node_modules/@next/swc-linux-arm64-musl": {
"version": "14.2.26",
"resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-14.2.26.tgz",
"integrity": "sha512-s6JaezoyJK2DxrwHWxLWtJKlqKqTdi/zaYigDXUJ/gmx/72CrzdVZfMvUc6VqnZ7YEvRijvYo+0o4Z9DencduA==",
"version": "14.2.30",
"resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-14.2.30.tgz",
"integrity": "sha512-8GkNA+sLclQyxgzCDs2/2GSwBc92QLMrmYAmoP2xehe5MUKBLB2cgo34Yu242L1siSkwQkiV4YLdCnjwc/Micw==",
"cpu": [
"arm64"
],
"license": "MIT",
"optional": true,
"os": [
"linux"
@@ -295,13 +290,12 @@
}
},
"node_modules/@next/swc-linux-x64-gnu": {
"version": "14.2.26",
"resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-14.2.26.tgz",
"integrity": "sha512-FEXeUQi8/pLr/XI0hKbe0tgbLmHFRhgXOUiPScz2hk0hSmbGiU8aUqVslj/6C6KA38RzXnWoJXo4FMo6aBxjzg==",
"version": "14.2.30",
"resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-14.2.30.tgz",
"integrity": "sha512-8Ly7okjssLuBoe8qaRCcjGtcMsv79hwzn/63wNeIkzJVFVX06h5S737XNr7DZwlsbTBDOyI6qbL2BJB5n6TV/w==",
"cpu": [
"x64"
],
"license": "MIT",
"optional": true,
"os": [
"linux"
@@ -311,13 +305,12 @@
}
},
"node_modules/@next/swc-linux-x64-musl": {
"version": "14.2.26",
"resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-14.2.26.tgz",
"integrity": "sha512-BUsomaO4d2DuXhXhgQCVt2jjX4B4/Thts8nDoIruEJkhE5ifeQFtvW5c9JkdOtYvE5p2G0hcwQ0UbRaQmQwaVg==",
"version": "14.2.30",
"resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-14.2.30.tgz",
"integrity": "sha512-dBmV1lLNeX4mR7uI7KNVHsGQU+OgTG5RGFPi3tBJpsKPvOPtg9poyav/BYWrB3GPQL4dW5YGGgalwZ79WukbKQ==",
"cpu": [
"x64"
],
"license": "MIT",
"optional": true,
"os": [
"linux"
@@ -327,13 +320,12 @@
}
},
"node_modules/@next/swc-win32-arm64-msvc": {
"version": "14.2.26",
"resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-14.2.26.tgz",
"integrity": "sha512-5auwsMVzT7wbB2CZXQxDctpWbdEnEW/e66DyXO1DcgHxIyhP06awu+rHKshZE+lPLIGiwtjo7bsyeuubewwxMw==",
"version": "14.2.30",
"resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-14.2.30.tgz",
"integrity": "sha512-6MMHi2Qc1Gkq+4YLXAgbYslE1f9zMGBikKMdmQRHXjkGPot1JY3n5/Qrbg40Uvbi8//wYnydPnyvNhI1DMUW1g==",
"cpu": [
"arm64"
],
"license": "MIT",
"optional": true,
"os": [
"win32"
@@ -343,13 +335,12 @@
}
},
"node_modules/@next/swc-win32-ia32-msvc": {
"version": "14.2.26",
"resolved": "https://registry.npmjs.org/@next/swc-win32-ia32-msvc/-/swc-win32-ia32-msvc-14.2.26.tgz",
"integrity": "sha512-GQWg/Vbz9zUGi9X80lOeGsz1rMH/MtFO/XqigDznhhhTfDlDoynCM6982mPCbSlxJ/aveZcKtTlwfAjwhyxDpg==",
"version": "14.2.30",
"resolved": "https://registry.npmjs.org/@next/swc-win32-ia32-msvc/-/swc-win32-ia32-msvc-14.2.30.tgz",
"integrity": "sha512-pVZMnFok5qEX4RT59mK2hEVtJX+XFfak+/rjHpyFh7juiT52r177bfFKhnlafm0UOSldhXjj32b+LZIOdswGTg==",
"cpu": [
"ia32"
],
"license": "MIT",
"optional": true,
"os": [
"win32"
@@ -359,13 +350,12 @@
}
},
"node_modules/@next/swc-win32-x64-msvc": {
"version": "14.2.26",
"resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-14.2.26.tgz",
"integrity": "sha512-2rdB3T1/Gp7bv1eQTTm9d1Y1sv9UuJ2LAwOE0Pe2prHKe32UNscj7YS13fRB37d0GAiGNR+Y7ZcW8YjDI8Ns0w==",
"version": "14.2.30",
"resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-14.2.30.tgz",
"integrity": "sha512-4KCo8hMZXMjpTzs3HOqOGYYwAXymXIy7PEPAXNEcEOyKqkjiDlECumrWziy+JEF0Oi4ILHGxzgQ3YiMGG2t/Lg==",
"cpu": [
"x64"
],
"license": "MIT",
"optional": true,
"os": [
"win32"
@@ -620,11 +610,10 @@
}
},
"node_modules/@typescript-eslint/typescript-estree/node_modules/brace-expansion": {
"version": "2.0.1",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
"integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
"version": "2.0.2",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
"integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
"dev": true,
"license": "MIT",
"dependencies": {
"balanced-match": "^1.0.0"
}
@@ -1224,11 +1213,10 @@
"license": "MIT"
},
"node_modules/brace-expansion": {
"version": "1.1.11",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
"integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==",
"version": "1.1.12",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
"integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
"dev": true,
"license": "MIT",
"dependencies": {
"balanced-match": "^1.0.0",
"concat-map": "0.0.1"
@@ -2614,11 +2602,10 @@
}
},
"node_modules/glob/node_modules/brace-expansion": {
"version": "2.0.1",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
"integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
"version": "2.0.2",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
"integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
"dev": true,
"license": "MIT",
"dependencies": {
"balanced-match": "^1.0.0"
}
@@ -3613,12 +3600,11 @@
"license": "MIT"
},
"node_modules/next": {
"version": "14.2.26",
"resolved": "https://registry.npmjs.org/next/-/next-14.2.26.tgz",
"integrity": "sha512-b81XSLihMwCfwiUVRRja3LphLo4uBBMZEzBBWMaISbKTwOmq3wPknIETy/8000tr7Gq4WmbuFYPS7jOYIf+ZJw==",
"license": "MIT",
"version": "14.2.30",
"resolved": "https://registry.npmjs.org/next/-/next-14.2.30.tgz",
"integrity": "sha512-+COdu6HQrHHFQ1S/8BBsCag61jZacmvbuL2avHvQFbWa2Ox7bE+d8FyNgxRLjXQ5wtPyQwEmk85js/AuaG2Sbg==",
"dependencies": {
"@next/env": "14.2.26",
"@next/env": "14.2.30",
"@swc/helpers": "0.5.5",
"busboy": "1.6.0",
"caniuse-lite": "^1.0.30001579",
@@ -3633,15 +3619,15 @@
"node": ">=18.17.0"
},
"optionalDependencies": {
"@next/swc-darwin-arm64": "14.2.26",
"@next/swc-darwin-x64": "14.2.26",
"@next/swc-linux-arm64-gnu": "14.2.26",
"@next/swc-linux-arm64-musl": "14.2.26",
"@next/swc-linux-x64-gnu": "14.2.26",
"@next/swc-linux-x64-musl": "14.2.26",
"@next/swc-win32-arm64-msvc": "14.2.26",
"@next/swc-win32-ia32-msvc": "14.2.26",
"@next/swc-win32-x64-msvc": "14.2.26"
"@next/swc-darwin-arm64": "14.2.30",
"@next/swc-darwin-x64": "14.2.30",
"@next/swc-linux-arm64-gnu": "14.2.30",
"@next/swc-linux-arm64-musl": "14.2.30",
"@next/swc-linux-x64-gnu": "14.2.30",
"@next/swc-linux-x64-musl": "14.2.30",
"@next/swc-win32-arm64-msvc": "14.2.30",
"@next/swc-win32-ia32-msvc": "14.2.30",
"@next/swc-win32-x64-msvc": "14.2.30"
},
"peerDependencies": {
"@opentelemetry/api": "^1.1.0",

2
examples/deployment/pipecat-cloud-example/bot.py
View File

@@ -67,10 +67,8 @@ async def main(transport: DailyTransport):
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/fal-smart-turn/README.md
View File

@@ -44,7 +44,7 @@ Try the hosted version of the demo here: https://pcc-smart-turn.vercel.app/.
4. Run the server:
```bash
LOCAL=1 python server.py
LOCAL_RUN=1 python server.py
```
### Run the client

1289
examples/fal-smart-turn/client/package-lock.json generated
View File

File diff suppressed because it is too large Load Diff

6
examples/fal-smart-turn/client/package.json
View File

@@ -9,9 +9,9 @@
"lint": "next lint"
},
"dependencies": {
"@pipecat-ai/client-js": "^0.3.5",
"@pipecat-ai/client-react": "^0.3.5",
"@pipecat-ai/daily-transport": "^0.3.10",
"@pipecat-ai/client-js": "^1.0.0",
"@pipecat-ai/client-react": "^1.0.0",
"@pipecat-ai/daily-transport": "^1.0.0",
"next": "15.3.1",
"react": "^19.0.0",
"react-dom": "^19.0.0"

4
examples/fal-smart-turn/client/src/app/layout.tsx
View File

@@ -1,5 +1,5 @@
import './globals.css';
import { RTVIProvider } from '@/providers/RTVIProvider';
import { PipecatProvider } from '@/providers/PipecatProvider';
export const metadata = {
title: 'Pipecat React Client',
@@ -20,7 +20,7 @@ export default function RootLayout({
<link rel="icon" href="/favicon.svg" type="image/svg+xml" />
</head>
<body>
<RTVIProvider>{children}</RTVIProvider>
<PipecatProvider>{children}</PipecatProvider>
</body>
</html>
);

12
examples/fal-smart-turn/client/src/app/page.tsx
View File

@@ -1,22 +1,22 @@
'use client';
import {
RTVIClientAudio,
RTVIClientVideo,
useRTVIClientTransportState,
PipecatClientAudio,
PipecatClientVideo,
usePipecatClientTransportState,
} from '@pipecat-ai/client-react';
import { ConnectButton } from '../components/ConnectButton';
import { StatusDisplay } from '../components/StatusDisplay';
import { DebugDisplay } from '../components/DebugDisplay';
function BotVideo() {
const transportState = useRTVIClientTransportState();
const transportState = usePipecatClientTransportState();
const isConnected = transportState !== 'disconnected';
return (
<div className="bot-container">
<div className="video-container">
{isConnected && <RTVIClientVideo participant="bot" fit="cover" />}
{isConnected && <PipecatClientVideo participant="bot" fit="cover" />}
</div>
</div>
);
@@ -35,7 +35,7 @@ export default function Home() {
</div>
<DebugDisplay />
<RTVIClientAudio />
<PipecatClientAudio />
</div>
);
}

19
examples/fal-smart-turn/client/src/components/ConnectButton.tsx
View File

@@ -1,11 +1,17 @@
import {
useRTVIClient,
useRTVIClientTransportState,
usePipecatClient,
usePipecatClientTransportState,
} from '@pipecat-ai/client-react';
// Get the API base URL from environment variables
// Default to "/api" if not specified
// "/api" is the default for Next.js API routes and used
// for the Pipecat Cloud deployed agent
const API_BASE_URL = process.env.NEXT_PUBLIC_API_BASE_URL || '/api';
export function ConnectButton() {
const client = useRTVIClient();
const transportState = useRTVIClientTransportState();
const client = usePipecatClient();
const transportState = usePipecatClientTransportState();
const isConnected = ['connected', 'ready'].includes(transportState);
const handleClick = async () => {
@@ -18,7 +24,10 @@ export function ConnectButton() {
if (isConnected) {
await client.disconnect();
} else {
await client.connect();
await client.connect({
endpoint: `${API_BASE_URL}/connect`,
requestData: { foo: 'bar' },
});
}
} catch (error) {
console.error('Connection error:', error);

4
examples/fal-smart-turn/client/src/components/DebugDisplay.tsx
View File

@@ -6,7 +6,7 @@ import {
TranscriptData,
BotLLMTextData,
} from '@pipecat-ai/client-js';
import { useRTVIClient, useRTVIClientEvent } from '@pipecat-ai/client-react';
import { usePipecatClient, useRTVIClientEvent } from '@pipecat-ai/client-react';
import './DebugDisplay.css';
interface SmartTurnResultData {
@@ -20,7 +20,7 @@ interface SmartTurnResultData {
export function DebugDisplay() {
const debugLogRef = useRef<HTMLDivElement>(null);
const client = useRTVIClient();
const client = usePipecatClient();
const log = useCallback((message: string) => {
if (!debugLogRef.current) return;

4
examples/fal-smart-turn/client/src/components/StatusDisplay.tsx
View File

@@ -1,7 +1,7 @@
import { useRTVIClientTransportState } from '@pipecat-ai/client-react';
import { usePipecatClientTransportState } from '@pipecat-ai/client-react';
export function StatusDisplay() {
const transportState = useRTVIClientTransportState();
const transportState = usePipecatClientTransportState();
return (
<div className="status">

28
examples/fal-smart-turn/client/src/providers/PipecatProvider.tsx Normal file
View File

@@ -0,0 +1,28 @@
'use client';
import { PipecatClient } from '@pipecat-ai/client-js';
import { DailyTransport } from '@pipecat-ai/daily-transport';
import { PipecatClientProvider } from '@pipecat-ai/client-react';
import { PropsWithChildren, useEffect, useState } from 'react';
export function PipecatProvider({ children }: PropsWithChildren) {
const [client, setClient] = useState<PipecatClient | null>(null);
useEffect(() => {
const pcClient = new PipecatClient({
transport: new DailyTransport(),
enableMic: true,
enableCam: false,
});
setClient(pcClient);
}, []);
if (!client) {
return null;
}
return (
<PipecatClientProvider client={client}>{children}</PipecatClientProvider>
);
}

43
examples/fal-smart-turn/client/src/providers/RTVIProvider.tsx
View File

@@ -1,43 +0,0 @@
'use client';
import { RTVIClient } from '@pipecat-ai/client-js';
import { DailyTransport } from '@pipecat-ai/daily-transport';
import { RTVIClientProvider } from '@pipecat-ai/client-react';
import { PropsWithChildren, useEffect, useState } from 'react';
// Get the API base URL from environment variables
// Default to "/api" if not specified
// "/api" is the default for Next.js API routes and used
// for the Pipecat Cloud deployed agent
const API_BASE_URL = process.env.NEXT_PUBLIC_API_BASE_URL || '/api';
console.log('Using API base URL:', API_BASE_URL);
export function RTVIProvider({ children }: PropsWithChildren) {
const [client, setClient] = useState<RTVIClient | null>(null);
useEffect(() => {
const transport = new DailyTransport();
const rtviClient = new RTVIClient({
transport,
params: {
baseUrl: API_BASE_URL,
endpoints: {
connect: '/connect',
},
requestData: { foo: 'bar' },
},
enableMic: true,
enableCam: false,
});
setClient(rtviClient);
}, []);
if (!client) {
return null;
}
return <RTVIClientProvider client={client}>{children}</RTVIClientProvider>;
}

3
examples/fal-smart-turn/server/bot.py
View File

@@ -45,7 +45,7 @@ from pipecat.transports.services.daily import DailyParams, DailyTransport
load_dotenv(override=True)
# Check if we're in local development mode
LOCAL = os.getenv("LOCAL")
LOCAL = os.getenv("LOCAL_RUN")
logger.remove()
logger.add(sys.stderr, level="DEBUG")
@@ -192,7 +192,6 @@ async def main(transport: DailyTransport):
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

5
examples/foundational/03b-still-frame-imagen.py
View File

@@ -47,7 +47,10 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
Pipeline([imagegen, transport.output()]),
params=PipelineParams(enable_metrics=True),
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
# Register an event handler so we can play the audio when the client joins

2
examples/foundational/04-transports-small-webrtc.py
View File

@@ -93,10 +93,8 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/04a-transports-daily.py
View File

@@ -75,10 +75,8 @@ async def main():
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

3
examples/foundational/04b-transports-livekit.py
View File

@@ -158,7 +158,8 @@ async def main():
],
),
params=PipelineParams(
allow_interruptions=True, enable_metrics=True, enable_usage_metrics=True
enable_metrics=True,
enable_usage_metrics=True,
),
)

2
examples/foundational/06a-image-sync.py
View File

@@ -133,10 +133,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07-interruptible-cartesia-http.py
View File

@@ -84,10 +84,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07-interruptible.py
View File

@@ -83,10 +83,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

153
examples/foundational/07a-interruptible-speechmatics.py Normal file
View File

@@ -0,0 +1,153 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_response import (
LLMUserAggregatorParams,
)
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
from pipecat.services.openai.base_llm import BaseOpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
"""Run example using Speechmatics STT.
This example will use diarization within our STT service and output the words spoken by
each individual speaker and wrap them with XML tags for the LLM to process. Note the
instructions in the system context for the LLM. This greatly improves the conversation
experience by allowing the LLM to understand who is speaking in a multi-party call.
If you do not wish to use diarization, then set the `enable_speaker_diarization` parameter
to `False` or omit it altogether. The `text_format` will only be used if diarization is enabled.
By default, this example will use our ENHANCED operating point, which is optimized for
high accuracy. You can change this by setting the `operating_point` parameter to a different
value.
For more information on operating points, see the Speechmatics documentation:
https://docs.speechmatics.com/rt-api-ref
"""
logger.info(f"Starting bot")
stt = SpeechmaticsSTTService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
language=Language.EN,
enable_speaker_diarization=True,
text_format="<{speaker_id}>{text}</{speaker_id}>",
)
tts = ElevenLabsTTSService(
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
model="eleven_turbo_v2_5",
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
params=BaseOpenAILLMService.InputParams(temperature=0.75),
)
messages = [
{
"role": "system",
"content": (
"You are a helpful British assistant called Alfred. "
"Your goal is to demonstrate your capabilities in a succinct way. "
"Your output will be converted to audio so don't include special characters in your answers. "
"Always include punctuation in your responses. "
"Give very short replies - do not give longer replies unless strictly necessary. "
"Respond to what the user said in a concise, funny, creative and helpful way. "
"Use `<Sn/>` tags to identify different speakers - do not use tags in your replies."
),
},
]
context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(
context,
user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
)
pipeline = Pipeline(
[
transport.input(), # Transport user input
stt, # STT
context_aggregator.user(), # User responses
llm, # LLM
tts, # TTS
transport.output(), # Transport bot output
context_aggregator.assistant(), # Assistant spoken responses
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
messages.append({"role": "system", "content": "Say a short hello to the user."})
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=handle_sigint)
await runner.run(task)
if __name__ == "__main__":
from pipecat.examples.run import main
main(run_example, transport_params=transport_params)

2
examples/foundational/07b-interruptible-langchain.py
View File

@@ -113,10 +113,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07c-interruptible-deepgram-vad.py
View File

@@ -87,10 +87,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07c-interruptible-deepgram.py
View File

@@ -81,10 +81,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

4
examples/foundational/07d-interruptible-elevenlabs-http.py
View File

@@ -35,7 +35,7 @@ transport_params = {
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"twilio": lambda: TransportParams(
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
@@ -88,10 +88,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07d-interruptible-elevenlabs.py
View File

@@ -84,10 +84,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07e-interruptible-playht-http.py
View File

@@ -84,10 +84,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07e-interruptible-playht.py
View File

@@ -86,10 +86,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07f-interruptible-azure.py
View File

@@ -90,10 +90,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07g-interruptible-openai.py
View File

@@ -84,11 +84,9 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
audio_out_sample_rate=24000,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07h-interruptible-openpipe.py
View File

@@ -89,10 +89,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07i-interruptible-xtts.py
View File

@@ -87,10 +87,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07j-interruptible-gladia.py
View File

@@ -92,10 +92,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07k-interruptible-lmnt.py
View File

@@ -80,10 +80,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

1
examples/foundational/07l-interruptible-groq.py
View File

@@ -85,7 +85,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

2
examples/foundational/07m-interruptible-aws.py
View File

@@ -87,10 +87,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

9
examples/foundational/07n-interruptible-google.py
View File

@@ -61,7 +61,12 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
)
llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
model="gemini-2.5-flash",
# turn on thinking if you want it
# params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),)
)
messages = [
{
@@ -88,10 +93,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07o-interruptible-assemblyai.py
View File

@@ -86,10 +86,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07p-interruptible-krisp.py
View File

@@ -84,10 +84,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07q-interruptible-rime-http.py
View File

@@ -89,10 +89,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07q-interruptible-rime.py
View File

@@ -83,10 +83,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07r-interruptible-riva-nim.py
View File

@@ -80,10 +80,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

14
examples/foundational/07s-interruptible-google-audio-in.py
View File

@@ -8,8 +8,8 @@ import argparse
import os
from dataclasses import dataclass
import google.ai.generativelanguage as glm
from dotenv import load_dotenv
from google.genai.types import Content, Part
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
@@ -164,9 +164,7 @@ class TanscriptionContextFixup(FrameProcessor):
and last_part.inline_data
and last_part.inline_data.mime_type == "audio/wav"
):
self._context.messages[-2] = glm.Content(
role="user", parts=[glm.Part(text=self._transcript)]
)
self._context.messages[-2] = Content(role="user", parts=[Part(text=self._transcript)])
def add_transcript_back_to_inference_output(self):
if not self._transcript:
@@ -216,7 +214,12 @@ transport_params = {
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
logger.info(f"Starting bot")
llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
model="gemini-2.5-flash",
# turn on thinking if you want it
# params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),
)
tts = GoogleTTSService(
voice_id="en-US-Chirp3-HD-Charon",
@@ -258,7 +261,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

2
examples/foundational/07t-interruptible-fish.py
View File

@@ -84,10 +84,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07u-interruptible-ultravox.py
View File

@@ -77,8 +77,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)

2
examples/foundational/07v-interruptible-neuphonic-http.py
View File

@@ -84,10 +84,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07v-interruptible-neuphonic.py
View File

@@ -83,10 +83,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07w-interruptible-fal.py
View File

@@ -86,10 +86,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07x-interruptible-local.py
View File

@@ -70,10 +70,8 @@ async def main():
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07y-interruptible-minimax.py
View File

@@ -90,10 +90,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/07z-interruptible-sarvam.py
View File

@@ -89,10 +89,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

8
examples/foundational/10-wake-phrase.py
View File

@@ -85,7 +85,13 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
]
)
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

5
examples/foundational/12a-describe-video-gemini-flash.py
View File

@@ -101,7 +101,10 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(allow_interruptions=True),
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")

5
examples/foundational/12b-describe-video-gpt-4o.py
View File

@@ -101,7 +101,10 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(allow_interruptions=True),
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")

5
examples/foundational/12c-describe-video-anthropic.py
View File

@@ -101,7 +101,10 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(allow_interruptions=True),
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")

2
examples/foundational/13e-whisper-mlx.py
View File

@@ -84,7 +84,7 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
pipeline,
params=PipelineParams(
enable_metrics=True,
report_only_initial_ttfb=False,
enable_usage_metrics=True,
),
)

108
examples/foundational/13g-sambanova-transcription.py Normal file
View File

@@ -0,0 +1,108 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
import time
from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.audio.vad.vad_analyzer import VADParams
from pipecat.frames.frames import Frame, TranscriptionFrame, UserStoppedSpeakingFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.sambanova.stt import SambaNovaSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
STOP_SECS = 2.0
class TranscriptionLogger(FrameProcessor):
"""Measures transcription latency.
Uses the (intentionally) long STOP_SECS parameter to give the transcription time to finish,
then outputs the timing between when the VAD first classified audio input as not-speech and
the delivery of the last transcription frame.
"""
def __init__(self):
super().__init__()
self._last_transcription_time = time.time()
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
if isinstance(frame, UserStoppedSpeakingFrame):
logger.debug(
f"Transcription latency: {(STOP_SECS - (time.time() - self._last_transcription_time)):.2f}"
)
if isinstance(frame, TranscriptionFrame):
self._last_transcription_time = time.time()
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
logger.info(f"Starting bot")
stt = SambaNovaSTTService(
model="Whisper-Large-v3",
api_key=os.getenv("SAMBANOVA_API_KEY"),
)
tl = TranscriptionLogger()
pipeline = Pipeline([transport.input(), stt, tl])
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=handle_sigint)
await runner.run(task)
if __name__ == "__main__":
from pipecat.examples.run import main
main(run_example, transport_params=transport_params)

89
examples/foundational/13h-speechmatics-transcription.py Normal file
View File

@@ -0,0 +1,89 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
from dotenv import load_dotenv
from loguru import logger
from pipecat.frames.frames import Frame, TranscriptionFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
class TranscriptionLogger(FrameProcessor):
async def process_frame(self, frame: Frame, direction: FrameDirection):
await super().process_frame(frame, direction)
if isinstance(frame, TranscriptionFrame):
print(f"Transcription: {frame.text}")
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(audio_in_enabled=True),
"twilio": lambda: FastAPIWebsocketParams(audio_in_enabled=True),
"webrtc": lambda: TransportParams(audio_in_enabled=True),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
"""Run example using Speechmatics STT.
This example will use diarization within our STT service and output the words spoken by
each individual speaker and wrap them with XML tags.
If you do not wish to use diarization, then set the `enable_speaker_diarization` parameter
to `False` or omit it altogether. The `text_format` will only be used if diarization is enabled.
By default, this example will use our ENHANCED operating point, which is optimized for
high accuracy. You can change this by setting the `operating_point` parameter to a different
value.
For more information on operating points, see the Speechmatics documentation:
https://docs.speechmatics.com/rt-api-ref
"""
logger.info(f"Starting bot")
stt = SpeechmaticsSTTService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
language=Language.EN,
enable_speaker_diarization=True,
text_format="<{speaker_id}>{text}</{speaker_id}>",
)
tl = TranscriptionLogger()
pipeline = Pipeline([transport.input(), stt, tl])
task = PipelineTask(pipeline)
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=handle_sigint)
await runner.run(task)
if __name__ == "__main__":
from pipecat.examples.run import main
main(run_example, transport_params=transport_params)

2
examples/foundational/14-function-calling.py
View File

@@ -134,10 +134,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/14a-function-calling-anthropic.py
View File

@@ -127,8 +127,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)

2
examples/foundational/14b-function-calling-anthropic-video.py
View File

@@ -172,8 +172,8 @@ If you need to use a tool, simply use the tool. Do not tell the user the tool yo
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)

10
examples/foundational/14c-function-calling-together.py
View File

@@ -16,7 +16,7 @@ from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import TTSSpeakFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -116,7 +116,13 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
]
)
task = PipelineTask(pipeline)
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

10
examples/foundational/14d-function-calling-video.py
View File

@@ -17,7 +17,7 @@ from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.examples.run import get_transport_client_id, maybe_capture_participant_camera
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -158,7 +158,13 @@ indicate you should use the get_image tool are:
]
)
task = PipelineTask(pipeline)
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

1
examples/foundational/14e-function-calling-gemini.py → examples/foundational/14e-function-calling-google.py
View File

@@ -183,7 +183,6 @@ indicate you should use the get_image tool are:
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

1
examples/foundational/14f-function-calling-groq.py
View File

@@ -121,7 +121,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

1
examples/foundational/14g-function-calling-grok.py
View File

@@ -111,7 +111,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

1
examples/foundational/14h-function-calling-azure.py
View File

@@ -120,7 +120,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

1
examples/foundational/14i-function-calling-fireworks.py
View File

@@ -119,7 +119,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

3
examples/foundational/14j-function-calling-nim.py
View File

@@ -42,7 +42,7 @@ transport_params = {
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"twilio": lambda: TransportParams(
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
@@ -117,7 +117,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

2
examples/foundational/14k-function-calling-cerebras.py
View File

@@ -126,10 +126,8 @@ Start by asking me for my location. Then, use 'get_weather_current' to give me a
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/14l-function-calling-deepseek.py
View File

@@ -126,10 +126,8 @@ Start by asking me for my location. Then, use 'get_weather_current' to give me a
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/14m-function-calling-openrouter.py
View File

@@ -120,10 +120,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/14n-function-calling-perplexity.py
View File

@@ -90,10 +90,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

1
examples/foundational/14o-function-calling-gemini-openai-format.py
View File

@@ -116,7 +116,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

1
examples/foundational/14p-function-calling-gemini-vertex-ai.py
View File

@@ -122,7 +122,6 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),

2
examples/foundational/14q-function-calling-qwen.py
View File

@@ -118,10 +118,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/14r-function-calling-aws.py
View File

@@ -134,10 +134,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

152
examples/foundational/14s-function-calling-sambanova.py Normal file
View File

@@ -0,0 +1,152 @@
#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
from dotenv import load_dotenv
from loguru import logger
from pipecat.adapters.schemas.function_schema import FunctionSchema
from pipecat.adapters.schemas.tools_schema import ToolsSchema
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import TTSSpeakFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_response import LLMUserAggregatorParams
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.sambanova.llm import SambaNovaLLMService
from pipecat.services.sambanova.stt import SambaNovaSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
async def fetch_weather_from_api(params: FunctionCallParams):
await params.result_callback({"conditions": "nice", "temperature": "75"})
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
logger.info(f"Starting bot")
stt = SambaNovaSTTService(
model="Whisper-Large-v3",
api_key=os.getenv("SAMBANOVA_API_KEY"),
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
)
llm = SambaNovaLLMService(
api_key=os.getenv("SAMBANOVA_API_KEY"),
model="Llama-4-Maverick-17B-128E-Instruct",
)
# You can also register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.
llm.register_function("get_current_weather", fetch_weather_from_api)
@llm.event_handler("on_function_calls_started")
async def on_function_calls_started(service, function_calls):
await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
weather_function = FunctionSchema(
name="get_current_weather",
description="Get the current weather",
properties={
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Infer this from the user's location.",
},
},
required=["location"],
)
tools = ToolsSchema(standard_tools=[weather_function])
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
context = OpenAILLMContext(messages, tools)
context_aggregator = llm.create_context_aggregator(
context, user_params=LLMUserAggregatorParams(aggregation_timeout=0.05)
)
pipeline = Pipeline(
[
transport.input(),
stt,
context_aggregator.user(),
llm,
tts,
transport.output(),
context_aggregator.assistant(),
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=handle_sigint)
await runner.run(task)
if __name__ == "__main__":
from pipecat.examples.run import main
main(run_example, transport_params=transport_params)

146
examples/foundational/14t-function-calling-direct.py Normal file
View File

@@ -0,0 +1,146 @@
#
# Copyright (c) 2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
from dotenv import load_dotenv
from loguru import logger
from pipecat.adapters.schemas.tools_schema import ToolsSchema
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import TTSSpeakFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams
load_dotenv(override=True)
async def get_current_weather(params: FunctionCallParams, location: str, format: str):
"""
Get the current weather.
Args:
location (str): The city and state, e.g. "San Francisco, CA".
format (str): The temperature unit to use. Must be either "celsius" or "fahrenheit". Infer this from the user's location.
"""
await params.result_callback({"conditions": "nice", "temperature": "75"})
async def get_restaurant_recommendation(params: FunctionCallParams, location: str):
"""
Get a restaurant recommendation.
Args:
location (str): The city and state, e.g. "San Francisco, CA".
"""
await params.result_callback({"name": "The Golden Dragon"})
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
logger.info(f"Starting bot")
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
)
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
# You can also register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.
llm.register_direct_function(get_current_weather)
llm.register_direct_function(get_restaurant_recommendation)
@llm.event_handler("on_function_calls_started")
async def on_function_calls_started(service, function_calls):
await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
tools = ToolsSchema(standard_tools=[get_current_weather, get_restaurant_recommendation])
messages = [
{
"role": "system",
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
},
]
context = OpenAILLMContext(messages, tools)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(),
stt,
context_aggregator.user(),
llm,
tts,
transport.output(),
context_aggregator.assistant(),
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=handle_sigint)
await runner.run(task)
if __name__ == "__main__":
from pipecat.examples.run import main
main(run_example, transport_params=transport_params)

8
examples/foundational/15-switch-voices.py
View File

@@ -147,7 +147,13 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
]
)
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

8
examples/foundational/15a-switch-languages.py
View File

@@ -135,7 +135,13 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
]
)
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):

4
examples/foundational/16-gpu-container-local-bot.py
View File

@@ -33,7 +33,7 @@ transport_params = {
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
),
"twilio": lambda: TransportParams(
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
vad_analyzer=SileroVADAnalyzer(),
@@ -90,8 +90,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)

3
examples/foundational/17-detect-user-idle.py
View File

@@ -117,9 +117,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
report_only_initial_ttfb=True,
enable_usage_metrics=True,
),
)

2
examples/foundational/19-openai-realtime-beta.py
View File

@@ -186,10 +186,8 @@ Remember, your responses should be short. Just one or two sentences, usually."""
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/19a-azure-realtime-beta.py
View File

@@ -179,10 +179,8 @@ Remember, your responses should be short. Just one or two sentences, usually."""
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/20a-persistent-context-openai.py
View File

@@ -223,10 +223,8 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

2
examples/foundational/20b-persistent-context-openai-realtime.py
View File

@@ -233,10 +233,8 @@ Remember, your responses should be short. Just one or two sentences, usually."""
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
),
)

Some files were not shown because too many files have changed in this diff Show More