Merge branch 'main' into groundingMetadata

This commit is contained in:
Pete
2025-07-03 18:47:47 -04:00
committed by GitHub
200 changed files with 10261 additions and 1831 deletions

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"
}

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]

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",

View File

@@ -0,0 +1,153 @@
#
# Copyright (c) 20242025, 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)

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(),

View File

@@ -0,0 +1,89 @@
#
# Copyright (c) 20242025, 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)

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(),

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)

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(),

View File

@@ -55,7 +55,7 @@ transport_params = {
# endpointing, for now.
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
),
"twilio": lambda: TransportParams(
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
# set stop_secs to something roughly similar to the internal setting

View File

@@ -0,0 +1,242 @@
#
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
import tempfile
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.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.gemini_multimodal_live.gemini import (
GeminiMultimodalLiveLLMService,
)
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,
video_in_enabled=False,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
video_in_enabled=False,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
video_in_enabled=False,
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
),
}
sample_file_path = ""
async def create_sample_file():
if sample_file_path:
return sample_file_path
else:
"""Create a sample text file for testing the File API."""
content = """# Sample Document for Gemini File API Test
This is a test document to demonstrate the Gemini File API functionality.
## Key Information:
- This document was created for testing purposes
- It contains information about AI assistants
- The document should be analyzed by Gemini
- The secret phrase for the test is "Pineapple Pizza"
## AI Assistant Capabilities:
1. Natural language processing
2. File analysis and understanding
3. Context-aware conversations
4. Multi-modal interactions
## Conclusion:
This document serves as a test case for the Gemini File API integration with Pipecat.
The AI should be able to reference and discuss the contents of this file.
"""
# Create a temporary file
with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
f.write(content)
return f.name
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
logger.info(f"Starting File API bot")
# Create a sample file to upload
sample_file_path = await create_sample_file()
logger.info(f"Created sample file: {sample_file_path}")
system_instruction = """
You are a helpful AI assistant with access to a document that has been uploaded for analysis.
The document contains test information.
You should be able to:
- Reference and discuss the contents of the uploaded document
- Answer questions about what's in the document
- Use the information from the document in our conversation
Your output will be converted to audio so don't include special characters in your answers.
Be friendly and demonstrate your ability to work with the uploaded file.
"""
# Initialize Gemini service with File API support
llm = GeminiMultimodalLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction=system_instruction,
voice_id="Charon", # Aoede, Charon, Fenrir, Kore, Puck
transcribe_user_audio=True,
)
# Upload the sample file to Gemini File API
logger.info("Uploading file to Gemini File API...")
file_info = None
try:
file_info = await llm.file_api.upload_file(
sample_file_path, display_name="Sample Test Document"
)
logger.info(f"File uploaded successfully: {file_info['file']['name']}")
# Get file URI and mime type
file_uri = file_info["file"]["uri"]
mime_type = "text/plain"
# Create context with file reference
context = OpenAILLMContext(
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Greet the user and let them know you have access to a document they can ask you about. Mention that you can discuss its contents.",
},
{
"type": "file_data",
"file_data": {"mime_type": mime_type, "file_uri": file_uri},
},
],
}
]
)
logger.info("File reference added to conversation context")
except Exception as e:
logger.error(f"Error uploading file: {e}")
# Continue with a basic context if file upload fails
context = OpenAILLMContext(
[
{
"role": "user",
"content": "Greet the user and explain that there was an issue with file upload, but you're ready to help with other tasks.",
}
]
)
# Create context aggregator
context_aggregator = llm.create_context_aggregator(context)
# Build the pipeline
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
llm,
transport.output(),
context_aggregator.assistant(),
]
)
# Configure the pipeline task
task = PipelineTask(
pipeline,
params=PipelineParams(
allow_interruptions=True,
enable_metrics=True,
enable_usage_metrics=True,
),
)
# Handle client connection event
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation using standard context frame
await task.queue_frames([context_aggregator.user().get_context_frame()])
# Handle client disconnection events
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
@transport.event_handler("on_client_closed")
async def on_client_closed(transport, client):
logger.info(f"Client closed connection")
await task.cancel()
# Run the pipeline
runner = PipelineRunner(handle_sigint=False)
await runner.run(task)
# Clean up: delete the uploaded file and temporary file
if file_info:
try:
await llm.file_api.delete_file(file_info["file"]["name"])
logger.info("Cleaned up uploaded file from Gemini")
except Exception as e:
logger.error(f"Error cleaning up file: {e}")
# Remove temporary file
try:
os.unlink(sample_file_path)
logger.info("Cleaned up temporary file")
except Exception as e:
logger.error(f"Error removing temporary file: {e}")
if __name__ == "__main__":
from pipecat.examples.run import main
upload_example_file = input("""
Please pass in a TEXT filepath to test upload.
NOTE: Files are stored on Google's servers for 48 hours.
Press Enter to use a default test file.
text filepath : """)
if upload_example_file:
print(f"Uploading file: {upload_example_file}")
sample_file_path = upload_example_file.strip()
else:
print(f"Using default file")
main(run_example, transport_params=transport_params)

View File

@@ -18,8 +18,8 @@ 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.google.llm import GoogleLLMService
from pipecat.services.mcp_service import MCPClient
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
@@ -58,7 +58,7 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
)
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o-mini")
llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash")
try:
# Github MCP docs: https://github.com/github/github-mcp-server

View File

@@ -102,6 +102,7 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
secret_access_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
access_key_id=os.getenv("AWS_ACCESS_KEY_ID"),
region=os.getenv("AWS_REGION"), # as of 2025-05-06, us-east-1 is the only supported region
session_token=os.getenv("AWS_SESSION_TOKEN"),
voice_id="tiffany", # matthew, tiffany, amy
# you could choose to pass instruction here rather than via context
# system_instruction=system_instruction

View File

@@ -191,7 +191,17 @@ class WebsocketClientApp {
const startTime = Date.now();
this.recordingSerializer = new RecordingSerializer()
const transport = this.ENABLE_RECORDING_MODE ? new WebSocketTransport({serializer: this.recordingSerializer}) : new WebSocketTransport();
const transport = this.ENABLE_RECORDING_MODE ?
new WebSocketTransport({
serializer: this.recordingSerializer,
recorderSampleRate: 8000,
playerSampleRate:8000
}) :
new WebSocketTransport({
serializer: new ProtobufFrameSerializer(),
recorderSampleRate: 8000,
playerSampleRate:8000
});
this.websocketTransport = transport
const RTVIConfig: RTVIClientOptions = {

View File

@@ -0,0 +1,4 @@
SENTRY_DSN=
DEEPGRAM_API_KEY=
CARTESIA_API_KEY=
OPENAI_API_KEY=

View File

@@ -18,7 +18,6 @@ from fastapi import FastAPI, Request, WebSocket
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import RedirectResponse
from loguru import logger
from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import (
@@ -27,11 +26,13 @@ from pipecat.frames.frames import (
Frame,
InterimTranscriptionFrame,
LLMFullResponseEndFrame,
LLMMessagesFrame,
StartFrame,
StartInterruptionFrame,
StopFrame,
StopInterruptionFrame,
TranscriptionFrame,
TTSSpeakFrame,
UserStartedSpeakingFrame,
UserStoppedSpeakingFrame,
)
@@ -47,6 +48,7 @@ from pipecat.processors.aggregators.openai_llm_context import (
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIProcessor
from pipecat.processors.metrics.sentry import SentryMetrics
from pipecat.processors.user_idle_processor import UserIdleProcessor
from pipecat.serializers.protobuf import ProtobufFrameSerializer
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -78,9 +80,6 @@ app.add_middleware(
allow_headers=["*"],
)
# Mount the frontend at /
app.mount("/client", SmallWebRTCPrebuiltUI)
class SimulateFreezeInput(FrameProcessor):
def __init__(
@@ -188,6 +187,37 @@ async def run_example(websocket_client):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
async def handle_user_idle(user_idle: UserIdleProcessor, retry_count: int) -> bool:
if retry_count == 1:
# First attempt: Add a gentle prompt to the conversation
messages.append(
{
"role": "system",
"content": "The user has been quiet. Politely and briefly ask if they're still there.",
}
)
await user_idle.push_frame(LLMMessagesFrame(messages))
return True
elif retry_count == 2:
# Second attempt: More direct prompt
messages.append(
{
"role": "system",
"content": "The user is still inactive. Ask if they'd like to continue our conversation.",
}
)
await user_idle.push_frame(LLMMessagesFrame(messages))
return True
else:
# Third attempt: End the conversation
await user_idle.push_frame(
TTSSpeakFrame("It seems like you're busy right now. Have a nice day!")
)
await task.queue_frame(EndFrame())
return False
user_idle = UserIdleProcessor(callback=handle_user_idle, timeout=10.0)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
@@ -222,6 +252,7 @@ async def run_example(websocket_client):
stt,
],
),
user_idle,
rtvi,
context_aggregator.user(), # User responses
llm, # LLM
@@ -238,6 +269,8 @@ async def run_example(websocket_client):
enable_metrics=True,
enable_usage_metrics=True,
report_only_initial_ttfb=True,
audio_in_sample_rate=8000,
audio_out_sample_rate=8000,
),
idle_timeout_secs=120,
observers=[
@@ -249,6 +282,10 @@ async def run_example(websocket_client):
# LLMTextFrame: None,
OpenAILLMContextFrame: None,
LLMFullResponseEndFrame: None,
UserStartedSpeakingFrame: None,
UserStoppedSpeakingFrame: None,
StartInterruptionFrame: None,
StopInterruptionFrame: None,
},
exclude_fields={
"result",

View File

@@ -0,0 +1,4 @@
python-dotenv
fastapi[all]
uvicorn
pipecat-ai[silero,websocket,openai, deepgram, cartesia, sentry]

View File

@@ -24,6 +24,7 @@ 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
from pipecat.utils.tracing.setup import setup_tracing
@@ -61,7 +62,7 @@ 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(),

View File

@@ -1,6 +1,6 @@
fastapi
uvicorn
python-dotenv
pipecat-ai[webrtc,silero,cartesia,deepgram,openai,tracing]
pipecat-ai[daily,webrtc,silero,cartesia,deepgram,openai,tracing]
pipecat-ai-small-webrtc-prebuilt
opentelemetry-exporter-otlp-proto-grpc

View File

@@ -26,7 +26,7 @@ Create a `.env` file with your API keys to enable tracing:
```
ENABLE_TRACING=true
# OTLP endpoint for Langfuse
OTEL_EXPORTER_OTLP_ENDPOINT=http://cloud.langfuse.com/api/public/otel
OTEL_EXPORTER_OTLP_ENDPOINT=https://cloud.langfuse.com/api/public/otel
OTEL_EXPORTER_OTLP_HEADERS=Authorization=Basic%20<base64_encoded_api_key>
# Set to any value to enable console output for debugging
# OTEL_CONSOLE_EXPORT=true

View File

@@ -24,6 +24,7 @@ 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
from pipecat.utils.tracing.setup import setup_tracing
@@ -58,7 +59,7 @@ 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(),

View File

@@ -1,6 +1,6 @@
fastapi
uvicorn
python-dotenv
pipecat-ai[webrtc,silero,cartesia,deepgram,openai,tracing]
pipecat-ai[daily,webrtc,silero,cartesia,deepgram,openai,tracing]
pipecat-ai-small-webrtc-prebuilt
opentelemetry-exporter-otlp-proto-http

View File

@@ -1,4 +1,4 @@
pipecat-ai[daily,elevenlabs,openai,silero]
pipecat-ai[daily,cartesia,openai,silero]
fastapi==0.115.6
uvicorn
python-dotenv

View File

@@ -15,7 +15,6 @@
90031FC22C616EE900408370 /* SimpleChatbotUITests.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90031FC12C616EE900408370 /* SimpleChatbotUITests.swift */; };
90031FC42C616EE900408370 /* SimpleChatbotUITestsLaunchTests.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90031FC32C616EE900408370 /* SimpleChatbotUITestsLaunchTests.swift */; };
90031FDC2C6D5DD700408370 /* ToastModifier.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90031FDB2C6D5DD700408370 /* ToastModifier.swift */; };
907C98842D37E6AF0079441F /* PipecatClientIOSDaily in Frameworks */ = {isa = PBXBuildFile; productRef = 907C98832D37E6AF0079441F /* PipecatClientIOSDaily */; };
90ABB98E2C735ED6000D9CC7 /* MeetingView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90ABB98D2C735ED6000D9CC7 /* MeetingView.swift */; };
90ABB9902C736A8B000D9CC7 /* WaveformView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90ABB98F2C736A8B000D9CC7 /* WaveformView.swift */; };
90ABB9932C73820D000D9CC7 /* MicrophoneView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90ABB9922C73820D000D9CC7 /* MicrophoneView.swift */; };
@@ -25,6 +24,8 @@
90ABB9A32C74E1CE000D9CC7 /* SettingsView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90ABB9A22C74E1CE000D9CC7 /* SettingsView.swift */; };
90ABB9A62C74EA8A000D9CC7 /* SettingsPreference.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90ABB9A52C74EA8A000D9CC7 /* SettingsPreference.swift */; };
90ABB9A82C74EAB1000D9CC7 /* SettingsManager.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90ABB9A72C74EAB1000D9CC7 /* SettingsManager.swift */; };
90CC98B02E158093003C2706 /* PipecatClientIOSDaily in Frameworks */ = {isa = PBXBuildFile; productRef = 90CC98AF2E158093003C2706 /* PipecatClientIOSDaily */; };
90CC98B62E15820B003C2706 /* PipecatClientIOSDaily in Frameworks */ = {isa = PBXBuildFile; productRef = 90CC98B52E15820B003C2706 /* PipecatClientIOSDaily */; };
/* End PBXBuildFile section */
/* Begin PBXContainerItemProxy section */
@@ -73,7 +74,8 @@
isa = PBXFrameworksBuildPhase;
buildActionMask = 2147483647;
files = (
907C98842D37E6AF0079441F /* PipecatClientIOSDaily in Frameworks */,
90CC98B62E15820B003C2706 /* PipecatClientIOSDaily in Frameworks */,
90CC98B02E158093003C2706 /* PipecatClientIOSDaily in Frameworks */,
);
runOnlyForDeploymentPostprocessing = 0;
};
@@ -218,7 +220,8 @@
);
name = SimpleChatbot;
packageProductDependencies = (
907C98832D37E6AF0079441F /* PipecatClientIOSDaily */,
90CC98AF2E158093003C2706 /* PipecatClientIOSDaily */,
90CC98B52E15820B003C2706 /* PipecatClientIOSDaily */,
);
productName = SimpleChatbot;
productReference = 90031FA32C616EE700408370 /* SimpleChatbot.app */;
@@ -293,7 +296,7 @@
);
mainGroup = 90031F9A2C616EE700408370;
packageReferences = (
907C98822D37E6AF0079441F /* XCRemoteSwiftPackageReference "pipecat-client-ios-daily" */,
90CC98B42E15820B003C2706 /* XCRemoteSwiftPackageReference "pipecat-client-ios-daily" */,
);
productRefGroup = 90031FA42C616EE700408370 /* Products */;
projectDirPath = "";
@@ -682,20 +685,24 @@
/* End XCConfigurationList section */
/* Begin XCRemoteSwiftPackageReference section */
907C98822D37E6AF0079441F /* XCRemoteSwiftPackageReference "pipecat-client-ios-daily" */ = {
90CC98B42E15820B003C2706 /* XCRemoteSwiftPackageReference "pipecat-client-ios-daily" */ = {
isa = XCRemoteSwiftPackageReference;
repositoryURL = "https://github.com/pipecat-ai/pipecat-client-ios-daily/";
requirement = {
kind = upToNextMajorVersion;
minimumVersion = 0.3.2;
minimumVersion = 0.3.6;
};
};
/* End XCRemoteSwiftPackageReference section */
/* Begin XCSwiftPackageProductDependency section */
907C98832D37E6AF0079441F /* PipecatClientIOSDaily */ = {
90CC98AF2E158093003C2706 /* PipecatClientIOSDaily */ = {
isa = XCSwiftPackageProductDependency;
package = 907C98822D37E6AF0079441F /* XCRemoteSwiftPackageReference "pipecat-client-ios-daily" */;
productName = PipecatClientIOSDaily;
};
90CC98B52E15820B003C2706 /* PipecatClientIOSDaily */ = {
isa = XCSwiftPackageProductDependency;
package = 90CC98B42E15820B003C2706 /* XCRemoteSwiftPackageReference "pipecat-client-ios-daily" */;
productName = PipecatClientIOSDaily;
};
/* End XCSwiftPackageProductDependency section */

View File

@@ -1,12 +1,13 @@
{
"originHash" : "cc17f08b06def9570d775e9c6f7a8dc10d1588b98127e977c47d052abac659b7",
"pins" : [
{
"identity" : "daily-client-ios",
"kind" : "remoteSourceControl",
"location" : "https://github.com/daily-co/daily-client-ios.git",
"state" : {
"revision" : "15804ce495780da3ec2d05ab99736315f7bfbd24",
"version" : "0.28.0"
"revision" : "431938db25e5807120e89e2dc5bab1c076729f59",
"version" : "0.31.0"
}
},
{
@@ -14,8 +15,8 @@
"kind" : "remoteSourceControl",
"location" : "https://github.com/pipecat-ai/pipecat-client-ios.git",
"state" : {
"revision" : "c679512e367002a1a67da85d503fec72d9b17191",
"version" : "0.3.2"
"revision" : "f92b5e68e56a8311f7d8ead68a7a5674843cbc40",
"version" : "0.3.6"
}
},
{
@@ -23,10 +24,10 @@
"kind" : "remoteSourceControl",
"location" : "https://github.com/pipecat-ai/pipecat-client-ios-daily/",
"state" : {
"revision" : "a337fe6642c52376d2f90eafcb965f5be772ce72",
"version" : "0.3.2"
"revision" : "8f494da903192c22c367ecf9e51248c9b651fbc6",
"version" : "0.3.6"
}
}
],
"version" : 2
"version" : 3
}

View File

@@ -78,10 +78,11 @@ class CallContainerModel: ObservableObject {
self.saveCredentials(backendURL: baseUrl)
}
@MainActor
func disconnect() {
self.rtviClientIOS?.disconnect(completion: nil)
self.rtviClientIOS?.release()
Task { @MainActor in
try await self.rtviClientIOS?.disconnect()
self.rtviClientIOS?.release()
}
}
func showError(message: String) {

View File

@@ -345,9 +345,9 @@
}
},
"node_modules/@next/env": {
"version": "14.2.28",
"resolved": "https://registry.npmjs.org/@next/env/-/env-14.2.28.tgz",
"integrity": "sha512-PAmWhJfJQlP+kxZwCjrVd9QnR5x0R3u0mTXTiZDgSd4h5LdXmjxCCWbN9kq6hkZBOax8Rm3xDW5HagWyJuT37g=="
"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": "14.1.4",
@@ -359,9 +359,9 @@
}
},
"node_modules/@next/swc-darwin-arm64": {
"version": "14.2.28",
"resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-14.2.28.tgz",
"integrity": "sha512-kzGChl9setxYWpk3H6fTZXXPFFjg7urptLq5o5ZgYezCrqlemKttwMT5iFyx/p1e/JeglTwDFRtb923gTJ3R1w==",
"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"
],
@@ -374,9 +374,9 @@
}
},
"node_modules/@next/swc-darwin-x64": {
"version": "14.2.28",
"resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-14.2.28.tgz",
"integrity": "sha512-z6FXYHDJlFOzVEOiiJ/4NG8aLCeayZdcRSMjPDysW297Up6r22xw6Ea9AOwQqbNsth8JNgIK8EkWz2IDwaLQcw==",
"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"
],
@@ -389,9 +389,9 @@
}
},
"node_modules/@next/swc-linux-arm64-gnu": {
"version": "14.2.28",
"resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-14.2.28.tgz",
"integrity": "sha512-9ARHLEQXhAilNJ7rgQX8xs9aH3yJSj888ssSjJLeldiZKR4D7N08MfMqljk77fAwZsWwsrp8ohHsMvurvv9liQ==",
"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"
],
@@ -404,9 +404,9 @@
}
},
"node_modules/@next/swc-linux-arm64-musl": {
"version": "14.2.28",
"resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-14.2.28.tgz",
"integrity": "sha512-p6gvatI1nX41KCizEe6JkF0FS/cEEF0u23vKDpl+WhPe/fCTBeGkEBh7iW2cUM0rvquPVwPWdiUR6Ebr/kQWxQ==",
"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"
],
@@ -419,9 +419,9 @@
}
},
"node_modules/@next/swc-linux-x64-gnu": {
"version": "14.2.28",
"resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-14.2.28.tgz",
"integrity": "sha512-nsiSnz2wO6GwMAX2o0iucONlVL7dNgKUqt/mDTATGO2NY59EO/ZKnKEr80BJFhuA5UC1KZOMblJHWZoqIJddpA==",
"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"
],
@@ -434,9 +434,9 @@
}
},
"node_modules/@next/swc-linux-x64-musl": {
"version": "14.2.28",
"resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-14.2.28.tgz",
"integrity": "sha512-+IuGQKoI3abrXFqx7GtlvNOpeExUH1mTIqCrh1LGFf8DnlUcTmOOCApEnPJUSLrSbzOdsF2ho2KhnQoO0I1RDw==",
"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"
],
@@ -449,9 +449,9 @@
}
},
"node_modules/@next/swc-win32-arm64-msvc": {
"version": "14.2.28",
"resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-14.2.28.tgz",
"integrity": "sha512-l61WZ3nevt4BAnGksUVFKy2uJP5DPz2E0Ma/Oklvo3sGj9sw3q7vBWONFRgz+ICiHpW5mV+mBrkB3XEubMrKaA==",
"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"
],
@@ -464,9 +464,9 @@
}
},
"node_modules/@next/swc-win32-ia32-msvc": {
"version": "14.2.28",
"resolved": "https://registry.npmjs.org/@next/swc-win32-ia32-msvc/-/swc-win32-ia32-msvc-14.2.28.tgz",
"integrity": "sha512-+Kcp1T3jHZnJ9v9VTJ/yf1t/xmtFAc/Sge4v7mVc1z+NYfYzisi8kJ9AsY8itbgq+WgEwMtOpiLLJsUy2qnXZw==",
"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"
],
@@ -479,9 +479,9 @@
}
},
"node_modules/@next/swc-win32-x64-msvc": {
"version": "14.2.28",
"resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-14.2.28.tgz",
"integrity": "sha512-1gCmpvyhz7DkB1srRItJTnmR2UwQPAUXXIg9r0/56g3O8etGmwlX68skKXJOp9EejW3hhv7nSQUJ2raFiz4MoA==",
"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"
],
@@ -1317,9 +1317,9 @@
}
},
"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,
"dependencies": {
"balanced-match": "^1.0.0"
@@ -1960,9 +1960,9 @@
"integrity": "sha512-AlcaJBi/pqqJBIQ8U9Mcpc9i8Aqxn88Skv5d+xBX006BY5u8N3mGLHa5Lgppa7L/HfwgwLgZ6NYs+Ag6uUmJRA=="
},
"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,
"dependencies": {
"balanced-match": "^1.0.0",
@@ -3391,9 +3391,9 @@
}
},
"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"
}
@@ -4389,11 +4389,11 @@
"dev": true
},
"node_modules/next": {
"version": "14.2.28",
"resolved": "https://registry.npmjs.org/next/-/next-14.2.28.tgz",
"integrity": "sha512-QLEIP/kYXynIxtcKB6vNjtWLVs3Y4Sb+EClTC/CSVzdLD1gIuItccpu/n1lhmduffI32iPGEK2cLLxxt28qgYA==",
"version": "14.2.30",
"resolved": "https://registry.npmjs.org/next/-/next-14.2.30.tgz",
"integrity": "sha512-+COdu6HQrHHFQ1S/8BBsCag61jZacmvbuL2avHvQFbWa2Ox7bE+d8FyNgxRLjXQ5wtPyQwEmk85js/AuaG2Sbg==",
"dependencies": {
"@next/env": "14.2.28",
"@next/env": "14.2.30",
"@swc/helpers": "0.5.5",
"busboy": "1.6.0",
"caniuse-lite": "^1.0.30001579",
@@ -4408,15 +4408,15 @@
"node": ">=18.17.0"
},
"optionalDependencies": {
"@next/swc-darwin-arm64": "14.2.28",
"@next/swc-darwin-x64": "14.2.28",
"@next/swc-linux-arm64-gnu": "14.2.28",
"@next/swc-linux-arm64-musl": "14.2.28",
"@next/swc-linux-x64-gnu": "14.2.28",
"@next/swc-linux-x64-musl": "14.2.28",
"@next/swc-win32-arm64-msvc": "14.2.28",
"@next/swc-win32-ia32-msvc": "14.2.28",
"@next/swc-win32-x64-msvc": "14.2.28"
"@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",

View File

@@ -6,10 +6,10 @@ Basic implementation using the [Pipecat JavaScript SDK](https://docs.pipecat.ai/
1. Run the bot server. See the [server README](../README).
2. Navigate to the `client/javascript` directory:
2. Navigate to the `client` directory:
```bash
cd client/javascript
cd client
```
3. Install dependencies: