Add dialout to the Daily phone example (#998)

* added dialout to daily phone example

* cleanup

* cleanup

* pre-commit hook

* Fix typo

* More explicit README instructions

---------

Co-authored-by: Mark Backman <mark@daily.co>
This commit is contained in:
chadbailey59
2025-01-27 12:21:30 -06:00
committed by GitHub
parent 86c1e6a3bd
commit 179ddbea7d
13 changed files with 212 additions and 108 deletions

View File

@@ -39,7 +39,7 @@ Next, follow the steps in the README for each demo.
| [Translation Chatbot](translation-chatbot) | Listens for user speech, then translates that speech to Spanish and speaks the translation back. Demonstrates multi-participant use-cases. | Deepgram, Azure, OpenAI, Daily, Daily Prebuilt UI |
| [Moondream Chatbot](moondream-chatbot) | Demonstrates how to add vision capabilities to GPT4. **Note: works best with a GPU** | Deepgram, ElevenLabs, OpenAI, Moondream, Daily, Daily Prebuilt UI |
| [Patient intake](patient-intake) | A chatbot that can call functions in response to user input. | Deepgram, ElevenLabs, OpenAI, Daily, Daily Prebuilt UI |
| [Dialin Chatbot](dialin-chatbot) | A chatbot that connects to an incoming phone call from Daily or Twilio. | Deepgram, ElevenLabs, OpenAI, Daily, Twilio |
| [Phone Chatbot](phone-chatbot) | A chatbot that connects to PSTN/SIP phone calls, powered by Daily or Twilio. | Deepgram, ElevenLabs, OpenAI, Daily, Twilio |
| [Twilio Chatbot](twilio-chatbot) | A chatbot that connects to an incoming phone call from Twilio. | Deepgram, ElevenLabs, OpenAI, Daily, Twilio |
| [studypal](studypal) | A chatbot to have a conversation about any article on the web | |
| [WebSocket Chatbot Server](websocket-server) | A real-time websocket server that handles audio streaming and bot interactions with speech-to-text and text-to-speech capabilities. | Cartesia, Deepgram, OpenAI, Websockets |

View File

@@ -1,85 +0,0 @@
<div align="center">
 <img alt="pipecat" width="300px" height="auto" src="image.png">
</div>
# Dialin example
Example project that demonstrates how to add phone number dialin to your Pipecat bots. We include examples for both Daily (`bot_daily.py`) and Twilio (`bot_twilio.py`), depending on who you want to use as a phone vendor.
- 🔁 Transport: Daily WebRTC
- 💬 Speech-to-Text: Deepgram via Daily transport
- 🤖 LLM: GPT4-o / OpenAI
- 🔉 Text-to-Speech: ElevenLabs
#### Should I use Daily or Twilio as a vendor?
If you're starting from scratch, using Daily to provision phone numbers alongside Daily as a transport offers some convenience (such as automatic call forwarding.)
If you already have Twilio numbers and workflows that you want to connect to your Pipecat bots, there is some additional configuration required (you'll need to create a `on_dialin_ready` and use the Twilio client to trigger the forward.)
You can read more about this, as well as see respective walkthroughs in our docs.
## Setup
```shell
# Install the requirements
pip install -r requirements.txt
# Setup your env
mv env.example .env
```
## Using Daily numbers
Run `bot_runner.py` to handle incoming HTTP requests:
`python bot_runner.py --host localhost`
Then target the following URL:
`POST /daily_start_bot`
For more configuration options, please consult Daily's API documentation.
## Using Twilio numbers
As above, but target the following URL:
`POST /twilio_start_bot`
For more configuration options, please consult Twilio's API documentation.
## Deployment example
A Dockerfile is included in this demo for convenience. Here is an example of how to build and deploy your bot to [fly.io](https://fly.io).
*Please note: This demo spawns agents as subprocesses for convenience / demonstration purposes. You would likely not want to do this in production as it would limit concurrency to available system resources. For more information on how to deploy your bots using VMs, refer to the Pipecat documentation.*
### Build the docker image
`docker build -t tag:project .`
### Launch the fly project
`mv fly.example.toml fly.toml`
`fly launch` (using the included fly.toml)
### Setup your secrets on Fly
Set the necessary secrets (found in `env.example`)
`fly secrets set DAILY_API_KEY=... OPENAI_API_KEY=... ELEVENLABS_API_KEY=... ELEVENLABS_VOICE_ID=...`
If you're using Twilio as a number vendor:
`fly secrets set TWILIO_ACCOUNT_SID=... TWILIO_AUTH_TOKEN=...`
### Deploy!
`fly deploy`
## Need to do something more advanced?
This demo covers the basics of bot telephony. If you want to know more about working with PSTN / SIP, please ping us on [Discord](https://discord.gg/pipecat).

View File

@@ -0,0 +1,149 @@
<div align="center">
 <img alt="pipecat" width="300px" height="auto" src="image.png">
</div>
# Phone Chatbot
Example project that demonstrates how to add phone funtionality to your Pipecat bots. We include examples for Daily (`bot_daily.py`) dial-in and dial-out, and Twilio (`bot_twilio.py`) dial-in, depending on who you want to use as a phone vendor.
- 🔁 Transport: Daily WebRTC
- 💬 Speech-to-Text: Deepgram via Daily transport
- 🤖 LLM: GPT4-o / OpenAI
- 🔉 Text-to-Speech: ElevenLabs
#### Should I use Daily or Twilio as a vendor?
If you're starting from scratch, using Daily to provision phone numbers alongside Daily as a transport offers some convenience (such as automatic call forwarding.)
If you already have Twilio numbers and workflows that you want to connect to your Pipecat bots, there is some additional configuration required (you'll need to create a `on_dialin_ready` and use the Twilio client to trigger the forward.)
You can read more about this, as well as see respective walkthroughs in our docs.
## Setup
1. Create and activate a virtual environment:
```shell
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
```
2. Install requirements:
```shell
pip install -r requirements.txt
```
3. Copy env.example to .env and configure:
```shell
cp env.example .env
```
4. Install [ngrok](https://ngrok.com/) so your local server can receive requests from Daily's servers.
## Using Daily numbers
### Running the example
To run either the dial-in or dial-out example, follow these steps to get started:
1. Run `bot_runner.py` to handle incoming HTTP requests:
```shell
python bot_runner.py --host localhost
```
2. Start ngrok running in a terminal window:
```shell
ngrok http --domain yourdomain.ngrok.app 8000
```
3. In a different terminal window, run the Daily bot file:
```shell
python bot_daily.py
```
### Dial-in
To dial-in to the bot, you will need to enable dial-in for your Daily domain. Follow [this guide](https://docs.daily.co/guides/products/dial-in-dial-out/dialin-pinless#provisioning-sip-interconnect-and-pinless-dialin-workflow) to set up your domain.
Note: For the `room_creation_api` property, point at your ngrok hostname: `"room_creation_api": "https://yourdomain.ngrok.app/daily_start_bot"`.
Once your domain is configured, receiving a phone call at a number associated with your Daily account will result in a POST to the `/daily_start_bot` endpoint, which will start a bot session.
### Dial-out
For the bot to dial out to a number, make a POST request to `/daily_start_bot` and include the dial-out phone number in the body of the request as `dialoutNumber`.
For example:
```shell
url -X "POST" "http://localhost:7860/daily_start_bot" \
-H 'Content-Type: application/json; charset=utf-8' \
-d $'{
"dialoutNumber": "+12125551234"
}'
```
### More information
For more configuration options, please consult [Daily's API documentation](https://docs.daily.co).
## Using Twilio numbers
### Running the example
Follow these steps to get started:
1. Run `bot_runner.py` to handle incoming HTTP requests:
```shell
python bot_runner.py --host localhost
```
2. Start ngrok running in a terminal window:
```shell
ngrok http --domain yourdomain.ngrok.app 8000
```
3. In a different terminal window, run the Daily bot file:
```shell
python bot_twilio.py
```
As above, but target the following URL:
`POST /twilio_start_bot`
For more configuration options, please consult Twilio's API documentation.
## Deployment example
A Dockerfile is included in this demo for convenience. Here is an example of how to build and deploy your bot to [fly.io](https://fly.io).
_Please note: This demo spawns agents as subprocesses for convenience / demonstration purposes. You would likely not want to do this in production as it would limit concurrency to available system resources. For more information on how to deploy your bots using VMs, refer to the Pipecat documentation._
### Build the docker image
`docker build -t tag:project .`
### Launch the fly project
`mv fly.example.toml fly.toml`
`fly launch` (using the included fly.toml)
### Setup your secrets on Fly
Set the necessary secrets (found in `env.example`)
`fly secrets set DAILY_API_KEY=... OPENAI_API_KEY=... ELEVENLABS_API_KEY=... ELEVENLABS_VOICE_ID=...`
If you're using Twilio as a number vendor:
`fly secrets set TWILIO_ACCOUNT_SID=... TWILIO_AUTH_TOKEN=...`
### Deploy!
`fly deploy`
## Need to do something more advanced?
This demo covers the basics of bot telephony. If you want to know more about working with PSTN / SIP, please ping us on [Discord](https://discord.gg/pipecat)!

View File

@@ -25,12 +25,11 @@ daily_api_key = os.getenv("DAILY_API_KEY", "")
daily_api_url = os.getenv("DAILY_API_URL", "https://api.daily.co/v1")
async def main(room_url: str, token: str, callId: str, callDomain: str):
# diallin_settings are only needed if Daily's SIP URI is used
async def main(room_url: str, token: str, callId: str, callDomain: str, dialout_number: str | None):
# dialin_settings are only needed if Daily's SIP URI is used
# If you are handling this via Twilio, Telnyx, set this to None
# and handle call-forwarding when on_dialin_ready fires.
diallin_settings = DailyDialinSettings(call_id=callId, call_domain=callDomain)
dialin_settings = DailyDialinSettings(call_id=callId, call_domain=callDomain)
transport = DailyTransport(
room_url,
token,
@@ -38,7 +37,7 @@ async def main(room_url: str, token: str, callId: str, callDomain: str):
DailyParams(
api_url=daily_api_url,
api_key=daily_api_key,
dialin_settings=diallin_settings,
dialin_settings=dialin_settings,
audio_in_enabled=True,
audio_out_enabled=True,
camera_out_enabled=False,
@@ -58,7 +57,7 @@ async def main(room_url: str, token: str, callId: str, callDomain: str):
messages = [
{
"role": "system",
"content": "You are Chatbot, a friendly, helpful robot. 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, but keep your responses brief. Start by saying 'Oh, hello! Who dares dial me at this hour?!'.",
"content": "You are Chatbot, a friendly, helpful robot. 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, but keep your responses brief. Start by saying 'Oh, hello! I'm a friendly chatbot. How can I help you?'.",
},
]
@@ -78,10 +77,41 @@ async def main(room_url: str, token: str, callId: str, callDomain: str):
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
await task.queue_frames([context_aggregator.user().get_context_frame()])
if dialout_number:
logger.debug("dialout number detected; doing dialout")
# Configure some handlers for dialing out
@transport.event_handler("on_joined")
async def on_joined(transport, data):
logger.debug(f"Joined; starting dialout to: {dialout_number}")
await transport.start_dialout({"phoneNumber": dialout_number})
@transport.event_handler("on_dialout_connected")
async def on_dialout_connected(transport, data):
logger.debug(f"Dial-out connected: {data}")
@transport.event_handler("on_dialout_answered")
async def on_dialout_answered(transport, data):
logger.debug(f"Dial-out answered: {data}")
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
# unlike the dialin case, for the dialout case, the caller will speak first. Presumably
# they will answer the phone and say "Hello?" Since we've captured their transcript,
# That will put a frame into the pipeline and prompt an LLM completion, which is how the
# bot will then greet the user.
else:
logger.debug("no dialout number; assuming dialin")
# Different handlers for dialin
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):
await transport.capture_participant_transcription(participant["id"])
# For the dialin case, we want the bot to answer the phone and greet the user. We
# can prompt the bot to speak by putting the context into the pipeline.
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_participant_left")
async def on_participant_left(transport, participant, reason):
@@ -98,6 +128,7 @@ if __name__ == "__main__":
parser.add_argument("-t", type=str, help="Token")
parser.add_argument("-i", type=str, help="Call ID")
parser.add_argument("-d", type=str, help="Call Domain")
parser.add_argument("-o", type=str, help="Dialout number", default=None)
config = parser.parse_args()
asyncio.run(main(config.u, config.t, config.i, config.d))
asyncio.run(main(config.u, config.t, config.i, config.d, config.o))

View File

@@ -73,24 +73,27 @@ action using the Twilio Client library.
"""
async def _create_daily_room(room_url, callId, callDomain=None, vendor="daily"):
async def _create_daily_room(room_url, callId, callDomain=None, dialoutNumber=None, vendor="daily"):
if not room_url:
params = DailyRoomParams(
properties=DailyRoomProperties(
# Note: these are the default values, except for the display name
sip=DailyRoomSipParams(
display_name="dialin-user", video=False, sip_mode="dial-in", num_endpoints=1
)
# Create base properties with SIP settings
properties = DailyRoomProperties(
sip=DailyRoomSipParams(
display_name="dialin-user", video=False, sip_mode="dial-in", num_endpoints=1
)
)
# Only enable dialout if dialoutNumber is provided
if dialoutNumber:
properties.enable_dialout = True
params = DailyRoomParams(properties=properties)
print(f"Creating new room...")
room: DailyRoomObject = await daily_helpers["rest"].create_room(params=params)
else:
# Check passed room URL exist (we assume that it already has a sip set up!)
try:
print(f"Joining existing room: {room_url}")
room: DailyRoomObject = await daily_helpers["rest"].get_room_from_url(room_url)
except Exception:
raise HTTPException(status_code=500, detail=f"Room not found: {room_url}")
@@ -107,6 +110,8 @@ async def _create_daily_room(room_url, callId, callDomain=None, vendor="daily"):
# Note: this is mostly for demonstration purposes (refer to 'deployment' in docs)
if vendor == "daily":
bot_proc = f"python3 -m bot_daily -u {room.url} -t {token} -i {callId} -d {callDomain}"
if dialoutNumber:
bot_proc += f" -o {dialoutNumber}"
else:
bot_proc = f"python3 -m bot_twilio -u {room.url} -t {token} -i {callId} -s {room.config.sip_endpoint}"
@@ -179,11 +184,15 @@ async def daily_start_bot(request: Request) -> JSONResponse:
return JSONResponse({"test": True})
callId = data.get("callId", None)
callDomain = data.get("callDomain", None)
dialoutNumber = data.get("dialoutNumber", None)
except Exception:
raise HTTPException(status_code=500, detail="Missing properties 'callId' or 'callDomain'")
raise HTTPException(
status_code=500, detail="Missing properties 'callId', 'callDomain', or 'dialoutNumber'"
)
print(f"CallId: {callId}, CallDomain: {callDomain}")
room: DailyRoomObject = await _create_daily_room(room_url, callId, callDomain, "daily")
room: DailyRoomObject = await _create_daily_room(
room_url, callId, callDomain, dialoutNumber, "daily"
)
# Grab a token for the user to join with
return JSONResponse({"room_url": room.url, "sipUri": room.config.sip_endpoint})

View File

Before

Width:  |  Height:  |  Size: 19 KiB

After

Width:  |  Height:  |  Size: 19 KiB