moved expiry time to create_room

add CHANGELOG.md

.github/workflows/publish.yaml

@@ -46,7 +46,7 @@ jobs:
     needs: [ build ]
     environment:
       name: pypi
-      url: https://pypi.org/p/dailyai
+      url: https://pypi.org/p/pipecat-ai
     permissions:
       id-token: write
     steps:
@@ -67,7 +67,7 @@ jobs:
     needs: [ build ]
     environment:
       name: testpypi
-      url: https://pypi.org/p/dailyai
+      url: https://pypi.org/p/pipecat-ai
     permissions:
       id-token: write
     steps:

.github/workflows/publish_test.yaml

@@ -46,7 +46,7 @@ jobs:
     needs: [ build ]
     environment:
       name: testpypi
-      url: https://pypi.org/p/dailyai
+      url: https://pypi.org/p/pipecat-ai
     permissions:
       id-token: write
     steps:

CHANGELOG.md

@@ -0,0 +1,232 @@
+# Changelog
+
+All notable changes to **pipecat** will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.0.15] - 2024-05-15
+
+### Fixed
+
+- Quick hot fix for receiving `DailyTransportMessage`.
+
+## [0.0.14] - 2024-05-15
+
+### Added
+
+- Added `DailyTransport` event `on_participant_left`.
+
+- Added support for receiving `DailyTransportMessage`.
+
+### Fixed
+
+- Images are now resized to the size of the output camera. This was causing
+  images not being displayed.
+
+- Fixed an issue in `DailyTransport` that would not allow the input processor to
+  shutdown if no participant ever joined the room.
+
+- Fixed base transports start and stop. In some situation processors would halt
+  or not shutdown properly.
+
+## [0.0.13] - 2024-05-14
+
+### Changed
+
+- `MoondreamService` argument `model_id` is now `model`.
+
+- `VADAnalyzer` arguments have been renamed for more clarity.
+
+### Fixed
+
+- Fixed an issue with `DailyInputTransport` and `DailyOutputTransport` that
+  could cause some threads to not start properly.
+
+- Fixed `STTService`. Add `max_silence_secs` and `max_buffer_secs` to handle
+  better what's being passed to the STT service. Also add exponential smoothing
+  to the RMS.
+
+- Fixed `WhisperSTTService`. Add `no_speech_prob` to avoid garbage output text.
+
+## [0.0.12] - 2024-05-14
+
+### Added
+
+- Added `DailyTranscriptionSettings` to be able to specify transcription
+  settings much easier (e.g. language).
+
+### Other
+
+- Updated `simple-chatbot` with Spanish.
+
+- Add missing dependencies in some of the examples.
+
+## [0.0.11] - 2024-05-13
+
+### Added
+
+- Allow stopping pipeline tasks with new `StopTaskFrame`.
+
+### Changed
+
+- TTS, STT and image generation service now use `AsyncGenerator`.
+
+### Fixed
+
+- `DailyTransport`: allow registering for participant transcriptions even if
+  input transport is not initialized yet.
+
+### Other
+
+- Updated `storytelling-chatbot`.
+
+## [0.0.10] - 2024-05-13
+
+### Added
+
+- Added Intel GPU support to `MoondreamService`.
+
+- Added support for sending transport messages (e.g. to communicate with an app
+  at the other end of the transport).
+
+- Added `FrameProcessor.push_error()` to easily send an `ErrorFrame` upstream.
+
+### Fixed
+
+- Fixed Azure services (TTS and image generation).
+
+### Other
+
+- Updated `simple-chatbot`, `moondream-chatbot` and `translation-chatbot`
+  examples.
+
+## [0.0.9] - 2024-05-12
+
+### Changed
+
+Many things have changed in this version. Many of the main ideas such as frames,
+processors, services and transports are still there but some things have changed
+a bit.
+
+- `Frame`s describe the basic units for processing. For example, text, image or
+  audio frames. Or control frames to indicate a user has started or stopped
+  speaking.
+
+- `FrameProcessor`s process frames (e.g. they convert a `TextFrame` to an
+  `ImageRawFrame`) and push new frames downstream or upstream to their linked
+  peers.
+
+- `FrameProcessor`s can be linked together. The easiest wait is to use the
+  `Pipeline` which is a container for processors. Linking processors allow
+  frames to travel upstream or downstream easily.
+
+- `Transport`s are a way to send or receive frames. There can be local
+  transports (e.g. local audio or native apps), network transports
+  (e.g. websocket) or service transports (e.g. https://daily.co).
+
+- `Pipeline`s are just a processor container for other processors.
+
+- A `PipelineTask` know how to run a pipeline.
+
+- A `PipelineRunner` can run one or more tasks and it is also used, for example,
+  to capture Ctrl-C from the user.
+
+## [0.0.8] - 2024-04-11
+
+### Added
+
+- Added `FireworksLLMService`.
+
+- Added `InterimTranscriptionFrame` and enable interim results in
+  `DailyTransport` transcriptions.
+
+### Changed
+
+- `FalImageGenService` now uses new `fal_client` package.
+
+### Fixed
+
+- `FalImageGenService`: use `asyncio.to_thread` to not block main loop when
+  generating images.
+
+- Allow `TranscriptionFrame` after an end frame (transcriptions can be delayed
+  and received after `UserStoppedSpeakingFrame`).
+
+## [0.0.7] - 2024-04-10
+
+### Added
+
+- Add `use_cpu` argument to `MoondreamService`.
+
+## [0.0.6] - 2024-04-10
+
+### Added
+
+- Added `FalImageGenService.InputParams`.
+
+- Added `URLImageFrame` and `UserImageFrame`.
+
+- Added `UserImageRequestFrame` and allow requesting an image from a participant.
+
+- Added base `VisionService` and `MoondreamService`
+
+### Changed
+
+- Don't pass `image_size` to `ImageGenService`, images should have their own size.
+
+- `ImageFrame` now receives a tuple`(width,height)` to specify the size.
+
+- `on_first_other_participant_joined` now gets a participant argument.
+
+### Fixed
+
+- Check if camera, speaker and microphone are enabled before writing to them.
+
+### Performance
+
+- `DailyTransport` only subscribe to desired participant video track.
+
+## [0.0.5] - 2024-04-06
+
+### Changed
+
+- Use `camera_bitrate` and `camera_framerate`.
+
+- Increase `camera_framerate` to 30 by default.
+
+### Fixed
+
+- Fixed `LocalTransport.read_audio_frames`.
+
+## [0.0.4] - 2024-04-04
+
+### Added
+
+- Added project optional dependencies `[silero,openai,...]`.
+
+### Changed
+
+- Moved thransports to its own directory.
+
+- Use `OPENAI_API_KEY` instead of `OPENAI_CHATGPT_API_KEY`.
+
+### Fixed
+
+- Don't write to microphone/speaker if not enabled.
+
+### Other
+
+- Added live translation example.
+
+- Fix foundational examples.
+
+## [0.0.3] - 2024-03-13
+
+### Other
+
+- Added `storybot` and `chatbot` examples.
+
+## [0.0.2] - 2024-03-12
+
+Initial public release.

CHANGELOG.md.template

@@ -0,0 +1,62 @@
+# Changelog
+
+All notable changes to the **<project name>** SDK will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+Please make sure to add your changes to the appropriate categories:
+
+## [Unreleased]
+
+### Added
+
+<!-- for new functionality -->
+
+- n/a
+
+### Changed
+
+<!-- for changed functionality -->
+
+- n/a
+
+### Deprecated
+
+<!-- for soon-to-be removed functionality -->
+
+- n/a
+
+### Removed
+
+<!-- for removed functionality -->
+
+- n/a
+
+### Fixed
+
+<!-- for fixed bugs -->
+
+- n/a
+
+### Performance
+
+<!-- for performance-relevant changes -->
+
+- n/a
+
+### Security
+
+<!-- for security-relevant changes -->
+
+- n/a
+
+### Other
+
+<!-- for everything else -->
+
+- n/a
+
+## [0.1.0] - YYYY-MM-DD
+
+Initial release.

LICENSE

@@ -1,6 +1,6 @@
 BSD 2-Clause License
 
-Copyright (c) 2024, Daily
+Copyright (c) 2024, Kwindla Hultman Kramer
 
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:

README.md

@@ -1,117 +1,164 @@
-# dailyai — an open source framework for real-time, multi-modal, conversational AI applications
+<div align="center">
+ <img alt="pipecat" width="300px" height="auto" src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/pipecat.png">
+</div>
 
-Build things like this:
+# Pipecat
 
-[![AI-powered voice patient intake for healthcare](https://img.youtube.com/vi/lDevgsp9vn0/0.jpg)](https://www.youtube.com/watch?v=lDevgsp9vn0)
+[![PyPI](https://img.shields.io/pypi/v/pipecat-ai)](https://pypi.org/project/pipecat-ai) [![Discord](https://img.shields.io/discord/1239284677165056021
+)](https://discord.gg/pipecat)
 
-**`dailyai` started as a toolkit for implementing generative AI voice bots.** Things like personal coaches, meeting assistants, story-telling toys for kids, customer support bots, and snarky social companions.
+`pipecat` is a framework for building voice (and multimodal) conversational agents. Things like personal coaches, meeting assistants, [story-telling toys for kids](https://storytelling-chatbot.fly.dev/), customer support bots, [intake flows](https://www.youtube.com/watch?v=lDevgsp9vn0), and snarky social companions.
 
-In 2023 a *lot* of us got excited about the possibility of having open-ended conversations with LLMs. It became clear pretty quickly that we were all solving the same [low-level problems](https://www.daily.co/blog/how-to-talk-to-an-llm-with-your-voice/):
-- low-latency, reliable audio transport
-- echo cancellation
-- phrase endpointing (knowing when the bot should respond to human speech)
-- interruptibility
-- writing clean code to stream data through "pipelines" of speech-to-text, LLM inference, and text-to-speech models
+Take a look at some example apps:
 
-As our applications expanded to include additional things like image generation, function calling, and vision models, we started to think about what a complete framework for these kinds of apps could look like.
+<p float="left">
+    <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/simple-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/simple-chatbot/image.png" width="280" /></a>&nbsp;
+    <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/storytelling-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/storytelling-chatbot/image.png" width="280" /></a>
+    <br/>
+    <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/translation-chatbot/image.png" width="280" /></a>&nbsp;
+    <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/moondream-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/moondream-chatbot/image.png" width="280" /></a>
+</p>
 
-Today, `dailyai` is:
+## Getting started with voice agents
 
-1. a set of code building blocks for interacting with generative AI services and creating low-latency, interruptible data pipelines that use multiple services
-2. transport services that moves audio, video, and events across the Internet
-3. implementations of specific generative AI services
+You can get started with Pipecat running on your local machine, then move your agent processes to the cloud when you’re ready. You can also add a 📞 telephone number, 🖼️ image output, 📺 video input, use different LLMs, and more.
 
-Currently implemented services:
-- Speech-to-text
-  - Deepgram
-  - Whisper
-- LLMs
-  - Azure
-  - OpenAI
-- Image generation
-  - Azure
-  - Fal
-  - OpenAI
-- Text-to-speech
-  - Azure
-  - Deepgram
-  - ElevenLabs
-- Transport
-  - Daily
-  - Local (in progress, intended as a quick start example service)
-- Vision
-  - Moondream
-
-If you'd like to [implement a service]((https://github.com/daily-co/daily-ai-sdk/tree/main/src/dailyai/services)), we welcome PRs! Our goal is to support lots of services in all of the above categories, plus new categories (like real-time video) as they emerge.
-
-## Getting started
-
-Today, the easiest way to get started with `dailyai` is to use [Daily](https://www.daily.co/) as your transport service. This toolkit started life as an internal SDK at Daily and millions of minutes of AI conversation have been served using it and its earlier prototype incarnations. (The [transport base class](https://github.com/daily-co/daily-ai-sdk/blob/main/src/dailyai/transports/abstract_transport.py) is easy to extend, though, so feel free to submit PRs if you'd like to implement another transport service.)
-
-```
+```shell
 # install the module
-pip install dailyai
+pip install pipecat-ai
 
 # set up an .env file with API keys
 cp dot-env.template .env
 ```
 
-By default, in order to minimize dependencies, only the basic framework functionality is available. Some third-party AI services require additional
-dependencies that you can install with:
+By default, in order to minimize dependencies, only the basic framework functionality is available. Some third-party AI services require additional dependencies that you can install with:
 
-```
-pip install "dailyai[option,...]"
+```shell
+pip install "pipecat-ai[option,...]"
 ```
 
 Your project may or may not need these, so they're made available as optional requirements. Here is a list:
 
 - **AI services**: `anthropic`, `azure`, `fal`, `moondream`, `openai`, `playht`, `silero`, `whisper`
-- **Transports**: `daily`, `local`, `websocket`
+- **Transports**: `local`, `websocket`, `daily`
 
 ## Code examples
 
-There are two directories of examples:
+- [foundational](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational) — small snippets that build on each other, introducing one or two concepts at a time
+- [example apps](https://github.com/pipecat-ai/pipecat/tree/main/examples/) — complete applications that you can use as starting points for development
 
-- [foundational](https://github.com/daily-co/daily-ai-sdk/tree/main/examples/foundational) — demos that build on each other, introducing one or two concepts at a time
-- [starter apps](https://github.com/daily-co/daily-ai-sdk/tree/main/examples/starter-apps) — complete applications that you can use as starting points for development
+## A simple voice agent running locally
 
-Before running the examples you need to install the dependencies (which will install all the dependencies to run all of the examples):
+Here is a very basic Pipecat bot that greets a user when they join a real-time session. We'll use [Daily](https://daily.co) for real-time media transport, and [ElevenLabs](https://elevenlabs.io/) for text-to-speech.
 
-```
-pip install -r {env}-requirements.txt
+```python
+#app.py
+
+import asyncio
+import aiohttp
+
+from pipecat.frames.frames import EndFrame, TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.task import PipelineTask
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+async def main():
+  async with aiohttp.ClientSession() as session:
+    # Use Daily as a real-time media transport (WebRTC)
+    transport = DailyTransport(
+      room_url=...,
+      token=...,
+      "Bot Name",
+      DailyParams(audio_out_enabled=True))
+
+    # Use Eleven Labs for Text-to-Speech
+    tts = ElevenLabsTTSService(
+      aiohttp_session=session,
+      api_key=...,
+      voice_id=...,
+      )
+
+    # Simple pipeline that will process text to speech and output the result
+    pipeline = Pipeline([tts, transport.output()])
+
+    # Create Pipecat processor that can run one or more pipelines tasks
+    runner = PipelineRunner()
+
+    # Assign the task callable to run the pipeline
+    task = PipelineTask(pipeline)
+
+    # Register an event handler to play audio when a
+    # participant joins the transport WebRTC session
+    @transport.event_handler("on_participant_joined")
+    async def on_new_participant_joined(transport, participant):
+      participant_name = participant["info"]["userName"] or ''
+      # Queue a TextFrame that will get spoken by the TTS service (Eleven Labs)
+      await task.queue_frames([TextFrame(f"Hello there, {participant_name}!"), EndFrame()])
+
+    # Run the pipeline task
+    await runner.run(task)
+
+if __name__ == "__main__":
+  asyncio.run(main())
 ```
 
-To run the example below you need to sign up for a [free Daily account](https://dashboard.daily.co/u/signup) and create a Daily room (so you can hear the LLM talking). After that, join the room's URL directly from a browser tab and run:
+Run it with:
 
+```shell
+python app.py
 ```
-python examples/foundational/02-llm-say-one-thing.py
+
+Daily provides a prebuilt WebRTC user interface. Whilst the app is running, you can visit at `https://<yourdomain>.daily.co/<room_url>` and listen to the bot say hello!
+
+
+## WebRTC for production use
+
+WebSockets are fine for server-to-server communication or for initial development. But for production use, you’ll need client-server audio to use a protocol designed for real-time media transport. (For an explanation of the difference between WebSockets and WebRTC, see [this post.](https://www.daily.co/blog/how-to-talk-to-an-llm-with-your-voice/#webrtc))
+
+One way to get up and running quickly with WebRTC is to sign up for a Daily developer account. Daily gives you SDKs and global infrastructure for audio (and video) routing. Every account gets 10,000 audio/video/transcription minutes free each month.
+
+Sign up [here](https://dashboard.daily.co/u/signup) and [create a room](https://docs.daily.co/reference/rest-api/rooms) in the developer Dashboard.
+
+## What is VAD?
+
+Voice Activity Detection &mdash; very important for knowing when a user has finished speaking to your bot. If you are not using press-to-talk, and want Pipecat to detect when the user has finished talking, VAD is an essential component for a natural feeling conversation.
+
+Pipecast makes use of WebRTC VAD by default when using a WebRTC transport layer. Optionally, you can use Silero VAD for improved accuracy at the cost of higher CPU usage.
+
+```shell
+pip install pipecat-ai[silero]
 ```
 
+The first time your run your bot with Silero, startup may take a while whilst it downloads and caches the model in the background. You can check the progress of this in the console.
+
+
 ## Hacking on the framework itself
 
 _Note that you may need to set up a virtual environment before following the instructions below. For instance, you might need to run the following from the root of the repo:_
 
-```
+```shell
 python3 -m venv venv
 source venv/bin/activate
 ```
 
 From the root of this repo, run the following:
 
-```
-pip install -r {env}-requirements.txt -r dev-requirements.txt
+```shell
+pip install -r dev-requirements.txt -r {env}-requirements.txt
 python -m build
 ```
 
 This builds the package. To use the package locally (eg to run sample files), run
 
-```
+```shell
 pip install --editable .
 ```
 
 If you want to use this package from another directory, you can run:
 
-```
+```shell
 pip install path_to_this_repo
 ```
 
@@ -119,7 +166,7 @@ pip install path_to_this_repo
 
 From the root directory, run:
 
-```
+```shell
 pytest --doctest-modules --ignore-glob="*to_be_updated*" src tests
 ```
 
@@ -166,3 +213,9 @@ Install the
     "--max-line-length=100"
 ],
 ```
+
+## Getting help
+
+➡️ [Join our Discord](https://discord.gg/pipecat)
+
+➡️ [Reach us on X](https://x.com/pipecat_ai)

dev-requirements.txt

@@ -1,6 +1,6 @@
-autopep8==2.0.4
-build==1.0.3
-pip-tools==7.4.1
-pytest==8.1.1
-setuptools==69.2.0
-setuptools_scm==8.0.4
+autopep8~=2.1.0
+build~=1.2.1
+pip-tools~=7.4.1
+pytest~=8.2.0
+setuptools~=69.5.1
+setuptools_scm~=8.1.0

docs/README.md

@@ -1,17 +1,10 @@
-# Daily AI SDK Docs
+# Pipecat Docs
 
 ## [Architecture Overview](architecture.md)
 
-Learn about the thinking behind the SDK's design.
+Learn about the thinking behind the framework's design.
 
 ## [A Frame's Progress](frame-progress.md)
 
 See how a Frame is processed through a Transport, a Pipeline, and a series of Frame Processors.
 
-## [Example Code](examples/)
-
-The repo includes several example apps in the `examples` directory. The docs explain how they work.
-
-## [API Reference](api/)
-
-Complete documentation of the available classes and methods in the SDK.

docs/architecture.md

@@ -1,4 +1,4 @@
-# Daily AI SDK Architecture Guide
+# Pipecat architecture guide
 
 ## Frames
 
@@ -10,8 +10,8 @@ Frame processors operate on frames. Every frame processor implements a `process_
 
 ## Pipelines
 
-Pipelines are lists of frame processors that read from a source queue and send the processed frames to a sink queue. A very simple pipeline might chain an LLM frame processor to a text-to-speech frame processor, with a transport's send queue as its sync. Placing LLM message frames on the pipeline's source queue will cause the LLM's response to be spoken. See example #2 for an implementation of this.
+Pipelines are lists of frame processors linked together. Frame processors can push frames upstream or downstream to their peers. A very simple pipeline might chain an LLM frame processor to a text-to-speech frame processor, with a transport as an output.
 
 ## Transports
 
-Transports provide a receive queue, which is input from "the outside world", and a sink queue, which is data that will be sent "to the outside world". The `LocalTransportService` does this with the local camera, mic, display and speaker. The `DailyTransportService` does this with a WebRTC session joined to a Daily.co room.
+Transports provide input and output frame processors to receive or send frames respectively. For example, the `DailyTransport` does this with a WebRTC session joined to a Daily.co room.

docs/examples/01-say-one-thing.md

@@ -1,119 +0,0 @@
-# 01: Say One Thing
-
-_video here - youtube?_
-
-This example uses a text-to-speech (TTS) service to say one predefined sentence. But first, a quick overview of the general structure of these examples.
-
-## Running the demos
-
-All of the demos have something like this at the bottom of the file:
-
-```python
-if __name__ == "__main__":
-    (url, token) = configure()
-    asyncio.run(main(url, token))
-```
-
-### `configure()`
-
-The `configure()` function comes from `examples/foundational/support/runner.py`, and it allows you to configure the examples from the command line directly, or using environment variables:
-
-```bash
-python 01-say-one-thing.py -u https://YOUR_DOMAIN.daily.co/YOUR_ROOM -k YOUR_API_KEY
-# or
-DAILY_ROOM_URL=https://YOUR_DOMAIN.daily.co/YOUR_ROOM DAILY_API_KEY=YOUR_API_KEY python 01-say-one-thing.py
-# or set DAILY_ROOM_URL and DAILY_API_KEY in a .env file
-python 01-say-one-thing.py
-```
-
-You'll need a Daily account to run these demos. You can sign up for free at [daily.co](https://daily.co). Once you've signed up you can create a room from the [Dashboard](https://dashboard.daily.co/rooms), and grab [your API key](https://dashboard.daily.co/developers) while you're there.
-
-Some functionality (such as transcription) requires the bot to have owner privileges in the room. `runner.py` uses the Daily REST API to create a meeting token with owner privileges. You can learn more about meeting tokens in the [Daily docs](https://docs.daily.co/reference/rest-api/meeting-tokens).
-
-### `asyncio.run()`
-
-The AI SDK makes heavy use of Python's `asyncio` module. [This is a reasonable intro to the topic](https://builtin.com/data-science/asyncio) if you haven't worked with `asyncio` and coroutines before.
-
-You can learn a bit more about the specifics of how the Daily AI SDK uses coroutines in the [Architecture Guide](../architecture.md).
-
-## The `main()` function
-
-All of the examples have a `main()` function with a similar structure:
-
-- Configure the transport
-- Configure the AI service(s) used in the demo
-- Configure any event listeners
-- Define a processing pipeline
-- Run the example's coroutine(s)
-
-### Configuring the transport
-
-The first section of the `main()` function configures the transport object:
-
-```python
-meeting_duration_minutes = 5
-transport = DailyTransportService(
-    room_url,
-    None,
-    "Say One Thing",
-    meeting_duration_minutes,
-)
-transport.mic_enabled = True
-```
-
-The [Architecture Guide](../architecture.md) explains the transport object in more detail. In this case, we're configuring a Daily transport object and enabling the virtual microphone, so our bot can play audio.
-
-### Configuring the services
-
-As described in the [Architecture Guide](../architecture.md), 'a 'Service' is a class that processes 'Frames' as part of a 'Pipeline'. In this demo app, we'll only need one service: a text-to-speech generator. We can create an instance of the `ElevenLabsTTSService` class with this line of code:
-
-```python
-tts = ElevenLabsTTSService(aiohttp_session=session, api_key=os.getenv("ELEVENLABS_API_KEY"), voice_id=os.getenv("ELEVENLABS_VOICE_ID"))
-```
-
-You'll need to make sure and set those environment variables somewhere. The easiest way to do that is to copy the `example.env` file in the repo and rename it to `.env`, and then add your credentials to that file. `runner.py` loads the `python-dotenv` module and initializes it, making the values in that file available in the environment.
-
-### Configuring event listeners
-
-This part isn't strictly necessary for an app like this. You could include the contents of the `on_participant_joined` function directly in the body of the `main()` function, and it would run as soon as you started the script from the command line.
-
-Instead, we can use an event handler to wait to run that code until someone else joins the meeting. We'll define a function called `greet_user()`, and use the `@transport.event_handler("on_participant_joined")` decorator to tell the SDK that we want to run that function whenever a user joins the room.
-
-```python
-@transport.event_handler("on_participant_joined")
-async def greet_user(transport, participant):
-    if participant["info"]["isLocal"]:
-        return
-
-    await tts.say(
-        "Hello there, " + participant["info"]["userName"] + "!",
-        transport.send_queue,
-    )
-
-    # wait for the output queue to be empty, then leave the meeting
-    await transport.stop_when_done()
-```
-
-### Defining a processing pipeline
-
-In this example, we don't actually have much of a processing pipeline! In fact, we're doing the whole thing inside the `greet_user()` function already.
-
-Pipelines usually look like a bunch of nested calls to the `run()` or `run_to_queue()` function from different Services. In this example, we're using the `say()` function from the TTS service. This is effectively a convenience wrapper around the `run_to_queue()` function, which we'll discuss more later. It's important to `await` this function to ensure that the speech frames are queued for playback before the next line of code, because of the `stop_when_done()` function being called immediately afterward.
-
-The output of the `say()` function goes to the transport's `send_queue`. This queue is the all-important connection between the world of the Services pipeline that's generating frames asynchronously and the ordered playback of audio and visual media in the WebRTC call.
-
-### Running the coroutines
-
-In this example, we don't actually have any separate processing pipelines—everything happens as a result of an event from the transport. So we only need to run the transport's coroutine, and await its completion:
-
-```python
-await transport.run()
-```
-
-In future examples, we'll run more processes in parallel. For now, this script can run until the transport exits—which will happen based on calling `stop_when_done()` in the `greet_user()` function.
-
-## Next Steps
-
-Next, we'll start connecting multiple AI services together by building a service pipeline.
-
-## [02 - LLM Say One Thing »](02-llm-say-one-thing.md)

docs/examples/README.md

@@ -1,5 +0,0 @@
-# Daily AI SDK Examples
-
-The docs in this folder pair with the example apps located in `examples/foundational`. They are designed to serve as a quick references for building different kinds of AI apps. But the examples also build on one another, so it can be really helpful to walk through them in order.
-
-To start, you can learn about the overall structure of the examples in [01 - Say One Thing](01-say-one-thing.md).

dot-env.template

@@ -22,8 +22,10 @@ ELEVENLABS_API_KEY=...
 ELEVENLABS_VOICE_ID=...
 
 # Fal
-FAL_KEY_ID=...
-FAL_KEY_SECRET=...
+FAL_KEY=...
+
+# Fireworks
+FIREWORKS_API_KEY=...
 
 # PlayHT
 PLAY_HT_USER_ID=...

examples/README.md

@@ -0,0 +1,84 @@
+
+
+# Pipecat — Examples
+
+## Foundational snippets
+Small snippets that build on each other, introducing one or two concepts at a time.
+
+➡️ [Take a look](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational)
+
+## Chatbot examples
+Collection of self-contained real-time voice and video AI demo applications built with Pipecat.
+
+### Quickstart
+
+Each project has its own set of dependencies and configuration variables. They intentionally avoids shared code across projects — you can grab whichever demo folder you want to work with as a starting point.
+
+We recommend you start with a virtual environment:
+
+```shell
+cd pipecat-ai/examples/simple-chatbot
+
+python -m venv venv
+
+source venv/bin/activate
+
+pip install -r requirements.txt
+```
+
+Next, follow the steps in the README for each demo.
+
+ℹ️ Make sure you `pip install -r requirements.txt` for each demo project, so you can be sure to have the necessary service dependencies that extend the functionality of Pipecat. You can read more about the framework architecture [here](https://github.com/pipecat-ai/pipecat/tree/main/docs).
+
+## Projects:
+
+| Project                                      | Description                                                                                                                                | Services                                       |
+| -------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------- |
+| [Simple Chatbot](simple-chatbot)             | Basic voice-driven conversational bot. A good starting point for learning the flow of the framework.                                       | Deepgram, OpenAI, Daily, Daily Prebuilt UI            |
+| [Storytelling Chatbot](storytelling-chatbot) | Stitches together multiple third-party services to create a collaborative storytime experience.                                            | Deepgram, ElevenLabs, Open AI, Fal, Daily, Custom UI  |
+| [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, OpenAI, Moondream, Daily, Daily Prebuilt UI |
+| Function-calling Chatbot (TBC)               | A chatbot that can call functions in response to user input                                                                                | Deepgram, OpenAI, Fireworks, Daily, Daily Prebuilt UI |
+
+> [!IMPORTANT]
+> These example projects use Daily as a WebRTC transport and can be joined using their hosted Prebuilt UI.
+> It provides a quick way to join a real-time session with your bot and test your ideas without building any frontend code. If you'd like to see an example of a custom UI, try Storybot.
+
+
+## FAQ
+
+### Deployment
+
+For each of these demos we've included a `Dockerfile`. Out of the box, this should provide everything needed to get the respective demo running on a VM:
+
+```shell
+docker build username/app:tag .
+
+docker run -p 7860:7860 --env-file ./.env username/app:tag
+
+docker push ...
+```
+
+### SSL
+
+If you're working with a custom UI (such as with the Storytelling Chatbot), it's important to ensure your deployment platform supports HTTPS, as accessing user devices such as mics and webcams requires SSL.
+
+If you try to run a custom UI without SSL, you may see an error in the console telling you that `navigator` is undefined, or no devices are available.
+
+### Are these examples production ready?
+
+Yes, kind of.
+
+These demos attempt to keep things simple and are unopinionated regarding environment or scalability.
+
+We're using FastAPI to spawn a subprocess for the bots / agents — useful for small tests, but not so great for production grade apps with many concurrent users. You can see how this works in each project's `start` endpoint in `server.py`.
+
+Creating virtualized worker pools and on-demand instances is out of scope for these examples, but we hope to add some examples to this repo soon!
+
+For projects that have CUDA as a requirement, such as Moondream Chatbot, be sure to deploy to a GPU-powered platform (such as [fly.io](https://fly.io) or [Runpod](https://runpod.io).)
+
+## Getting help
+
+➡️ [Join our Discord](https://discord.gg/pipecat)
+
+➡️ [Reach us on Twitter](https://x.com/pipecat_ai)

examples/foundational/01-say-one-thing.py

@@ -1,31 +1,36 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
 import asyncio
 import aiohttp
-import logging
 import os
-from dailyai.pipeline.frames import EndFrame, TextFrame
-from dailyai.pipeline.pipeline import Pipeline
+import sys
 
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
+from pipecat.frames.frames import EndFrame, TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.task import PipelineTask
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 from runner import configure
 
+from loguru import logger
+
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
 
 
 async def main(room_url):
     async with aiohttp.ClientSession() as session:
         transport = DailyTransport(
-            room_url,
-            None,
-            "Say One Thing",
-            mic_enabled=True,
-        )
+            room_url, None, "Say One Thing", DailyParams(audio_out_enabled=True))
 
         tts = ElevenLabsTTSService(
             aiohttp_session=session,
@@ -33,21 +38,18 @@ async def main(room_url):
             voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
         )
 
-        pipeline = Pipeline([tts])
+        runner = PipelineRunner()
+
+        task = PipelineTask(Pipeline([tts, transport.output()]))
 
         # Register an event handler so we can play the audio when the
         # participant joins.
         @transport.event_handler("on_participant_joined")
-        async def on_participant_joined(transport, participant):
-            if participant["info"]["isLocal"]:
-                return
-
+        async def on_new_participant_joined(transport, participant):
             participant_name = participant["info"]["userName"] or ''
-            await pipeline.queue_frames([TextFrame("Hello there, " + participant_name + "!"), EndFrame()])
-
-        await transport.run(pipeline)
-        del tts
+            await task.queue_frames([TextFrame(f"Hello there, {participant_name}!"), EndFrame()])
 
+        await runner.run(task)
 
 if __name__ == "__main__":
     (url, token) = configure()

examples/foundational/01a-local-audio.py

@@ -0,0 +1,53 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import EndFrame, TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.local.audio import LocalAudioTransport
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        transport = LocalAudioTransport(TransportParams(audio_out_enabled=True))
+
+        tts = ElevenLabsTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
+        )
+
+        pipeline = Pipeline([tts, transport.output()])
+
+        task = PipelineTask(pipeline)
+
+        async def say_something():
+            await asyncio.sleep(1)
+            await task.queue_frames([TextFrame("Hello there!"), EndFrame()])
+
+        runner = PipelineRunner()
+
+        await asyncio.gather(runner.run(task), say_something())
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/01a-local-transport.py

@@ -1,38 +0,0 @@
-import asyncio
-import aiohttp
-import logging
-import os
-
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
-from dailyai.transports.local_transport import LocalTransport
-
-from dotenv import load_dotenv
-load_dotenv(override=True)
-
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        meeting_duration_minutes = 1
-        transport = LocalTransport(
-            duration_minutes=meeting_duration_minutes, mic_enabled=True
-        )
-        tts = ElevenLabsTTSService(
-            aiohttp_session=session,
-            api_key=os.getenv("ELEVENLABS_API_KEY"),
-            voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
-        )
-
-        async def say_something():
-            await asyncio.sleep(1)
-            await transport.say("Hello there.", tts)
-            await transport.stop_when_done()
-
-        await asyncio.gather(transport.run(), say_something())
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

examples/foundational/02-llm-say-one-thing.py

@@ -1,23 +1,31 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
 import asyncio
-import os
-import logging
-
 import aiohttp
+import os
+import sys
 
-from dailyai.pipeline.frames import EndFrame, LLMMessagesFrame
-from dailyai.pipeline.pipeline import Pipeline
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
-from dailyai.services.open_ai_services import OpenAILLMService
+from pipecat.frames.frames import EndFrame, LLMMessagesFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 from runner import configure
 
+from loguru import logger
+
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
 
 
 async def main(room_url):
@@ -26,8 +34,7 @@ async def main(room_url):
             room_url,
             None,
             "Say One Thing From an LLM",
-            mic_enabled=True,
-        )
+            DailyParams(audio_out_enabled=True))
 
         tts = ElevenLabsTTSService(
             aiohttp_session=session,
@@ -45,13 +52,15 @@ async def main(room_url):
                 "content": "You are an LLM in a WebRTC session, and this is a 'hello world' demo. Say hello to the world.",
             }]
 
-        pipeline = Pipeline([llm, tts])
+        runner = PipelineRunner()
 
-        @transport.event_handler("on_first_other_participant_joined")
-        async def on_first_other_participant_joined(transport, participant):
-            await pipeline.queue_frames([LLMMessagesFrame(messages), EndFrame()])
+        task = PipelineTask(Pipeline([llm, tts, transport.output()]))
 
-        await transport.run(pipeline)
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await task.queue_frames([LLMMessagesFrame(messages), EndFrame()])
+
+        await runner.run(task)
 
 
 if __name__ == "__main__":

examples/foundational/03-still-frame.py

@@ -1,21 +1,30 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
 import asyncio
 import aiohttp
-import logging
 import os
+import sys
 
-from dailyai.pipeline.frames import TextFrame
-from dailyai.pipeline.pipeline import Pipeline
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.fal_ai_services import FalImageGenService
+from pipecat.frames.frames import TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.services.fal import FalImageGenService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 from runner import configure
 
+from loguru import logger
+
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
 
 
 async def main(room_url):
@@ -24,10 +33,11 @@ async def main(room_url):
             room_url,
             None,
             "Show a still frame image",
-            camera_enabled=True,
-            camera_width=1024,
-            camera_height=1024,
-            duration_minutes=1
+            DailyParams(
+                camera_out_enabled=True,
+                camera_out_width=1024,
+                camera_out_height=1024
+            )
         )
 
         imagegen = FalImageGenService(
@@ -35,23 +45,22 @@ async def main(room_url):
                 image_size="square_hd"
             ),
             aiohttp_session=session,
-            key_id=os.getenv("FAL_KEY_ID"),
-            key_secret=os.getenv("FAL_KEY_SECRET"),
+            key=os.getenv("FAL_KEY"),
         )
 
-        pipeline = Pipeline([imagegen])
+        runner = PipelineRunner()
 
-        @transport.event_handler("on_first_other_participant_joined")
-        async def on_first_other_participant_joined(transport, participant):
+        task = PipelineTask(Pipeline([imagegen, transport.output()]))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
             # Note that we do not put an EndFrame() item in the pipeline for this demo.
             # This means that the bot will stay in the channel until it times out.
             # An EndFrame() in the pipeline would cause the transport to shut
             # down.
-            await pipeline.queue_frames(
-                [TextFrame("a cat in the style of picasso")]
-            )
+            await task.queue_frames([TextFrame("a cat in the style of picasso")])
 
-        await transport.run(pipeline)
+        await runner.run(task)
 
 
 if __name__ == "__main__":

examples/foundational/03a-image-local.py

@@ -1,59 +0,0 @@
-import asyncio
-import aiohttp
-import logging
-import os
-
-import tkinter as tk
-
-from dailyai.pipeline.frames import TextFrame
-from dailyai.pipeline.pipeline import Pipeline
-from dailyai.services.fal_ai_services import FalImageGenService
-from dailyai.transports.local_transport import LocalTransport
-
-from dotenv import load_dotenv
-load_dotenv(override=True)
-
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        meeting_duration_minutes = 2
-
-        tk_root = tk.Tk()
-        tk_root.title("dailyai")
-
-        transport = LocalTransport(
-            tk_root=tk_root,
-            mic_enabled=False,
-            camera_enabled=True,
-            camera_width=1024,
-            camera_height=1024,
-            duration_minutes=meeting_duration_minutes,
-        )
-
-        imagegen = FalImageGenService(
-            params=FalImageGenService.InputParams(
-                image_size="square_hd"
-            ),
-            aiohttp_session=session,
-            key_id=os.getenv("FAL_KEY_ID"),
-            key_secret=os.getenv("FAL_KEY_SECRET"),
-        )
-
-        pipeline = Pipeline([imagegen])
-        await pipeline.queue_frames([TextFrame("a cat in the style of picasso")])
-
-        async def run_tk():
-            while not transport._stop_threads.is_set():
-                tk_root.update()
-                tk_root.update_idletasks()
-                await asyncio.sleep(0.1)
-
-        await asyncio.gather(transport.run(pipeline, override_pipeline_source_queue=False), run_tk())
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

examples/foundational/03a-local-still-frame.py

@@ -0,0 +1,68 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+import tkinter as tk
+
+from pipecat.frames.frames import TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.services.fal import FalImageGenService
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.local.tk import TkLocalTransport
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        tk_root = tk.Tk()
+        tk_root.title("Picasso Cat")
+
+        transport = TkLocalTransport(
+            tk_root,
+            TransportParams(
+                camera_out_enabled=True,
+                camera_out_width=1024,
+                camera_out_height=1024))
+
+        imagegen = FalImageGenService(
+            params=FalImageGenService.InputParams(
+                image_size="square_hd"
+            ),
+            aiohttp_session=session,
+            key=os.getenv("FAL_KEY"),
+        )
+
+        pipeline = Pipeline([imagegen, transport.output()])
+
+        task = PipelineTask(pipeline)
+        await task.queue_frames([TextFrame("a cat in the style of picasso")])
+
+        runner = PipelineRunner()
+
+        async def run_tk():
+            while runner.is_active():
+                tk_root.update()
+                tk_root.update_idletasks()
+                await asyncio.sleep(0.1)
+
+        await asyncio.gather(runner.run(task), run_tk())
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/04-utterance-and-speech.py

@@ -1,37 +1,40 @@
-import asyncio
-import logging
-import os
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
 
 import aiohttp
-from dailyai.pipeline.merge_pipeline import SequentialMergePipeline
-from dailyai.pipeline.pipeline import Pipeline
+import asyncio
+import os
+import sys
 
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
-from dailyai.services.deepgram_ai_services import DeepgramTTSService
-from dailyai.pipeline.frames import EndPipeFrame, LLMMessagesFrame, TextFrame
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
+from pipecat.pipeline.merge_pipeline import SequentialMergePipeline
+from pipecat.pipeline.pipeline import Pipeline
+
+from pipecat.frames.frames import EndPipeFrame, LLMMessagesFrame, TextFrame
+from pipecat.pipeline.task import PipelineTask
+from pipecat.services.azure import AzureLLMService, AzureTTSService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.transport_services import TransportServiceOutput
+from pipecat.services.transports.daily_transport import DailyTransport
 
 from runner import configure
 
+from loguru import logger
+
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
 
 
 async def main(room_url: str):
     async with aiohttp.ClientSession() as session:
-        transport = DailyTransport(
-            room_url,
-            None,
-            "Static And Dynamic Speech",
-            duration_minutes=1,
-            mic_enabled=True,
-            mic_sample_rate=16000,
-        )
+        transport = DailyTransport(room_url, None, "Static And Dynamic Speech")
+
+        meeting = TransportServiceOutput(transport, mic_enabled=True)
 
         llm = AzureLLMService(
             api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
@@ -43,10 +46,6 @@ async def main(room_url: str):
             region=os.getenv("AZURE_SPEECH_REGION"),
         )
 
-        deepgram_tts = DeepgramTTSService(
-            aiohttp_session=session,
-            api_key=os.getenv("DEEPGRAM_API_KEY"),
-        )
         elevenlabs_tts = ElevenLabsTTSService(
             aiohttp_session=session,
             api_key=os.getenv("ELEVENLABS_API_KEY"),
@@ -56,11 +55,13 @@ async def main(room_url: str):
         messages = [{"role": "system",
                      "content": "tell the user a joke about llamas"}]
 
-        # Start a task to run the LLM to create a joke, and convert the LLM output to audio frames. This task
-        # will run in parallel with generating and speaking the audio for static text, so there's no delay to
-        # speak the LLM response.
+        # Start a task to run the LLM to create a joke, and convert the LLM
+        # output to audio frames. This task will run in parallel with generating
+        # and speaking the audio for static text, so there's no delay to speak
+        # the LLM response.
         llm_pipeline = Pipeline([llm, elevenlabs_tts])
-        await llm_pipeline.queue_frames([LLMMessagesFrame(messages), EndPipeFrame()])
+        llm_task = PipelineTask(llm_pipeline)
+        await llm_task.queue_frames([LLMMessagesFrame(messages), EndPipeFrame()])
 
         simple_tts_pipeline = Pipeline([azure_tts])
         await simple_tts_pipeline.queue_frames(

examples/foundational/05-sync-speech-and-image.py

@@ -1,64 +1,74 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
 import asyncio
 import aiohttp
 import os
-import logging
+import sys
 
 from dataclasses import dataclass
-from typing import AsyncGenerator
 
-from dailyai.pipeline.aggregators import (
-    GatedAggregator,
-    LLMFullResponseAggregator,
-    ParallelPipeline,
-    SentenceAggregator,
-)
-from dailyai.pipeline.frames import (
+from pipecat.frames.frames import (
+    AppFrame,
     Frame,
+    ImageRawFrame,
     TextFrame,
     EndFrame,
-    ImageFrame,
     LLMMessagesFrame,
     LLMResponseStartFrame,
 )
-from dailyai.pipeline.frame_processor import FrameProcessor
-
-from dailyai.pipeline.pipeline import Pipeline
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.open_ai_services import OpenAILLMService
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
-from dailyai.services.fal_ai_services import FalImageGenService
+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.processors.aggregators.gated import GatedAggregator
+from pipecat.processors.aggregators.llm_response import LLMFullResponseAggregator
+from pipecat.processors.aggregators.sentence import SentenceAggregator
+from pipecat.processors.aggregators.parallel_task import ParallelTask
+from pipecat.services.openai import OpenAILLMService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.fal import FalImageGenService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 from runner import configure
 
+from loguru import logger
+
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
 
 
 @dataclass
-class MonthFrame(Frame):
+class MonthFrame(AppFrame):
     month: str
 
+    def __str__(self):
+        return f"{self.name}(month: {self.month})"
+
 
 class MonthPrepender(FrameProcessor):
     def __init__(self):
+        super().__init__()
         self.most_recent_month = "Placeholder, month frame not yet received"
         self.prepend_to_next_text_frame = False
 
-    async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
         if isinstance(frame, MonthFrame):
             self.most_recent_month = frame.month
         elif self.prepend_to_next_text_frame and isinstance(frame, TextFrame):
-            yield TextFrame(f"{self.most_recent_month}: {frame.text}")
+            await self.push_frame(TextFrame(f"{self.most_recent_month}: {frame.text}"))
             self.prepend_to_next_text_frame = False
         elif isinstance(frame, LLMResponseStartFrame):
             self.prepend_to_next_text_frame = True
-            yield frame
+            await self.push_frame(frame)
         else:
-            yield frame
+            await self.push_frame(frame, direction)
 
 
 async def main(room_url):
@@ -67,11 +77,12 @@ async def main(room_url):
             room_url,
             None,
             "Month Narration Bot",
-            mic_enabled=True,
-            camera_enabled=True,
-            mic_sample_rate=16000,
-            camera_width=1024,
-            camera_height=1024,
+            DailyParams(
+                audio_out_enabled=True,
+                camera_out_enabled=True,
+                camera_out_width=1024,
+                camera_out_height=1024
+            )
         )
 
         tts = ElevenLabsTTSService(
@@ -89,29 +100,29 @@ async def main(room_url):
                 image_size="square_hd"
             ),
             aiohttp_session=session,
-            key_id=os.getenv("FAL_KEY_ID"),
-            key_secret=os.getenv("FAL_KEY_SECRET"),
+            key=os.getenv("FAL_KEY"),
         )
 
         gated_aggregator = GatedAggregator(
-            gate_open_fn=lambda frame: isinstance(
-                frame, ImageFrame), gate_close_fn=lambda frame: isinstance(
-                frame, LLMResponseStartFrame), start_open=False, )
+            gate_open_fn=lambda frame: isinstance(frame, ImageRawFrame),
+            gate_close_fn=lambda frame: isinstance(frame, LLMResponseStartFrame),
+            start_open=False
+        )
 
         sentence_aggregator = SentenceAggregator()
         month_prepender = MonthPrepender()
         llm_full_response_aggregator = LLMFullResponseAggregator()
 
-        pipeline = Pipeline(
-            processors=[
-                llm,
-                sentence_aggregator,
-                ParallelPipeline(
-                    [[month_prepender, tts], [llm_full_response_aggregator, imagegen]]
-                ),
-                gated_aggregator,
-            ],
-        )
+        pipeline = Pipeline([
+            llm,
+            sentence_aggregator,
+            ParallelTask(
+                [month_prepender, tts],
+                [llm_full_response_aggregator, imagegen]
+            ),
+            gated_aggregator,
+            transport.output()
+        ])
 
         frames = []
         for month in [
@@ -134,13 +145,18 @@ async def main(room_url):
                     "content": f"Describe a nature photograph suitable for use in a calendar, for the month of {month}. Include only the image description with no preamble. Limit the description to one sentence, please.",
                 }
             ]
-            frames.append(MonthFrame(month))
+            frames.append(MonthFrame(month=month))
             frames.append(LLMMessagesFrame(messages))
 
         frames.append(EndFrame())
-        await pipeline.queue_frames(frames)
 
-        await transport.run(pipeline, override_pipeline_source_queue=False)
+        runner = PipelineRunner()
+
+        task = PipelineTask(pipeline)
+
+        await task.queue_frames(frames)
+
+        await runner.run(task)
 
 
 if __name__ == "__main__":

examples/foundational/05a-local-sync-speech-and-image.py

@@ -0,0 +1,164 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import os
+import sys
+
+import tkinter as tk
+
+from pipecat.frames.frames import AudioRawFrame, Frame, URLImageRawFrame, LLMMessagesFrame, TextFrame
+from pipecat.pipeline.parallel_pipeline import ParallelPipeline
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.aggregators.llm_response import LLMFullResponseAggregator
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.services.openai import OpenAILLMService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.fal import FalImageGenService
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.local.tk import TkLocalTransport
+
+from loguru import logger
+
+from dotenv import load_dotenv
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        tk_root = tk.Tk()
+        tk_root.title("Calendar")
+
+        runner = PipelineRunner()
+
+        async def get_month_data(month):
+            messages = [{"role": "system", "content": f"Describe a nature photograph suitable for use in a calendar, for the month of {month}. Include only the image description with no preamble. Limit the description to one sentence, please.", }]
+
+            class ImageDescription(FrameProcessor):
+                def __init__(self):
+                    super().__init__()
+                    self.text = ""
+
+                async def process_frame(self, frame: Frame, direction: FrameDirection):
+                    if isinstance(frame, TextFrame):
+                        self.text = frame.text
+                    await self.push_frame(frame, direction)
+
+            class AudioGrabber(FrameProcessor):
+                def __init__(self):
+                    super().__init__()
+                    self.audio = bytearray()
+
+                async def process_frame(self, frame: Frame, direction: FrameDirection):
+                    if isinstance(frame, AudioRawFrame):
+                        self.audio.extend(frame.audio)
+                        self.frame = AudioRawFrame(
+                            bytes(self.audio), frame.sample_rate, frame.num_channels)
+
+            class ImageGrabber(FrameProcessor):
+                def __init__(self):
+                    super().__init__()
+                    self.frame = None
+
+                async def process_frame(self, frame: Frame, direction: FrameDirection):
+                    if isinstance(frame, URLImageRawFrame):
+                        self.frame = frame
+
+            llm = OpenAILLMService(
+                api_key=os.getenv("OPENAI_API_KEY"),
+                model="gpt-4-turbo-preview")
+
+            tts = ElevenLabsTTSService(
+                aiohttp_session=session,
+                api_key=os.getenv("ELEVENLABS_API_KEY"),
+                voice_id=os.getenv("ELEVENLABS_VOICE_ID"))
+
+            imagegen = FalImageGenService(
+                params=FalImageGenService.InputParams(
+                    image_size="square_hd"
+                ),
+                aiohttp_session=session,
+                key=os.getenv("FAL_KEY"))
+
+            aggregator = LLMFullResponseAggregator()
+
+            description = ImageDescription()
+
+            audio_grabber = AudioGrabber()
+
+            image_grabber = ImageGrabber()
+
+            pipeline = Pipeline([llm, aggregator, description,
+                                 ParallelPipeline([tts, audio_grabber],
+                                                  [imagegen, image_grabber])])
+
+            task = PipelineTask(pipeline)
+            await task.queue_frame(LLMMessagesFrame(messages))
+            await task.stop_when_done()
+
+            await runner.run(task)
+
+            return {
+                "month": month,
+                "text": description.text,
+                "image": image_grabber.frame,
+                "audio": audio_grabber.frame,
+            }
+
+        transport = TkLocalTransport(
+            tk_root,
+            TransportParams(
+                audio_out_enabled=True,
+                camera_out_enabled=True,
+                camera_out_width=1024,
+                camera_out_height=1024))
+
+        pipeline = Pipeline([transport.output()])
+
+        task = PipelineTask(pipeline)
+
+        # We only specify 5 months as we create tasks all at once and we might
+        # get rate limited otherwise.
+        months: list[str] = [
+            "January",
+            "February",
+            # "March",
+            # "April",
+            # "May",
+        ]
+
+        # We create one task per month. This will be executed concurrently.
+        month_tasks = [asyncio.create_task(get_month_data(month)) for month in months]
+
+        # Now we wait for each month task in the order they're completed. The
+        # benefit is we'll have as little delay as possible before the first
+        # month, and likely no delay between months, but the months won't
+        # display in order.
+        async def show_images(month_tasks):
+            for month_data_task in asyncio.as_completed(month_tasks):
+                data = await month_data_task
+                await task.queue_frames([data["image"], data["audio"]])
+
+            await runner.stop_when_done()
+
+        async def run_tk():
+            while True:
+                tk_root.update()
+                tk_root.update_idletasks()
+                await asyncio.sleep(0.1)
+
+        await asyncio.gather(runner.run(task), show_images(month_tasks), run_tk())
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/05a-local-sync-speech-and-text.py

@@ -1,147 +0,0 @@
-import aiohttp
-import asyncio
-import logging
-import tkinter as tk
-import os
-from dailyai.pipeline.aggregators import LLMFullResponseAggregator
-
-from dailyai.pipeline.frames import AudioFrame, URLImageFrame, LLMMessagesFrame, TextFrame
-from dailyai.services.open_ai_services import OpenAILLMService
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
-from dailyai.services.fal_ai_services import FalImageGenService
-from dailyai.transports.local_transport import LocalTransport
-
-from dotenv import load_dotenv
-load_dotenv(override=True)
-
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        meeting_duration_minutes = 5
-        tk_root = tk.Tk()
-        tk_root.title("dailyai")
-
-        transport = LocalTransport(
-            mic_enabled=True,
-            camera_enabled=True,
-            camera_width=1024,
-            camera_height=1024,
-            duration_minutes=meeting_duration_minutes,
-            tk_root=tk_root,
-        )
-
-        tts = ElevenLabsTTSService(
-            aiohttp_session=session,
-            api_key=os.getenv("ELEVENLABS_API_KEY"),
-            voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
-        )
-
-        llm = OpenAILLMService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4-turbo-preview")
-
-        imagegen = FalImageGenService(
-            params=FalImageGenService.InputParams(
-                image_size="1024x1024"
-            ),
-            aiohttp_session=session,
-            key_id=os.getenv("FAL_KEY_ID"),
-            key_secret=os.getenv("FAL_KEY_SECRET"),
-        )
-
-        # Get a complete audio chunk from the given text. Splitting this into its own
-        # coroutine lets us ensure proper ordering of the audio chunks on the
-        # send queue.
-        async def get_all_audio(text):
-            all_audio = bytearray()
-            async for audio in tts.run_tts(text):
-                all_audio.extend(audio)
-
-            return all_audio
-
-        async def get_month_description(aggregator, frame):
-            async for frame in aggregator.process_frame(frame):
-                if isinstance(frame, TextFrame):
-                    return frame.text
-
-        async def get_month_data(month):
-            messages = [{"role": "system", "content": f"Describe a nature photograph suitable for use in a calendar, for the month of {month}. Include only the image description with no preamble. Limit the description to one sentence, please.", }]
-
-            messages_frame = LLMMessagesFrame(messages)
-
-            llm_full_response_aggregator = LLMFullResponseAggregator()
-
-            image_description = None
-            async for frame in llm.process_frame(messages_frame):
-                result = await get_month_description(llm_full_response_aggregator, frame)
-                if result:
-                    image_description = result
-                    break
-
-            if not image_description:
-                return
-
-            to_speak = f"{month}: {image_description}"
-            audio_task = asyncio.create_task(get_all_audio(to_speak))
-            image_task = asyncio.create_task(
-                imagegen.run_image_gen(image_description))
-            (audio, image_data) = await asyncio.gather(audio_task, image_task)
-
-            return {
-                "month": month,
-                "text": image_description,
-                "image_url": image_data[0],
-                "image": image_data[1],
-                "image_size": image_data[2],
-                "audio": audio,
-            }
-
-        # We only specify 5 months as we create tasks all at once and we might
-        # get rate limited otherwise.
-        months: list[str] = [
-            "January",
-            "February",
-            "March",
-            "April",
-            "May",
-        ]
-
-        async def show_images():
-            # This will play the months in the order they're completed. The benefit
-            # is we'll have as little delay as possible before the first month, and
-            # likely no delay between months, but the months won't display in
-            # order.
-            for month_data_task in asyncio.as_completed(month_tasks):
-                data = await month_data_task
-                if data:
-                    await transport.send_queue.put(
-                        [
-                            URLImageFrame(data["image_url"], data["image"], data["image_size"]),
-                            AudioFrame(data["audio"]),
-                        ]
-                    )
-
-            await asyncio.sleep(25)
-
-            # wait for the output queue to be empty, then leave the meeting
-            await transport.stop_when_done()
-
-        async def run_tk():
-            while not transport._stop_threads.is_set():
-                tk_root.update()
-                tk_root.update_idletasks()
-                await asyncio.sleep(0.1)
-
-        month_tasks = [
-            asyncio.create_task(
-                get_month_data(month)) for month in months]
-
-        await asyncio.gather(transport.run(), show_images(), run_tk())
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

examples/foundational/06-listen-and-respond.py

@@ -1,26 +1,37 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
 import asyncio
 import aiohttp
-import logging
 import os
-from dailyai.pipeline.frames import LLMMessagesFrame
-from dailyai.pipeline.pipeline import Pipeline
+import sys
 
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
-from dailyai.services.open_ai_services import OpenAILLMService
-from dailyai.services.ai_services import FrameLogger
-from dailyai.pipeline.aggregators import (
-    LLMAssistantContextAggregator,
-    LLMUserContextAggregator,
+from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator,
+    LLMUserResponseAggregator,
 )
+from pipecat.processors.logger import FrameLogger
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVAD
+
 from runner import configure
 
+from loguru import logger
+
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
 
 
 async def main(room_url: str, token):
@@ -29,14 +40,15 @@ async def main(room_url: str, token):
             room_url,
             token,
             "Respond bot",
-            duration_minutes=5,
-            start_transcription=True,
-            mic_enabled=True,
-            mic_sample_rate=16000,
-            camera_enabled=False,
-            vad_enabled=True,
+            DailyParams(
+                audio_in_enabled=True,  # This is so Silero VAD can get audio data
+                audio_out_enabled=True,
+                transcription_enabled=True
+            )
         )
 
+        vad = SileroVAD()
+
         tts = ElevenLabsTTSService(
             aiohttp_session=session,
             api_key=os.getenv("ELEVENLABS_API_KEY"),
@@ -46,41 +58,35 @@ async def main(room_url: str, token):
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             model="gpt-4-turbo-preview")
-        fl = FrameLogger("Inner")
-        fl2 = FrameLogger("Outer")
+
+        fl_in = FrameLogger("Inner")
+        fl_out = FrameLogger("Outer")
+
         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. Respond to what the user said in a creative and helpful way.",
+                "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 it should not contain special characters. Respond to what the user said in a creative and helpful way.",
             },
         ]
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
 
-        tma_in = LLMUserContextAggregator(
-            messages, transport._my_participant_id)
-        tma_out = LLMAssistantContextAggregator(
-            messages, transport._my_participant_id
-        )
-        pipeline = Pipeline(
-            processors=[
-                fl,
-                tma_in,
-                llm,
-                fl2,
-                tts,
-                tma_out,
-            ],
-        )
+        pipeline = Pipeline([fl_in, transport.input(), vad, tma_in, llm,
+                            fl_out, tts, tma_out, transport.output()])
 
-        @transport.event_handler("on_first_other_participant_joined")
-        async def on_first_other_participant_joined(transport, participant):
+        task = PipelineTask(pipeline)
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append(
                 {"role": "system", "content": "Please introduce yourself to the user."})
-            await pipeline.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([LLMMessagesFrame(messages)])
 
-        transport.transcription_settings["extra"]["endpointing"] = True
-        transport.transcription_settings["extra"]["punctuate"] = True
-        await transport.run(pipeline)
+        runner = PipelineRunner()
+
+        await runner.run(task)
 
 
 if __name__ == "__main__":

examples/foundational/06a-image-sync.py

@@ -1,43 +1,59 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
 import asyncio
-import os
-import logging
-from typing import AsyncGenerator
 import aiohttp
+import os
+import sys
+
 from PIL import Image
 
-from dailyai.pipeline.frames import ImageFrame, Frame, TextFrame
-from dailyai.pipeline.pipeline import Pipeline
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.ai_services import AIService
-from dailyai.pipeline.aggregators import (
+from pipecat.frames.frames import ImageRawFrame, Frame, SystemFrame, TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.aggregators.llm_context import (
     LLMAssistantContextAggregator,
     LLMUserContextAggregator,
 )
-from dailyai.services.open_ai_services import OpenAILLMService
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.services.openai import OpenAILLMService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.transports.services.daily import DailyTransport
 
+from pipecat.transports.services.daily import DailyParams
 from runner import configure
 
+from loguru import logger
+
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
 
 
-class ImageSyncAggregator(AIService):
+class ImageSyncAggregator(FrameProcessor):
     def __init__(self, speaking_path: str, waiting_path: str):
+        super().__init__()
         self._speaking_image = Image.open(speaking_path)
+        self._speaking_image_format = self._speaking_image.format
         self._speaking_image_bytes = self._speaking_image.tobytes()
 
         self._waiting_image = Image.open(waiting_path)
+        self._waiting_image_format = self._waiting_image.format
         self._waiting_image_bytes = self._waiting_image.tobytes()
 
-    async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
-        yield ImageFrame(self._speaking_image_bytes, (1024, 1024))
-        yield frame
-        yield ImageFrame(self._waiting_image_bytes, (1024, 1024))
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        if not isinstance(frame, SystemFrame):
+            await self.push_frame(ImageRawFrame(image=self._speaking_image_bytes, size=(1024, 1024), format=self._speaking_image_format))
+            await self.push_frame(frame)
+            await self.push_frame(ImageRawFrame(image=self._waiting_image_bytes, size=(1024, 1024), format=self._waiting_image_format))
+        else:
+            await self.push_frame(frame)
 
 
 async def main(room_url: str, token):
@@ -46,14 +62,13 @@ async def main(room_url: str, token):
             room_url,
             token,
             "Respond bot",
-            5,
+            DailyParams(
+                audio_out_enabled=True,
+                camera_out_width=1024,
+                camera_out_height=1024,
+                transcription_enabled=True
+            )
         )
-        transport._camera_enabled = True
-        transport._camera_width = 1024
-        transport._camera_height = 1024
-        transport._mic_enabled = True
-        transport._mic_sample_rate = 16000
-        transport.transcription_settings["extra"]["punctuate"] = True
 
         tts = ElevenLabsTTSService(
             aiohttp_session=session,
@@ -68,27 +83,32 @@ async def main(room_url: str, token):
         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 it should not include any special characters. Respond to what the user said in a creative and helpful way.",
+                "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 it should not contain special characters. Respond to what the user said in a creative and helpful way.",
             },
         ]
 
-        tma_in = LLMUserContextAggregator(
-            messages, transport._my_participant_id)
-        tma_out = LLMAssistantContextAggregator(
-            messages, transport._my_participant_id
-        )
+        tma_in = LLMUserContextAggregator(messages)
+        tma_out = LLMAssistantContextAggregator(messages)
+
         image_sync_aggregator = ImageSyncAggregator(
             os.path.join(os.path.dirname(__file__), "assets", "speaking.png"),
             os.path.join(os.path.dirname(__file__), "assets", "waiting.png"),
         )
 
-        pipeline = Pipeline([image_sync_aggregator, tma_in, llm, tma_out, tts])
+        pipeline = Pipeline([transport.input(), image_sync_aggregator,
+                            tma_in, llm, tma_out, tts, transport.output()])
 
-        @transport.event_handler("on_first_other_participant_joined")
-        async def on_first_other_participant_joined(transport, participant):
-            await pipeline.queue_frames([TextFrame("Hi, I'm listening!")])
+        task = PipelineTask(pipeline)
 
-        await transport.run(pipeline)
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            participant_name = participant["info"]["userName"] or ''
+            transport.capture_participant_transcription(participant["id"])
+            await task.queue_frames([TextFrame(f"Hi, this is {participant_name}.")])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
 
 
 if __name__ == "__main__":

examples/foundational/07-interruptible.py

@@ -2,16 +2,16 @@ import asyncio
 import aiohttp
 import logging
 import os
-from dailyai.pipeline.aggregators import (
+from pipecat.pipeline.aggregators import (
     LLMAssistantResponseAggregator,
     LLMUserResponseAggregator,
 )
 
-from dailyai.pipeline.pipeline import Pipeline
-from dailyai.services.ai_services import FrameLogger
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.open_ai_services import OpenAILLMService
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.services.ai_services import FrameLogger
+from pipecat.transports.daily_transport import DailyTransport
+from pipecat.services.open_ai_services import OpenAILLMService
+from pipecat.services.elevenlabs_ai_services import ElevenLabsTTSService
 
 from runner import configure
 
@@ -19,7 +19,7 @@ from dotenv import load_dotenv
 load_dotenv(override=True)
 
 logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
+logger = logging.getLogger("pipecat")
 logger.setLevel(logging.DEBUG)
 
 
@@ -67,7 +67,6 @@ async def main(room_url: str, token):
                 pre_processor=LLMUserResponseAggregator(messages),
             )
 
-        transport.transcription_settings["extra"]["punctuate"] = False
         await asyncio.gather(transport.run(), run_conversation())
 
 

examples/foundational/08-bots-arguing.py

@@ -3,14 +3,14 @@ import aiohttp
 import asyncio
 import logging
 import os
-from dailyai.pipeline.aggregators import SentenceAggregator
-from dailyai.pipeline.pipeline import Pipeline
+from pipecat.pipeline.aggregators import SentenceAggregator
+from pipecat.pipeline.pipeline import Pipeline
 
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
-from dailyai.services.fal_ai_services import FalImageGenService
-from dailyai.pipeline.frames import AudioFrame, EndFrame, ImageFrame, LLMMessagesFrame, TextFrame
+from pipecat.transports.daily_transport import DailyTransport
+from pipecat.services.azure_ai_services import AzureLLMService, AzureTTSService
+from pipecat.services.elevenlabs_ai_services import ElevenLabsTTSService
+from pipecat.services.fal_ai_services import FalImageGenService
+from pipecat.pipeline.frames import AudioFrame, EndFrame, ImageFrame, LLMMessagesFrame, TextFrame
 
 from runner import configure
 
@@ -18,7 +18,7 @@ from dotenv import load_dotenv
 load_dotenv(override=True)
 
 logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
+logger = logging.getLogger("pipecat")
 logger.setLevel(logging.DEBUG)
 
 
@@ -55,8 +55,7 @@ async def main(room_url: str):
                 image_size="1024x1024"
             ),
             aiohttp_session=session,
-            key_id=os.getenv("FAL_KEY_ID"),
-            key_secret=os.getenv("FAL_KEY_SECRET"),
+            key=os.getenv("FAL_KEY"),
         )
 
         bot1_messages = [
@@ -93,7 +92,7 @@ async def main(room_url: str):
                 if isinstance(frame, TextFrame):
                     message += frame.text
                 elif isinstance(frame, AudioFrame):
-                    all_audio.extend(frame.data)
+                    all_audio.extend(frame.audio)
 
             return (message, all_audio)
 

examples/foundational/09-mirror.py

@@ -0,0 +1,53 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import sys
+
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.transports.services.daily import DailyTransport, DailyParams
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main(room_url, token):
+    transport = DailyTransport(
+        room_url, token, "Test",
+        DailyParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_out_enabled=True,
+            camera_out_width=1280,
+            camera_out_height=720
+        )
+    )
+
+    @transport.event_handler("on_first_participant_joined")
+    async def on_first_participant_joined(transport, participant):
+        transport.capture_participant_video(participant["id"])
+
+    pipeline = Pipeline([transport.input(), transport.output()])
+
+    runner = PipelineRunner()
+
+    task = PipelineTask(pipeline)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    (url, token) = configure()
+    asyncio.run(main(url, token))

examples/foundational/09a-local-mirror.py

@@ -0,0 +1,65 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import sys
+
+import tkinter as tk
+
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.local.tk import TkLocalTransport
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main(room_url, token):
+    tk_root = tk.Tk()
+    tk_root.title("Local Mirror")
+
+    daily_transport = DailyTransport(room_url, token, "Test", DailyParams(audio_in_enabled=True))
+
+    tk_transport = TkLocalTransport(
+        tk_root,
+        TransportParams(
+            audio_out_enabled=True,
+            camera_out_enabled=True,
+            camera_out_width=1280,
+            camera_out_height=720))
+
+    @daily_transport.event_handler("on_first_participant_joined")
+    async def on_first_participant_joined(transport, participant):
+        transport.capture_participant_video(participant["id"])
+
+    pipeline = Pipeline([daily_transport.input(), tk_transport.output()])
+
+    runner = PipelineRunner()
+
+    async def run_tk():
+        while runner.is_active():
+            tk_root.update()
+            tk_root.update_idletasks()
+            await asyncio.sleep(0.1)
+
+    task = PipelineTask(pipeline)
+
+    await asyncio.gather(runner.run(task), run_tk())
+
+
+if __name__ == "__main__":
+    (url, token) = configure()
+    asyncio.run(main(url, token))

examples/foundational/10-wake-word.py

@@ -1,36 +1,47 @@
-import aiohttp
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
 import asyncio
-import logging
+import aiohttp
 import os
 import random
-from typing import AsyncGenerator
-from PIL import Image
-from dailyai.pipeline.pipeline import Pipeline
+import sys
 
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.open_ai_services import OpenAILLMService
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
-from dailyai.pipeline.aggregators import (
-    LLMUserContextAggregator,
-    LLMAssistantContextAggregator,
-)
-from dailyai.pipeline.frames import (
+from PIL import Image
+
+from pipecat.frames.frames import (
     Frame,
+    SystemFrame,
     TextFrame,
-    ImageFrame,
+    ImageRawFrame,
     SpriteFrame,
     TranscriptionFrame,
 )
-from dailyai.services.ai_services import AIService
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.aggregators.llm_context import (
+    LLMUserContextAggregator,
+    LLMAssistantContextAggregator,
+)
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.services.openai import OpenAILLMService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 from runner import configure
 
+from loguru import logger
+
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
 
 sprites = {}
 image_files = [
@@ -52,14 +63,15 @@ for file in image_files:
     filename = os.path.splitext(os.path.basename(full_path))[0]
     # Open the image and convert it to bytes
     with Image.open(full_path) as img:
-        sprites[file] = img.tobytes()
+        sprites[file] = ImageRawFrame(image=img.tobytes(), size=img.size, format=img.format)
 
 # When the bot isn't talking, show a static image of the cat listening
-quiet_frame = ImageFrame(sprites["sc-listen-1.png"], (720, 1280))
+quiet_frame = sprites["sc-listen-1.png"]
+
 # When the bot is talking, build an animation from two sprites
 talking_list = [sprites["sc-default.png"], sprites["sc-talk.png"]]
 talking = [random.choice(talking_list) for x in range(30)]
-talking_frame = SpriteFrame(images=talking)
+talking_frame = SpriteFrame(talking)
 
 # TODO: Support "thinking" as soon as we get a valid transcript, while LLM
 # is processing
@@ -69,50 +81,42 @@ thinking_list = [
     sprites["sc-think-3.png"],
     sprites["sc-think-4.png"],
 ]
-thinking_frame = SpriteFrame(images=thinking_list)
+thinking_frame = SpriteFrame(thinking_list)
 
 
-class TranscriptFilter(AIService):
-    def __init__(self, bot_participant_id=None):
-        self.bot_participant_id = bot_participant_id
-
-    async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
-        if isinstance(frame, TranscriptionFrame):
-            if frame.participantId != self.bot_participant_id:
-                yield frame
-
-
-class NameCheckFilter(AIService):
+class NameCheckFilter(FrameProcessor):
     def __init__(self, names: list[str]):
-        self.names = names
-        self.sentence = ""
+        super().__init__()
+        self._names = names
+        self._sentence = ""
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        if isinstance(frame, SystemFrame):
+            await self.push_frame(frame, direction)
+            return
 
-    async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
         content: str = ""
 
         # TODO: split up transcription by participant
-        if isinstance(frame, TextFrame):
+        if isinstance(frame, TranscriptionFrame):
             content = frame.text
-
-        self.sentence += content
-        if self.sentence.endswith((".", "?", "!")):
-            if any(name in self.sentence for name in self.names):
-                out = self.sentence
-                self.sentence = ""
-                yield TextFrame(out)
-            else:
-                out = self.sentence
-                self.sentence = ""
+            self._sentence += content
+            if self._sentence.endswith((".", "?", "!")):
+                if any(name in self._sentence for name in self._names):
+                    await self.push_frame(TextFrame(self._sentence))
+                    self._sentence = ""
+                else:
+                    self._sentence = ""
+        else:
+            await self.push_frame(frame, direction)
 
 
-class ImageSyncAggregator(AIService):
-    def __init__(self):
-        pass
+class ImageSyncAggregator(FrameProcessor):
 
-    async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
-        yield talking_frame
-        yield frame
-        yield quiet_frame
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await self.push_frame(talking_frame)
+        await self.push_frame(frame)
+        await self.push_frame(quiet_frame)
 
 
 async def main(room_url: str, token):
@@ -121,20 +125,15 @@ async def main(room_url: str, token):
             room_url,
             token,
             "Santa Cat",
-            duration_minutes=3,
-            start_transcription=True,
-            mic_enabled=True,
-            mic_sample_rate=16000,
-            camera_enabled=True,
-            camera_width=720,
-            camera_height=1280,
+            DailyParams(
+                audio_out_enabled=True,
+                camera_out_enabled=True,
+                camera_out_width=720,
+                camera_out_height=1280,
+                camera_out_framerate=10,
+                transcription_enabled=True
+            )
         )
-        transport._mic_enabled = True
-        transport._mic_sample_rate = 16000
-        transport._camera_enabled = True
-        transport._camera_width = 720
-        transport._camera_height = 1280
-        transport.transcription_settings["extra"]["punctuate"] = True
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
@@ -154,27 +153,27 @@ async def main(room_url: str, token):
             },
         ]
 
-        tma_in = LLMUserContextAggregator(
-            messages, transport._my_participant_id)
-        tma_out = LLMAssistantContextAggregator(
-            messages, transport._my_participant_id
-        )
-        tf = TranscriptFilter(transport._my_participant_id)
+        tma_in = LLMUserContextAggregator(messages)
+        tma_out = LLMAssistantContextAggregator(messages)
         ncf = NameCheckFilter(["Santa Cat", "Santa"])
 
-        pipeline = Pipeline([isa, tf, ncf, tma_in, llm, tma_out, tts])
+        pipeline = Pipeline([transport.input(), isa, ncf, tma_in,
+                            llm, tma_out, tts, transport.output()])
 
-        @transport.event_handler("on_first_other_participant_joined")
-        async def on_first_other_participant_joined(transport, participant):
-            await transport.say(
-                "Hi! If you want to talk to me, just say 'hey Santa Cat'.",
-                tts,
-            )
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            # Send some greeting at the beginning.
+            await tts.say("Hi! If you want to talk to me, just say 'hey Santa Cat'.")
+            transport.capture_participant_transcription(participant["id"])
 
         async def starting_image():
-            await transport.send_queue.put(quiet_frame)
+            await transport.send_image(quiet_frame)
 
-        await asyncio.gather(transport.run(pipeline), starting_image())
+        runner = PipelineRunner()
+
+        task = PipelineTask(pipeline)
+
+        await asyncio.gather(runner.run(task), starting_image())
 
 
 if __name__ == "__main__":

examples/foundational/11-sound-effects.py

@@ -1,34 +1,44 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
 import aiohttp
 import asyncio
-import logging
 import os
+import sys
 import wave
-from dailyai.pipeline.pipeline import Pipeline
 
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.open_ai_services import OpenAILLMService
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
-from dailyai.pipeline.aggregators import (
-    LLMUserContextAggregator,
-    LLMAssistantContextAggregator,
-)
-from dailyai.services.ai_services import AIService, FrameLogger
-from dailyai.pipeline.frames import (
+from pipecat.frames.frames import (
     Frame,
-    AudioFrame,
+    AudioRawFrame,
     LLMResponseEndFrame,
     LLMMessagesFrame,
 )
-from typing import AsyncGenerator
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.aggregators.llm_context import (
+    LLMUserContextAggregator,
+    LLMAssistantContextAggregator,
+)
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.processors.logger import FrameLogger
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 from runner import configure
 
+from loguru import logger
+
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
 
 sounds = {}
 sound_files = ["ding1.wav", "ding2.wav"]
@@ -42,33 +52,30 @@ for file in sound_files:
     filename = os.path.splitext(os.path.basename(full_path))[0]
     # Open the image and convert it to bytes
     with wave.open(full_path) as audio_file:
-        sounds[file] = audio_file.readframes(-1)
+        sounds[file] = AudioRawFrame(audio_file.readframes(-1),
+                                     audio_file.getframerate(), audio_file.getnchannels())
 
 
-class OutboundSoundEffectWrapper(AIService):
-    def __init__(self):
-        pass
+class OutboundSoundEffectWrapper(FrameProcessor):
 
-    async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
         if isinstance(frame, LLMResponseEndFrame):
-            yield AudioFrame(sounds["ding1.wav"])
-            # In case anything else up the stack needs it
-            yield frame
+            await self.push_frame(sounds["ding1.wav"])
+            # In case anything else downstream needs it
+            await self.push_frame(frame, direction)
         else:
-            yield frame
+            await self.push_frame(frame, direction)
 
 
-class InboundSoundEffectWrapper(AIService):
-    def __init__(self):
-        pass
+class InboundSoundEffectWrapper(FrameProcessor):
 
-    async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
         if isinstance(frame, LLMMessagesFrame):
-            yield AudioFrame(sounds["ding2.wav"])
-            # In case anything else up the stack needs it
-            yield frame
+            await self.push_frame(sounds["ding2.wav"])
+            # In case anything else downstream needs it
+            await self.push_frame(frame, direction)
         else:
-            yield frame
+            await self.push_frame(frame, direction)
 
 
 async def main(room_url: str, token):
@@ -77,12 +84,8 @@ async def main(room_url: str, token):
             room_url,
             token,
             "Respond bot",
-            duration_minutes=5,
-            mic_enabled=True,
-            mic_sample_rate=16000,
-            camera_enabled=False,
+            DailyParams(audio_out_enabled=True, transcription_enabled=True)
         )
-        transport.transcription_settings["extra"]["punctuate"] = True
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
@@ -101,24 +104,27 @@ async def main(room_url: str, token):
             },
         ]
 
-        tma_in = LLMUserContextAggregator(
-            messages, transport._my_participant_id)
-        tma_out = LLMAssistantContextAggregator(
-            messages, transport._my_participant_id
-        )
+        tma_in = LLMUserContextAggregator(messages)
+        tma_out = LLMAssistantContextAggregator(messages)
         out_sound = OutboundSoundEffectWrapper()
         in_sound = InboundSoundEffectWrapper()
         fl = FrameLogger("LLM Out")
         fl2 = FrameLogger("Transcription In")
 
-        pipeline = Pipeline([tma_in, in_sound, fl2, llm, tma_out, fl, tts, out_sound])
+        pipeline = Pipeline([transport.input(), tma_in, in_sound, fl2, llm,
+                            tma_out, fl, tts, out_sound, transport.output()])
 
-        @transport.event_handler("on_first_other_participant_joined")
-        async def on_first_other_participant_joined(transport, participant):
-            await transport.say("Hi, I'm listening!", tts)
-            await transport.send_queue.put(AudioFrame(sounds["ding1.wav"]))
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
+            await tts.say("Hi, I'm listening!")
+            await transport.send_audio(sounds["ding1.wav"])
 
-        await asyncio.gather(transport.run(pipeline))
+        runner = PipelineRunner()
+
+        task = PipelineTask(pipeline)
+
+        await runner.run(task)
 
 
 if __name__ == "__main__":

examples/foundational/12-describe-video.py

@@ -1,38 +1,50 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
 import asyncio
 import aiohttp
-import logging
 import os
+import sys
 
-from typing import AsyncGenerator
-
-from dailyai.pipeline.aggregators import FrameProcessor, UserResponseAggregator, VisionImageFrameAggregator
-
-from dailyai.pipeline.frames import Frame, TextFrame, UserImageRequestFrame
-from dailyai.pipeline.pipeline import Pipeline
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
-from dailyai.services.moondream_ai_service import MoondreamService
-from dailyai.transports.daily_transport import DailyTransport
+from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.aggregators.user_response import UserResponseAggregator
+from pipecat.processors.aggregators.vision_image_frame import VisionImageFrameAggregator
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.moondream import MoondreamService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVAD
 
 from runner import configure
 
+from loguru import logger
+
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
 
 
 class UserImageRequester(FrameProcessor):
-    participant_id: str
+
+    def __init__(self, participant_id: str | None = None):
+        super().__init__()
+        self._participant_id = participant_id
 
     def set_participant_id(self, participant_id: str):
-        self.participant_id = participant_id
+        self._participant_id = participant_id
 
-    async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
-        if self.participant_id and isinstance(frame, TextFrame):
-            yield UserImageRequestFrame(self.participant_id)
-        yield frame
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        if self._participant_id and isinstance(frame, TextFrame):
+            await self.push_frame(UserImageRequestFrame(self._participant_id), FrameDirection.UPSTREAM)
+        await self.push_frame(frame, direction)
 
 
 async def main(room_url: str, token):
@@ -41,14 +53,15 @@ async def main(room_url: str, token):
             room_url,
             token,
             "Describe participant video",
-            duration_minutes=5,
-            mic_enabled=True,
-            mic_sample_rate=16000,
-            vad_enabled=True,
-            start_transcription=True,
-            video_rendering_enabled=True
+            DailyParams(
+                audio_in_enabled=True,  # This is so Silero VAD can get audio data
+                audio_out_enabled=True,
+                transcription_enabled=True
+            )
         )
 
+        vad = SileroVAD()
+
         tts = ElevenLabsTTSService(
             aiohttp_session=session,
             api_key=os.getenv("ELEVENLABS_API_KEY"),
@@ -61,6 +74,7 @@ async def main(room_url: str, token):
 
         vision_aggregator = VisionImageFrameAggregator()
 
+        # If you run into weird description, try with use_cpu=True
         moondream = MoondreamService()
 
         tts = ElevenLabsTTSService(
@@ -69,15 +83,21 @@ async def main(room_url: str, token):
             voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
         )
 
-        @transport.event_handler("on_first_other_participant_joined")
-        async def on_first_other_participant_joined(transport, participant):
-            await transport.say("Hi there! Feel free to ask me what I see.", tts)
-            transport.render_participant_video(participant["id"], framerate=0)
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await tts.say("Hi there! Feel free to ask me what I see.")
+            transport.capture_participant_video(participant["id"], framerate=0)
+            transport.capture_participant_transcription(participant["id"])
             image_requester.set_participant_id(participant["id"])
 
-        pipeline = Pipeline([user_response, image_requester, vision_aggregator, moondream, tts])
+        pipeline = Pipeline([transport.input(), vad, user_response, image_requester,
+                             vision_aggregator, moondream, tts, transport.output()])
 
-        await transport.run(pipeline)
+        task = PipelineTask(pipeline)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
 
 if __name__ == "__main__":
     (url, token) = configure()

examples/foundational/13-whisper-transcription.py

@@ -1,56 +1,53 @@
-import asyncio
-import logging
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
 
-from dailyai.pipeline.frames import EndFrame, TranscriptionFrame
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.whisper_ai_services import WhisperSTTService
-from dailyai.pipeline.pipeline import Pipeline
+import asyncio
+import sys
+
+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.whisper import WhisperSTTService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 from runner import configure
 
+from loguru import logger
+
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class TranscriptionLogger(FrameProcessor):
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        if isinstance(frame, TranscriptionFrame):
+            print(f"Transcription: {frame.text}")
 
 
 async def main(room_url: str):
-    transport = DailyTransport(
-        room_url,
-        None,
-        "Transcription bot",
-        start_transcription=False,
-        mic_enabled=False,
-        camera_enabled=False,
-        speaker_enabled=True,
-    )
+    transport = DailyTransport(room_url, None, "Transcription bot",
+                               DailyParams(audio_in_enabled=True))
 
     stt = WhisperSTTService()
 
-    transcription_output_queue = asyncio.Queue()
-    transport_done = asyncio.Event()
+    tl = TranscriptionLogger()
 
-    pipeline = Pipeline([stt], source=transport.receive_queue, sink=transcription_output_queue)
+    pipeline = Pipeline([transport.input(), stt, tl])
 
-    async def handle_transcription():
-        print("`````````TRANSCRIPTION`````````")
-        while not transport_done.is_set():
-            item = await transcription_output_queue.get()
-            print("got item from queue", item)
-            if isinstance(item, TranscriptionFrame):
-                print(item.text)
-            elif isinstance(item, EndFrame):
-                break
-        print("handle_transcription done")
+    task = PipelineTask(pipeline)
 
-    async def run_until_done():
-        await transport.run()
-        transport_done.set()
-        print("run_until_done done")
+    runner = PipelineRunner()
 
-    await asyncio.gather(run_until_done(), pipeline.run_pipeline(), handle_transcription())
+    await runner.run(task)
 
 
 if __name__ == "__main__":

examples/foundational/13a-whisper-local.py

@@ -1,51 +1,55 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
 import asyncio
-import logging
+import sys
 
-from dailyai.pipeline.frames import EndFrame, TranscriptionFrame
-from dailyai.transports.local_transport import LocalTransport
-from dailyai.services.whisper_ai_services import WhisperSTTService
-from dailyai.pipeline.pipeline import Pipeline
+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.whisper import WhisperSTTService
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.local.audio import LocalAudioTransport
 
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
 
 
-async def main():
-    meeting_duration_minutes = 1
+class TranscriptionLogger(FrameProcessor):
 
-    transport = LocalTransport(
-        mic_enabled=True,
-        camera_enabled=False,
-        speaker_enabled=True,
-        duration_minutes=meeting_duration_minutes,
-    )
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        if isinstance(frame, TranscriptionFrame):
+            print(f"Transcription: {frame.text}")
+
+
+async def main(room_url: str):
+    transport = LocalAudioTransport(TransportParams(audio_in_enabled=True))
 
     stt = WhisperSTTService()
 
-    transcription_output_queue = asyncio.Queue()
-    transport_done = asyncio.Event()
+    tl = TranscriptionLogger()
 
-    pipeline = Pipeline([stt], source=transport.receive_queue, sink=transcription_output_queue)
+    pipeline = Pipeline([transport.input(), stt, tl])
 
-    async def handle_transcription():
-        print("`````````TRANSCRIPTION`````````")
-        while not transport_done.is_set():
-            item = await transcription_output_queue.get()
-            print("got item from queue", item)
-            if isinstance(item, TranscriptionFrame):
-                print(item.text)
-            elif isinstance(item, EndFrame):
-                break
-        print("handle_transcription done")
+    task = PipelineTask(pipeline)
 
-    async def run_until_done():
-        await transport.run()
-        transport_done.set()
-        print("run_until_done done")
+    runner = PipelineRunner()
 
-    await asyncio.gather(run_until_done(), pipeline.run_pipeline(), handle_transcription())
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    (url, token) = configure()
+    asyncio.run(main(url))

examples/foundational/14-render-remote-participant.py

@@ -1,52 +0,0 @@
-import asyncio
-import logging
-
-from typing import AsyncGenerator
-
-from dailyai.pipeline.aggregators import FrameProcessor
-
-from dailyai.pipeline.frames import ImageFrame, Frame, UserImageFrame
-from dailyai.pipeline.pipeline import Pipeline
-from dailyai.transports.daily_transport import DailyTransport
-
-from runner import configure
-
-from dotenv import load_dotenv
-load_dotenv(override=True)
-
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
-
-
-class UserImageProcessor(FrameProcessor):
-
-    async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
-        if isinstance(frame, UserImageFrame):
-            yield ImageFrame(frame.image, frame.size)
-        else:
-            yield frame
-
-
-async def main(room_url: str, token):
-    transport = DailyTransport(
-        room_url,
-        token,
-        "Render participant video",
-        camera_width=1280,
-        camera_height=720,
-        camera_enabled=True,
-        video_rendering_enabled=True
-    )
-
-    @ transport.event_handler("on_first_other_participant_joined")
-    async def on_first_other_participant_joined(transport, participant):
-        transport.render_participant_video(participant["id"])
-
-    pipeline = Pipeline([UserImageProcessor()])
-
-    await asyncio.gather(transport.run(pipeline))
-
-if __name__ == "__main__":
-    (url, token) = configure()
-    asyncio.run(main(url, token))

examples/foundational/14a-local-render-remote-participant.py

@@ -1,71 +0,0 @@
-import asyncio
-import logging
-import tkinter as tk
-
-from typing import AsyncGenerator
-
-from dailyai.pipeline.aggregators import FrameProcessor
-
-from dailyai.pipeline.frames import ImageFrame, Frame, UserImageFrame
-from dailyai.pipeline.pipeline import Pipeline
-from dailyai.transports.daily_transport import DailyTransport
-
-from dailyai.transports.local_transport import LocalTransport
-from runner import configure
-
-from dotenv import load_dotenv
-load_dotenv(override=True)
-
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
-logger.setLevel(logging.DEBUG)
-
-
-class UserImageProcessor(FrameProcessor):
-
-    async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
-        if isinstance(frame, UserImageFrame):
-            yield ImageFrame(frame.image, frame.size)
-        else:
-            yield frame
-
-
-async def main(room_url: str, token):
-    tk_root = tk.Tk()
-    tk_root.title("dailyai")
-
-    local_transport = LocalTransport(
-        tk_root=tk_root,
-        camera_enabled=True,
-        camera_width=1280,
-        camera_height=720
-    )
-
-    transport = DailyTransport(
-        room_url,
-        token,
-        "Render participant video",
-        video_rendering_enabled=True
-    )
-
-    @transport.event_handler("on_first_other_participant_joined")
-    async def on_first_other_participant_joined(transport, participant):
-        transport.render_participant_video(participant["id"])
-
-    async def run_tk():
-        while not transport._stop_threads.is_set():
-            tk_root.update()
-            tk_root.update_idletasks()
-            await asyncio.sleep(0.1)
-
-    local_pipeline = Pipeline([UserImageProcessor()], source=transport.receive_queue)
-
-    await asyncio.gather(
-        transport.run(),
-        local_transport.run(local_pipeline, override_pipeline_source_queue=False),
-        run_tk()
-    )
-
-if __name__ == "__main__":
-    (url, token) = configure()
-    asyncio.run(main(url, token))

examples/foundational/websocket-server/frames.proto

@@ -1,6 +1,6 @@
 syntax = "proto3";
 
-package dailyai_proto;
+package pipecat_proto;
 
 message TextFrame {
     string text = 1;

examples/foundational/websocket-server/index.html

@@ -28,7 +28,7 @@
 
         const proto = protobuf.load("frames.proto", (err, root) => {
             if (err) throw err;
-            frame = root.lookupType("dailyai_proto.Frame");
+            frame = root.lookupType("pipecat_proto.Frame");
         });
 
         function initWebSocket() {

examples/foundational/websocket-server/sample.py

@@ -2,15 +2,15 @@ import asyncio
 import aiohttp
 import logging
 import os
-from dailyai.pipeline.frame_processor import FrameProcessor
-from dailyai.pipeline.frames import TextFrame, TranscriptionFrame
-from dailyai.pipeline.pipeline import Pipeline
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
-from dailyai.transports.websocket_transport import WebsocketTransport
-from dailyai.services.whisper_ai_services import WhisperSTTService
+from pipecat.pipeline.frame_processor import FrameProcessor
+from pipecat.pipeline.frames import TextFrame, TranscriptionFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.services.elevenlabs_ai_services import ElevenLabsTTSService
+from pipecat.transports.websocket_transport import WebsocketTransport
+from pipecat.services.whisper_ai_services import WhisperSTTService
 
 logging.basicConfig(format="%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("dailyai")
+logger = logging.getLogger("pipecat")
 logger.setLevel(logging.DEBUG)
 
 

examples/image-gen.py

@@ -1,125 +0,0 @@
-import argparse
-import asyncio
-import requests
-import time
-import urllib.parse
-import random
-
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
-from dailyai.pipeline.frames import Frame, FrameType
-from dailyai.services.fal_ai_services import FalImageGenService
-from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
-
-
-async def main(room_url: str, token):
-    global transport
-    global llm
-    global tts
-
-    transport = DailyTransport(
-        room_url,
-        token,
-        "Imagebot",
-        1,
-    )
-    transport._mic_enabled = True
-    transport._camera_enabled = True
-    transport._mic_sample_rate = 16000
-    transport._camera_width = 1024
-    transport._camera_height = 1024
-
-    llm = AzureLLMService()
-    tts = AzureTTSService()
-    img = FalImageGenService()
-
-    async def handle_transcriptions():
-        print("handle_transcriptions got called")
-
-        sentence = ""
-        async for message in transport.get_transcriptions():
-            print(f"transcription message: {message}")
-            if message["session_id"] == transport._my_participant_id:
-                continue
-            finder = message["text"].find("start over")
-            print(f"finder: {finder}")
-            if finder >= 0:
-                async for audio in tts.run_tts(f"Resetting."):
-                    transport.output_queue.put(
-                        Frame(FrameType.AUDIO_FRAME, audio))
-                sentence = ""
-                continue
-            # todo: we could differentiate between transcriptions from
-            # different participants
-            sentence += f" {message['text']}"
-            print(f"sentence is now: {sentence}")
-            # TODO: Cache this audio
-            phrase = random.choice(
-                ["OK.", "Got it.", "Sure.", "You bet.", "Sure thing."])
-            async for audio in tts.run_tts(phrase):
-                transport.output_queue.put(Frame(FrameType.AUDIO_FRAME, audio))
-            img_result = img.run_image_gen(sentence, "1024x1024")
-            awaited_img = await asyncio.gather(img_result)
-            transport.output_queue.put(
-                [
-                    Frame(FrameType.IMAGE_FRAME, awaited_img[0][1]),
-                ]
-            )
-
-    @transport.event_handler("on_participant_joined")
-    async def on_participant_joined(transport, participant):
-        print(f"participant joined: {participant['info']['userName']}")
-        if participant["info"]["isLocal"]:
-            return
-        async for audio in tts.run_tts("Describe an image, and I'll create it."):
-            audio_generator = tts.run_tts(
-                f"Hello, {participant['info']['userName']}! Describe an image and I'll create it. To start over, just say 'start over'.")
-            async for audio in audio_generator:
-                transport.output_queue.put(Frame(FrameType.AUDIO_FRAME, audio))
-
-    transport.transcription_settings["extra"]["punctuate"] = False
-    transport.transcription_settings["extra"]["endpointing"] = False
-    await asyncio.gather(transport.run(), handle_transcriptions())
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Simple Daily Bot Sample")
-    parser.add_argument(
-        "-u",
-        "--url",
-        type=str,
-        required=True,
-        help="URL of the Daily room to join")
-    parser.add_argument(
-        "-k",
-        "--apikey",
-        type=str,
-        required=True,
-        help="Daily API Key (needed to create token)",
-    )
-
-    args, unknown = parser.parse_known_args()
-
-    # Create a meeting token for the given room with an expiration 1 hour in
-    # the future.
-    room_name: str = urllib.parse.urlparse(args.url).path[1:]
-    expiration: float = time.time() + 60 * 60
-
-    res: requests.Response = requests.post(
-        f"https://api.daily.co/v1/meeting-tokens",
-        headers={
-            "Authorization": f"Bearer {args.apikey}"},
-        json={
-            "properties": {
-                "room_name": room_name,
-                "is_owner": True,
-                "exp": expiration}},
-    )
-
-    if res.status_code != 200:
-        raise Exception(
-            f"Failed to create meeting token: {res.status_code} {res.text}")
-
-    token: str = res.json()["token"]
-
-    asyncio.run(main(args.url, token))

examples/internal/11a-dial-out.py

@@ -1,137 +0,0 @@
-import aiohttp
-import asyncio
-import os
-import wave
-
-from dailyai.transports.daily_transport import DailyTransport
-from dailyai.services.azure_ai_services import AzureLLMService, AzureTTSService
-from dailyai.pipeline.aggregators import LLMContextAggregator
-from dailyai.services.ai_services import AIService, FrameLogger
-from dailyai.pipeline.frames import Frame, AudioFrame, LLMResponseEndFrame, LLMMessagesFrame
-from typing import AsyncGenerator
-
-from runner import configure
-
-from dotenv import load_dotenv
-load_dotenv(override=True)
-
-sounds = {}
-sound_files = [
-    'ding1.wav',
-    'ding2.wav'
-]
-
-script_dir = os.path.dirname(__file__)
-
-for file in sound_files:
-    # Build the full path to the image file
-    full_path = os.path.join(script_dir, "assets", file)
-    # Get the filename without the extension to use as the dictionary key
-    filename = os.path.splitext(os.path.basename(full_path))[0]
-    # Open the image and convert it to bytes
-    with wave.open(full_path) as audio_file:
-        sounds[file] = audio_file.readframes(-1)
-
-
-class OutboundSoundEffectWrapper(AIService):
-    def __init__(self):
-        pass
-
-    async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
-        if isinstance(frame, LLMResponseEndFrame):
-            yield AudioFrame(sounds["ding1.wav"])
-            # In case anything else up the stack needs it
-            yield frame
-        else:
-            yield frame
-
-
-class InboundSoundEffectWrapper(AIService):
-    def __init__(self):
-        pass
-
-    async def process_frame(self, frame: Frame) -> AsyncGenerator[Frame, None]:
-        if isinstance(frame, LLMMessagesFrame):
-            yield AudioFrame(sounds["ding2.wav"])
-            # In case anything else up the stack needs it
-            yield frame
-        else:
-            yield frame
-
-
-async def main(room_url: str, token, phone):
-    async with aiohttp.ClientSession() as session:
-
-        global transport
-        global llm
-        global tts
-
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            300,
-        )
-        transport._mic_enabled = True
-        transport._mic_sample_rate = 16000
-        transport._camera_enabled = False
-
-        llm = AzureLLMService()
-        tts = AzureTTSService()
-
-        @transport.event_handler("on_first_other_participant_joined")
-        async def on_first_other_participant_joined(transport, participant):
-            await tts.say("Hi, I'm listening!", transport.send_queue)
-            await transport.send_queue.put(AudioFrame(sounds["ding1.wav"]))
-
-        async def handle_transcriptions():
-            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. Respond to what the user said in a creative and helpful way."},
-            ]
-
-            tma_in = LLMContextAggregator(
-                messages, "user", transport._my_participant_id
-            )
-            tma_out = LLMContextAggregator(
-                messages, "assistant", transport._my_participant_id
-            )
-            out_sound = OutboundSoundEffectWrapper()
-            in_sound = InboundSoundEffectWrapper()
-            fl = FrameLogger("LLM Out")
-            fl2 = FrameLogger("Transcription In")
-            await out_sound.run_to_queue(
-                transport.send_queue,
-                tts.run(
-                    tma_out.run(
-                        llm.run(
-                            fl2.run(
-                                in_sound.run(
-                                    tma_in.run(
-                                        transport.get_receive_frames()
-                                    )
-                                )
-                            )
-                        )
-                    )
-                )
-            )
-
-        @transport.event_handler("on_participant_joined")
-        async def pax_joined(transport, pax):
-            print(f"PARTICIPANT JOINED: {pax}")
-
-        @transport.event_handler("on_call_state_updated")
-        async def on_call_state_updated(transport, state):
-            if (state == "joined"):
-                if (phone):
-                    transport.start_recording()
-                    transport.dialout(phone)
-
-        transport.transcription_settings["extra"]["punctuate"] = True
-
-        await asyncio.gather(transport.run(), handle_transcriptions())
-
-
-if __name__ == "__main__":
-    (url, token) = configure()
-    asyncio.run(main(url, token))

examples/moondream-chatbot/.dockerignore

@@ -0,0 +1,163 @@
+# flyctl launch added from .gitignore
+# Byte-compiled / optimized / DLL files
+**/__pycache__
+**/*.py[cod]
+**/*$py.class
+
+# C extensions
+**/*.so
+
+# Distribution / packaging
+**/.Python
+**/build
+**/develop-eggs
+**/dist
+**/downloads
+**/eggs
+**/.eggs
+**/lib
+**/lib64
+**/parts
+**/sdist
+**/var
+**/wheels
+**/share/python-wheels
+**/*.egg-info
+**/.installed.cfg
+**/*.egg
+**/MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+**/*.manifest
+**/*.spec
+
+# Installer logs
+**/pip-log.txt
+**/pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+**/htmlcov
+**/.tox
+**/.nox
+**/.coverage
+**/.coverage.*
+**/.cache
+**/nosetests.xml
+**/coverage.xml
+**/*.cover
+**/*.py,cover
+**/.hypothesis
+**/.pytest_cache
+**/cover
+
+# Translations
+**/*.mo
+**/*.pot
+
+# Django stuff:
+**/*.log
+**/local_settings.py
+**/db.sqlite3
+**/db.sqlite3-journal
+
+# Flask stuff:
+**/instance
+**/.webassets-cache
+
+# Scrapy stuff:
+**/.scrapy
+
+# Sphinx documentation
+**/docs/_build
+
+# PyBuilder
+**/.pybuilder
+**/target
+
+# Jupyter Notebook
+**/.ipynb_checkpoints
+
+# IPython
+**/profile_default
+**/ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+**/.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+**/__pypackages__
+
+# Celery stuff
+**/celerybeat-schedule
+**/celerybeat.pid
+
+# SageMath parsed files
+**/*.sage.py
+
+# Environments
+**/.env
+**/.venv
+**/env
+**/venv
+**/ENV
+**/env.bak
+**/venv.bak
+
+# Spyder project settings
+**/.spyderproject
+**/.spyproject
+
+# Rope project settings
+**/.ropeproject
+
+# mkdocs documentation
+site
+
+# mypy
+**/.mypy_cache
+**/.dmypy.json
+**/dmypy.json
+
+# Pyre type checker
+**/.pyre
+
+# pytype static type analyzer
+**/.pytype
+
+# Cython debug symbols
+**/cython_debug
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+**/runpod.toml
+fly.toml

examples/moondream-chatbot/.gitignore

@@ -0,0 +1,161 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+runpod.toml

examples/moondream-chatbot/Dockerfile

@@ -0,0 +1,25 @@
+FROM ubuntu:22.04
+
+RUN apt-get update && apt-get install -y wget
+RUN wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
+RUN dpkg -i cuda-keyring_1.1-1_all.deb
+
+RUN echo "deb [signed-by=/usr/share/keyrings/cuda-archive-keyring.gpg] https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/ /" > /etc/apt/sources.list.d/cuda-ubuntu2204-x86_64.list
+
+RUN apt-get update && apt-get install -y python3 python3-pip
+RUN apt-get install -y cuda-nvcc-12-4 libcublas-12-4 libcudnn8
+
+RUN mkdir /app
+RUN mkdir /app/assets
+RUN mkdir /app/utils
+COPY *.py /app/
+COPY requirements.txt /app/
+copy assets/* /app/assets/
+copy utils/* /app/utils/
+
+WORKDIR /app
+RUN pip3 install -r requirements.txt
+
+EXPOSE 7860
+
+CMD ["python3", "server.py"]

examples/moondream-chatbot/Dockerfile.intel

@@ -0,0 +1,76 @@
+FROM ubuntu:22.04
+
+# environment variables for Intel OneAPI components
+ENV DPCPPROOT=/opt/intel/oneapi/compiler/latest
+ENV MKLROOT=/opt/intel/oneapi/mkl/latest
+ENV CCLROOT=/opt/intel/oneapi/ccl/latest
+ENV MPIROOT=/opt/intel/oneapi/mpi/latest
+
+# Install necessary dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    wget \
+    lsb-release \
+    pciutils \
+    gnupg2 \
+    python3-pip
+
+# Add Intel OneAPI repository and GPG key
+# Intel GPU repository and GPG key
+# Install Intel OneAPI components and source the environment scripts
+RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null && \
+    echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list && \
+    /bin/bash -c ' \
+    . /etc/os-release && \
+    if [[ " jammy " =~ " ${VERSION_CODENAME} " ]]; then \
+        wget -qO - https://repositories.intel.com/gpu/intel-graphics.key | gpg --dearmor --output /usr/share/keyrings/intel-graphics.gpg && \
+        echo "deb [arch=amd64 signed-by=/usr/share/keyrings/intel-graphics.gpg] https://repositories.intel.com/gpu/ubuntu ${VERSION_CODENAME}/lts/2350 unified" | \
+        tee /etc/apt/sources.list.d/intel-gpu-${VERSION_CODENAME}.list && \
+        apt-get update && \
+        apt-get install -y --no-install-recommends intel-opencl-icd \
+            intel-level-zero-gpu level-zero intel-media-va-driver-non-free \
+            libmfx1 libmfxgen1 libvpl2 libegl-mesa0 libegl1-mesa \
+            libegl1-mesa-dev libgbm1 libgl1-mesa-dev libgl1-mesa-dri \
+            libglapi-mesa libgles2-mesa-dev libglx-mesa0 libigdgmm12 \
+            libxatracker2 mesa-va-drivers mesa-vdpau-drivers \
+            mesa-vulkan-drivers va-driver-all; \
+    else \
+        echo "Ubuntu version ${VERSION_CODENAME} not supported. Exiting..."; \
+        exit 1; \
+    fi' && \
+    apt-get update && apt-get install -y --no-install-recommends \
+    intel-oneapi-dpcpp-cpp-2024.1=2024.1.0-963 intel-oneapi-mkl-devel=2024.1.0-691 \
+    intel-oneapi-ccl-devel=2021.12.0-309 && \
+    apt-get clean && rm -rf /var/lib/apt/lists/* && \
+    groupadd -r render && usermod -aG render root && \
+    echo "source ${DPCPPROOT}/env/vars.sh" >> ~/.bashrc && \
+    echo "source ${MKLROOT}/env/vars.sh" >> ~/.bashrc && \
+    echo "source ${CCLROOT}/env/vars.sh" >> ~/.bashrc && \
+    echo "source ${MPIROOT}/env/vars.sh" >> ~/.bashrc && \
+    echo "export LD_LIBRARY_PATH=${MKLROOT}/lib:${DPCPPROOT}/linux/compiler/lib/intel64_lin:$LD_LIBRARY_PATH" >> ~/.bashrc
+
+WORKDIR /app
+COPY . /app
+RUN mkdir -p /app /app/assets /app/utils
+COPY *.py requirements.txt assets/* utils/* /app/
+
+# Install the Intel-specific versions of torch
+RUN python3 -m pip install --no-cache-dir -r requirements.txt && \
+    pip uninstall -y torch && \
+    pip freeze | grep 'nvidia-' | xargs pip uninstall -y && \
+    pip install --no-cache-dir --force-reinstall torch==2.1.0.post2 torchvision==0.16.0.post2 torchaudio==2.1.0.post2 \
+    intel-extension-for-pytorch==2.1.30+xpu oneccl_bind_pt==2.1.300+xpu \
+    --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/  
+
+RUN echo '#!/bin/bash\n\
+source ${DPCPPROOT}/env/vars.sh\n\
+source ${MKLROOT}/env/vars.sh\n\
+source ${CCLROOT}/env/vars.sh\n\
+source ${MPIROOT}/env/vars.sh\n\
+export LD_LIBRARY_PATH=${MKLROOT}/lib:${DPCPPROOT}/linux/compiler/lib/intel64_lin:$LD_LIBRARY_PATH\n\
+python3 server.py' > /usr/local/bin/run_app.sh && \
+    chmod +x /usr/local/bin/run_app.sh && \
+    find / -type d -name "__pycache__" -exec rm -rf {} + 
+
+EXPOSE 7860
+ENTRYPOINT ["/usr/local/bin/run_app.sh"]

examples/moondream-chatbot/README.md

@@ -0,0 +1,44 @@
+# Moondream Chatbot
+
+<img src="image.png" width="420px">
+
+
+This app connects you to a chatbot powered by GPT-4, complete with animations generated by Stable Video Diffusion. The chatbot also has vision powers thanks to [Moondream](https://moondream.ai) so you can ask it, for example, "what do you see?".
+
+ℹ️ The first time, things might take some time to get started since VAD (Voice Activity Detection) and vision models need to be downloaded.
+
+## Get started
+
+```python
+python3 -m venv venv
+source venv/bin/activate
+pip install -r requirements.txt
+
+cp env.example .env # and add your credentials
+
+```
+
+## Run the server
+
+```bash
+python server.py
+```
+
+Then, visit `http://localhost:7860/start` in your browser to start a chatbot
+session.
+
+## Build and test the Docker image
+
+```
+docker build -t moonbot .
+docker run --env-file .env -p 7860:7860 moonbot
+```
+
+### For Intel GPUs (Arc, Max and Flex series)
+
+```
+docker build -t moonbot -f Dockerfile.intel .
+docker run --env-file .env -p 7860:7860 --device /dev/dri moonbot
+```
+
+You can try to visit `http://localhost:7860/start` again.

examples/moondream-chatbot/bot.py

@@ -0,0 +1,195 @@
+import asyncio
+import aiohttp
+import os
+import sys
+
+from PIL import Image
+
+from pipecat.frames.frames import (
+    ImageRawFrame,
+    SpriteFrame,
+    Frame,
+    LLMMessagesFrame,
+    AudioRawFrame,
+    TTSStoppedFrame,
+    TextFrame,
+    UserImageRawFrame,
+    UserImageRequestFrame,
+)
+
+from pipecat.pipeline.parallel_pipeline import ParallelPipeline
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.aggregators.llm_response import LLMUserResponseAggregator
+from pipecat.processors.aggregators.sentence import SentenceAggregator
+from pipecat.processors.aggregators.vision_image_frame import VisionImageFrameAggregator
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.moondream import MoondreamService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVAD
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+user_request_answer = "Let me take a look."
+
+sprites = []
+
+script_dir = os.path.dirname(__file__)
+
+for i in range(1, 26):
+    # Build the full path to the image file
+    full_path = os.path.join(script_dir, f"assets/robot0{i}.png")
+    # Get the filename without the extension to use as the dictionary key
+    # Open the image and convert it to bytes
+    with Image.open(full_path) as img:
+        sprites.append(ImageRawFrame(image=img.tobytes(), size=img.size, format=img.format))
+
+flipped = sprites[::-1]
+sprites.extend(flipped)
+
+# When the bot isn't talking, show a static image of the cat listening
+quiet_frame = sprites[0]
+talking_frame = SpriteFrame(images=sprites)
+
+
+class TalkingAnimation(FrameProcessor):
+    """
+    This class starts a talking animation when it receives an first AudioFrame,
+    and then returns to a "quiet" sprite when it sees a LLMResponseEndFrame.
+    """
+
+    def __init__(self):
+        super().__init__()
+        self._is_talking = False
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        if isinstance(frame, AudioRawFrame):
+            if not self._is_talking:
+                await self.push_frame(talking_frame)
+                self._is_talking = True
+        elif isinstance(frame, TTSStoppedFrame):
+            await self.push_frame(quiet_frame)
+            self._is_talking = False
+        await self.push_frame(frame)
+
+
+class UserImageRequester(FrameProcessor):
+    def __init__(self):
+        super().__init__()
+        self.participant_id = None
+
+    def set_participant_id(self, participant_id: str):
+        self.participant_id = participant_id
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        if self.participant_id and isinstance(frame, TextFrame):
+            if frame.text == user_request_answer:
+                await self.push_frame(UserImageRequestFrame(self.participant_id), FrameDirection.UPSTREAM)
+                await self.push_frame(TextFrame("Describe the image in a short sentence."))
+        elif isinstance(frame, UserImageRawFrame):
+            await self.push_frame(frame)
+
+
+class TextFilterProcessor(FrameProcessor):
+    def __init__(self, text: str):
+        super().__init__()
+        self.text = text
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        if isinstance(frame, TextFrame):
+            if frame.text != self.text:
+                await self.push_frame(frame)
+        else:
+            await self.push_frame(frame)
+
+
+class ImageFilterProcessor(FrameProcessor):
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        if not isinstance(frame, ImageRawFrame):
+            await self.push_frame(frame)
+
+
+async def main(room_url: str, token):
+    async with aiohttp.ClientSession() as session:
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Chatbot",
+            DailyParams(
+                audio_in_enabled=True,
+                audio_out_enabled=True,
+                camera_out_enabled=True,
+                camera_out_width=1024,
+                camera_out_height=576,
+                transcription_enabled=True
+            )
+        )
+
+        vad = SileroVAD()
+
+        tts = ElevenLabsTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            voice_id="pNInz6obpgDQGcFmaJgB",
+        )
+
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4-turbo-preview")
+
+        ta = TalkingAnimation()
+
+        sa = SentenceAggregator()
+        ir = UserImageRequester()
+        va = VisionImageFrameAggregator()
+
+        # If you run into weird description, try with use_cpu=True
+        moondream = MoondreamService()
+
+        tf = TextFilterProcessor(user_request_answer)
+        imgf = ImageFilterProcessor()
+
+        messages = [
+            {
+                "role": "system",
+                "content": f"You are Chatbot, a friendly, helpful robot. Let the user know that you are capable of chatting or describing what you see. Your goal is to demonstrate your capabilities in a succinct way. Reply with only '{user_request_answer}' if the user asks you to describe what you see. Your output will be converted to audio so never 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 introducing yourself.",
+            },
+        ]
+
+        ura = LLMUserResponseAggregator(messages)
+
+        pipeline = Pipeline([transport.input(), vad, ura, llm,
+                             ParallelPipeline(
+                                 [sa, ir, va, moondream],
+                                 [tf, imgf]),
+                             tts, ta, transport.output()])
+
+        task = PipelineTask(pipeline)
+        await task.queue_frame(quiet_frame)
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
+            transport.capture_participant_video(participant["id"], framerate=0)
+            ir.set_participant_id(participant["id"])
+            await task.queue_frames([LLMMessagesFrame(messages)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    (url, token) = configure()
+    asyncio.run(main(url, token))

examples/moondream-chatbot/env.example

@@ -0,0 +1,4 @@
+DAILY_SAMPLE_ROOM_URL=https://yourdomain.daily.co/yourroom # (for joining the bot to the same room repeatedly for local dev)
+DAILY_API_KEY=7df...
+OPENAI_API_KEY=sk-PL...
+ELEVENLABS_API_KEY=aeb...

examples/moondream-chatbot/requirements.txt

@@ -0,0 +1,5 @@
+python-dotenv
+requests
+fastapi[all]
+uvicorn
+pipecat-ai[daily,moondream,openai,silero]

examples/moondream-chatbot/server.py

@@ -0,0 +1,124 @@
+import os
+import argparse
+import subprocess
+import atexit
+
+from fastapi import FastAPI, Request, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse, RedirectResponse
+
+from utils.daily_helpers import create_room as _create_room, get_token
+
+MAX_BOTS_PER_ROOM = 1
+
+# Bot sub-process dict for status reporting and concurrency control
+bot_procs = {}
+
+
+def cleanup():
+    # Clean up function, just to be extra safe
+    for proc in bot_procs.values():
+        proc.terminate()
+        proc.wait()
+
+
+atexit.register(cleanup)
+
+
+app = FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+@app.get("/start")
+async def start_agent(request: Request):
+    print(f"!!! Creating room")
+    room_url, room_name = _create_room()
+    print(f"!!! Room URL: {room_url}")
+    # Ensure the room property is present
+    if not room_url:
+        raise HTTPException(
+            status_code=500,
+            detail="Missing 'room' property in request data. Cannot start agent without a target room!")
+
+    # Check if there is already an existing process running in this room
+    num_bots_in_room = sum(
+        1 for proc in bot_procs.values() if proc[1] == room_url and proc[0].poll() is None)
+    if num_bots_in_room >= MAX_BOTS_PER_ROOM:
+        raise HTTPException(
+            status_code=500, detail=f"Max bot limited reach for room: {room_url}")
+
+    # Get the token for the room
+    token = get_token(room_url)
+
+    if not token:
+        raise HTTPException(
+            status_code=500, detail=f"Failed to get token for room: {room_url}")
+
+    # Spawn a new agent, and join the user session
+    # Note: this is mostly for demonstration purposes (refer to 'deployment' in README)
+    try:
+        proc = subprocess.Popen(
+            [
+                f"python3 -m bot -u {room_url} -t {token}"
+            ],
+            shell=True,
+            bufsize=1,
+            cwd=os.path.dirname(os.path.abspath(__file__))
+        )
+        bot_procs[proc.pid] = (proc, room_url)
+    except Exception as e:
+        raise HTTPException(
+            status_code=500, detail=f"Failed to start subprocess: {e}")
+
+    return RedirectResponse(room_url)
+
+
+@app.get("/status/{pid}")
+def get_status(pid: int):
+    # Look up the subprocess
+    proc = bot_procs.get(pid)
+
+    # If the subprocess doesn't exist, return an error
+    if not proc:
+        raise HTTPException(
+            status_code=404, detail=f"Bot with process id: {pid} not found")
+
+    # Check the status of the subprocess
+    if proc[0].poll() is None:
+        status = "running"
+    else:
+        status = "finished"
+
+    return JSONResponse({"bot_id": pid, "status": status})
+
+
+if __name__ == "__main__":
+    import uvicorn
+
+    default_host = os.getenv("HOST", "0.0.0.0")
+    default_port = int(os.getenv("FAST_API_PORT", "7860"))
+
+    parser = argparse.ArgumentParser(
+        description="Daily Moondream FastAPI server")
+    parser.add_argument("--host", type=str,
+                        default=default_host, help="Host address")
+    parser.add_argument("--port", type=int,
+                        default=default_port, help="Port number")
+    parser.add_argument("--reload", action="store_true",
+                        help="Reload code on change")
+
+    config = parser.parse_args()
+
+    uvicorn.run(
+        "server:app",
+        host=config.host,
+        port=config.port,
+        reload=config.reload,
+    )

examples/moondream-chatbot/utils/daily_helpers.py

@@ -0,0 +1,109 @@
+
+import urllib.parse
+import os
+import time
+import urllib
+import requests
+
+from dotenv import load_dotenv
+load_dotenv()
+
+
+daily_api_path = os.getenv("DAILY_API_URL") or "api.daily.co/v1"
+daily_api_key = os.getenv("DAILY_API_KEY")
+
+
+def create_room() -> tuple[str, str]:
+    """
+    Helper function to create a Daily room.
+    # See: https://docs.daily.co/reference/rest-api/rooms
+
+    Returns:
+        tuple: A tuple containing the room URL and room name.
+
+    Raises:
+        Exception: If the request to create the room fails or if the response does not contain the room URL or room name.
+    """
+    room_props = {
+        "exp": time.time() + 60 * 60,  # 1 hour
+        "enable_chat": True,
+        "enable_emoji_reactions": True,
+        "eject_at_room_exp": True,
+        "enable_prejoin_ui": False,  # Important for the bot to be able to join headlessly
+    }
+    res = requests.post(
+        f"https://{daily_api_path}/rooms",
+        headers={"Authorization": f"Bearer {daily_api_key}"},
+        json={
+            "properties": room_props
+        },
+    )
+    if res.status_code != 200:
+        raise Exception(f"Unable to create room: {res.text}")
+
+    data = res.json()
+    room_url: str = data.get("url")
+    room_name: str = data.get("name")
+    if room_url is None or room_name is None:
+        raise Exception("Missing room URL or room name in response")
+
+    return room_url, room_name
+
+
+def get_name_from_url(room_url: str) -> str:
+    """
+    Extracts the name from a given room URL.
+
+    Args:
+        room_url (str): The URL of the room.
+
+    Returns:
+        str: The extracted name from the room URL.
+    """
+    return urllib.parse.urlparse(room_url).path[1:]
+
+
+def get_token(room_url: str) -> str:
+    """
+    Retrieves a meeting token for the specified Daily room URL.
+    # See: https://docs.daily.co/reference/rest-api/meeting-tokens
+
+    Args:
+        room_url (str): The URL of the Daily room.
+
+    Returns:
+        str: The meeting token.
+
+    Raises:
+        Exception: If no room URL is specified or if no Daily API key is specified.
+        Exception: If there is an error creating the meeting token.
+    """
+    if not room_url:
+        raise Exception(
+            "No Daily room specified. You must specify a Daily room in order a token to be generated.")
+
+    if not daily_api_key:
+        raise Exception(
+            "No Daily API key specified. set DAILY_API_KEY in your environment to specify a Daily API key, available from https://dashboard.daily.co/developers.")
+
+    expiration: float = time.time() + 60 * 60
+    room_name = get_name_from_url(room_url)
+
+    res: requests.Response = requests.post(
+        f"https://{daily_api_path}/meeting-tokens",
+        headers={
+            "Authorization": f"Bearer {daily_api_key}"},
+        json={
+            "properties": {
+                "room_name": room_name,
+                "is_owner": True,  # Owner tokens required for transcription
+                "exp": expiration}},
+    )
+
+    if res.status_code != 200:
+        raise Exception(
+            f"Failed to create meeting token: {res.status_code} {res.text}")
+
+    token: str = res.json()["token"]
+
+    return token

examples/server/README.md

@@ -1,34 +0,0 @@
-# Server Example
-
-Use this server app to quickly host a bot on the web:
-
-```
-flask --app daily-bot-manager.py --debug run
-```
-
-It's currently configured to serve example apps defined in the APPS constant in the server file:
-
-```
-chatbot
-patient-intake
-storybot
-translator
-```
-
-Once the server is started, you can create a bot instance by opening `http://127.0.0.1:5000/start/chatbot` in a browser, and the server will do the following:
-
-- Create a new, randomly-named Daily room with `DAILY_API_KEY` from your .env file or environment
-- Start an instance of `chatbot.py` and connect it to that room
-- 301 redirect your browser to the room
-
-### Options
-
-The server supports several options, which can be set in the body of a POST request, or as params in the URL of a GET request.
-
-- `room_url` (default: none): A room URL to join. If empty, the server will create a Daily room and return the URL in the response.
-  room_properties (none): A JSON object (URL encoded if included as a GET parameter) for overriding default room creation properties, as described here: https://docs.daily.co/reference/rest-api/rooms/create-room This will be ignored if a room_url is provided.
-- `token_properties` (none): A JSON object (URL encoded if included as a GET parameter) for overriding default token properties. By default, the server creates an owner token with an expiration time of one hour.
-- `duration` (7200 seconds, or two hours): Use this property to set a time limit for the bot, as well as an expiration time for the room (if the server is creating one). This will not add an expiration time to an existing room. Expiration times in `token_properties` or `room_properties` will also take precedence over this value. You can set this property to `0` to disable timeouts, but this isn't recommended.
-- `bot_args` (none): A string containing any additional command-line args to pass to the bot.
-- `wait_for_bot` (true): Whether to wait for the bot to successfully join the room before returning a response from the server. If true, the server will start the bot script, then poll the room for up to 5 seconds to confirm the bot has joined the room. If it doesn't, the server will stop the bot and return a 500 response. If set to `false`, the server will start the bot, but immediately return a 200 response. This can be useful if the server is creating rooms for you, and you need the room URL to join the user to the room.
-- `redirect` (true): Instead of returning a 200 for GET requests, the server will return a 301 redirect to the ROOM_URL. This is handy for testing by creating a bot with a GET request directly in the browser. POST requests will never return redirects. Set to `false` to get 200 responses with info in a JSON object even for GET requests.

examples/server/daily-bot-manager.py

@@ -1,165 +0,0 @@
-import os
-import requests
-import urllib
-import subprocess
-import time
-
-from flask import Flask, jsonify, redirect, request
-from flask_cors import CORS
-
-from dotenv import load_dotenv
-load_dotenv(override=True)
-
-app = Flask(__name__)
-CORS(app)
-
-APPS = {
-    "chatbot": "../starter-apps/chatbot.py",
-    "patient-intake": "../starter-apps/patient-intake.py",
-    "storybot": "../starter-apps/storybot.py",
-    "translator": "../starter-apps/translator.py"
-}
-
-daily_api_key = os.getenv("DAILY_API_KEY")
-api_path = os.getenv("DAILY_API_PATH") or "https://api.daily.co/v1"
-
-
-def get_room_name(room_url):
-    return urllib.parse.urlparse(room_url).path[1:]
-
-
-def create_room(room_properties, exp):
-    room_props = {
-        "exp": exp,
-        "enable_chat": True,
-        "enable_emoji_reactions": True,
-        "eject_at_room_exp": True,
-        "enable_prejoin_ui": False,
-        "enable_recording": "cloud"
-    }
-    if room_properties:
-        room_props |= room_properties
-
-    res = requests.post(
-        f"{api_path}/rooms",
-        headers={"Authorization": f"Bearer {daily_api_key}"},
-        json={
-            "properties": room_props
-        },
-    )
-    if res.status_code != 200:
-        raise Exception(f"Unable to create room: {res.text}")
-
-    room_url = res.json()["url"]
-    room_name = res.json()["name"]
-    return (room_url, room_name)
-
-
-def create_token(room_name, token_properties, exp):
-    token_props = {"exp": exp, "is_owner": True}
-    if token_properties:
-        token_props |= token_properties
-    # Force the token to be limited to the room
-    token_props |= {"room_name": room_name}
-    res = requests.post(
-        f'{api_path}/meeting-tokens',
-        headers={
-            'Authorization': f'Bearer {daily_api_key}'},
-        json={
-            'properties': token_props})
-    if res.status_code != 200:
-        if res.status_code != 200:
-            raise Exception(f"Unable to create meeting token: {res.text}")
-
-    meeting_token = res.json()['token']
-    return meeting_token
-
-
-def start_bot(*, bot_path, room_url, token, bot_args, wait_for_bot):
-
-    room_name = get_room_name(room_url)
-    proc = subprocess.Popen(
-        [f"python {bot_path} -u {room_url} -t {token} -k {daily_api_key} {bot_args}"],
-        shell=True,
-        bufsize=1,
-    )
-
-    if wait_for_bot:
-        # Don't return until the bot has joined the room, but wait for at most 5
-        # seconds.
-        attempts = 0
-        while attempts < 50:
-            time.sleep(0.1)
-            attempts += 1
-            res = requests.get(
-                f"{api_path}/rooms/{room_name}/get-session-data",
-                headers={"Authorization": f"Bearer {daily_api_key}"},
-            )
-            if res.status_code == 200:
-                print(f"Took {attempts} attempts to join room {room_name}")
-                return True
-
-        # If we don't break from the loop, that means we never found the bot in the room
-        raise Exception("The bot was unable to join the room. Please try again.")
-
-    return True
-
-
-@app.route("/start/<string:botname>", methods=["GET", "POST"])
-def start(botname):
-    try:
-        if botname not in APPS:
-            raise Exception(f"Bot '{botname}' is not in the allowlist.")
-
-        bot_path = APPS[botname]
-        props = {
-            "room_url": None,
-            "room_properties": None,
-            "token_properties": None,
-            "bot_args": None,
-            "wait_for_bot": True,
-            "duration": None,
-            "redirect": True
-        }
-        props |= request.values.to_dict()  # gets URL params as well as plaintext POST body
-        try:
-            props |= request.json
-        except BaseException:
-            pass
-        if props['redirect'] == "false":
-            props['redirect'] = False
-        if props['wait_for_bot'] == "false":
-            props['wait_for_bot'] = False
-
-        duration = int(os.getenv("DAILY_BOT_DURATION") or 7200)
-        if props['duration']:
-            duration = props['duration']
-        exp = time.time() + duration
-        if (props['room_url']):
-            room_url = props['room_url']
-            try:
-                room_name = get_room_name(room_url)
-            except ValueError:
-                raise Exception(
-                    "There was a problem detecting the room name. Please double-check the value of room_url.")
-        else:
-            room_url, room_name = create_room(props['room_properties'], exp)
-        token = create_token(room_name, props['token_properties'], exp)
-        bot = start_bot(
-            room_url=room_url,
-            bot_path=bot_path,
-            token=token,
-            bot_args=props['bot_args'],
-            wait_for_bot=props['wait_for_bot'])
-
-        if props['redirect'] and request.method == "GET":
-            return redirect(room_url, 302)
-        else:
-            return jsonify({"room_url": room_url, "token": token})
-    except BaseException as e:
-        return f"There was a problem starting the bot: {e}", 500
-
-
-@app.route("/healthz")
-def health_check():
-    return "ok", 200

examples/simple-chatbot/.gitignore

@@ -0,0 +1,161 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+runpod.toml

examples/simple-chatbot/Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.10-bullseye
+
+RUN mkdir /app
+RUN mkdir /app/assets
+RUN mkdir /app/utils
+COPY *.py /app/
+COPY requirements.txt /app/
+copy assets/* /app/assets/
+copy utils/* /app/utils/
+
+WORKDIR /app
+RUN pip3 install -r requirements.txt
+
+EXPOSE 7860
+
+CMD ["python3", "server.py"]

examples/simple-chatbot/README.md

@@ -0,0 +1,37 @@
+# Simple Chatbot
+
+<img src="image.png" width="420px">
+
+This app connects you to a chatbot powered by GPT-4, complete with animations generated by Stable Video Diffusion.
+
+See a video of it in action: https://x.com/kwindla/status/1778628911817183509
+
+And a quick video walkthrough of the code: https://www.loom.com/share/13df1967161f4d24ade054e7f8753416
+
+ℹ️ The first time, things might take extra time to get started since VAD (Voice Activity Detection) model needs to be downloaded.
+
+## Get started
+
+```python
+python3 -m venv venv
+source venv/bin/activate
+pip install -r requirements.txt
+
+cp env.example .env # and add your credentials
+
+```
+
+## Run the server
+
+```bash
+python server.py
+```
+
+Then, visit `http://localhost:7860/start` in your browser to start a chatbot session.
+
+## Build and test the Docker image
+
+```
+docker build -t chatbot .
+docker run --env-file .env -p 7860:7860 chatbot
+```