pipecat-ai 0.0.9__tar.gz

pipecat_ai-0.0.9/.dockerignore

@@ -0,0 +1,30 @@
+# flyctl launch added from .gitignore
+**/.vscode
+**/env
+**/__pycache__
+**/*~
+**/venv
+#*#
+
+# 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
+**/.DS_Store
+**/.env
+fly.toml

pipecat_ai-0.0.9/.github/workflows/build.yaml

@@ -0,0 +1,44 @@
+name: build
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - "**"
+    paths-ignore:
+      - "docs/**"
+
+concurrency:
+  group: build-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build:
+    name: "Build and Install"
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        id: setup_python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+      - name: Setup virtual environment
+        run: |
+          python -m venv .venv
+      - name: Install basic Python dependencies
+        run: |
+          source .venv/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r dev-requirements.txt
+      - name: Build project
+        run: |
+          source .venv/bin/activate
+          python -m build
+      - name: Install project and other Python dependencies
+        run: |
+          source .venv/bin/activate
+          pip install --editable .

pipecat_ai-0.0.9/.github/workflows/lint.yaml

@@ -0,0 +1,44 @@
+name: lint
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - "**"
+    paths-ignore:
+      - "docs/**"
+
+concurrency:
+  group: build-lint-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  autopep8:
+    name: "Formatting lints"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+      - name: Setup virtual environment
+        run: |
+          python -m venv .venv
+      - name: Install development Python dependencies
+        run: |
+          source .venv/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r dev-requirements.txt
+      - name: autopep8
+        id: autopep8
+        run: |
+          source .venv/bin/activate
+          autopep8 --max-line-length 100 --exit-code -r -d --exclude "*_pb2.py" -a -a src/
+      - name: Fail if autopep8 requires changes
+        if: steps.autopep8.outputs.exit-code == 2
+        run: exit 1

pipecat_ai-0.0.9/.github/workflows/publish.yaml

@@ -0,0 +1,84 @@
+name: publish
+
+on:
+  workflow_dispatch:
+    inputs:
+      gitref:
+        type: string
+        description: "what git ref to build"
+        required: true
+
+jobs:
+  build:
+    name: "Build and upload wheels"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.inputs.gitref }}
+      - name: Set up Python
+        id: setup_python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+      - name: Setup virtual environment
+        run: |
+          python -m venv .venv
+      - name: Install basic Python dependencies
+        run: |
+          source .venv/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r dev-requirements.txt
+      - name: Build project
+        run: |
+          source .venv/bin/activate
+          python -m build
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels
+          path: ./dist
+
+  publish-to-pypi:
+    name: "Publish to PyPI"
+    runs-on: ubuntu-latest
+    needs: [ build ]
+    environment:
+      name: pypi
+      url: https://pypi.org/p/pipecat-ai
+    permissions:
+      id-token: write
+    steps:
+      - name: Download wheels
+        uses: actions/download-artifact@v4
+        with:
+          name: wheels
+          path: ./dist
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          verbose: true
+          print-hash: true
+
+  publish-to-test-pypi:
+    name: "Publish to Test PyPI"
+    runs-on: ubuntu-latest
+    needs: [ build ]
+    environment:
+      name: testpypi
+      url: https://pypi.org/p/pipecat-ai
+    permissions:
+      id-token: write
+    steps:
+      - name: Download wheels
+        uses: actions/download-artifact@v4
+        with:
+          name: wheels
+          path: ./dist
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          verbose: true
+          print-hash: true
+          repository-url: https://test.pypi.org/legacy/

pipecat_ai-0.0.9/.github/workflows/publish_test.yaml

@@ -0,0 +1,63 @@
+name: publish-test
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    name: "Build and upload wheels"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.inputs.gitref }}
+          fetch-tags: true
+          fetch-depth: 100
+      - name: Set up Python
+        id: setup_python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+      - name: Setup virtual environment
+        run: |
+          python -m venv .venv
+      - name: Install basic Python dependencies
+        run: |
+          source .venv/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r dev-requirements.txt
+      - name: Build project
+        run: |
+          source .venv/bin/activate
+          python -m build
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels
+          path: ./dist
+
+  publish-to-pypi:
+    name: "Publish to Test PyPI"
+    runs-on: ubuntu-latest
+    needs: [ build ]
+    environment:
+      name: testpypi
+      url: https://pypi.org/p/pipecat-ai
+    permissions:
+      id-token: write
+    steps:
+      - name: Download wheels
+        uses: actions/download-artifact@v4
+        with:
+          name: wheels
+          path: ./dist
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          verbose: true
+          print-hash: true
+          repository-url: https://test.pypi.org/legacy/

pipecat_ai-0.0.9/.github/workflows/tests.yaml

@@ -0,0 +1,49 @@
+name: test
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - "**"
+    paths-ignore:
+      - "docs/**"
+
+concurrency:
+  group: build-test-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    name: "Unit and Integration Tests"
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        id: setup_python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+      - name: Cache virtual environment
+        uses: actions/cache@v3
+        with:
+          # We are hashing requirements-dev.txt and requirements-extra.txt which
+          # contain all dependencies needed to run the tests and examples.
+          key: venv-${{ runner.os }}-${{ steps.setup_python.outputs.python-version}}-${{ hashFiles('linux-py3.10-requirements.txt') }}-${{ hashFiles('dev-requirements.txt') }}
+          path: .venv
+      - name: Install system packages
+        run: sudo apt-get install -y portaudio19-dev
+      - name: Setup virtual environment
+        run: |
+          python -m venv .venv
+      - name: Install basic Python dependencies
+        run: |
+          source .venv/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r linux-py3.10-requirements.txt -r dev-requirements.txt
+      - name: Test with pytest
+        run: |
+          source .venv/bin/activate
+          pytest --doctest-modules --ignore-glob="*to_be_updated*" src tests

pipecat_ai-0.0.9/.gitignore

@@ -0,0 +1,30 @@
+.vscode
+env/
+__pycache__/
+*~
+venv
+.venv
+#*#
+
+# 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
+.DS_Store
+.env
+fly.toml

pipecat_ai-0.0.9/Dockerfile

@@ -0,0 +1,40 @@
+# setup
+FROM python:3.11.5
+
+WORKDIR /app
+COPY requirements.txt /app
+COPY *.py /app
+COPY pyproject.toml /app
+
+COPY src/ /app/src/
+COPY examples/ /app/examples/
+
+WORKDIR /app
+RUN ls --recursive /app/
+RUN pip3 install --upgrade -r requirements.txt
+RUN python -m build .
+RUN pip3 install .
+RUN pip3 install gunicorn
+# If running on Ubuntu, Azure TTS requires some extra config
+# https://learn.microsoft.com/en-us/azure/ai-services/speech-service/quickstarts/setup-platform?pivots=programming-language-python&tabs=linux%2Cubuntu%2Cdotnetcli%2Cdotnet%2Cjre%2Cmaven%2Cnodejs%2Cmac%2Cpypi
+
+RUN wget -O - https://www.openssl.org/source/openssl-1.1.1w.tar.gz | tar zxf -
+WORKDIR openssl-1.1.1w
+RUN ./config --prefix=/usr/local
+RUN make -j $(nproc)
+RUN make install_sw install_ssldirs
+RUN ldconfig -v
+ENV SSL_CERT_DIR=/etc/ssl/certs
+
+#ENV LD_LIBRARY_PATH=/usr/local/lib:$LD_LIBRARY_PATH
+RUN apt clean
+RUN apt-get update
+RUN apt-get -y install build-essential libssl-dev ca-certificates libasound2 wget
+
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+EXPOSE 8000
+# run
+CMD ["gunicorn", "--workers=2", "--log-level", "debug", "--chdir", "examples/server", "--capture-output", "daily-bot-manager:app", "--bind=0.0.0.0:8000"]

pipecat_ai-0.0.9/LICENSE

@@ -0,0 +1,24 @@
+BSD 2-Clause License
+
+Copyright (c) 2024, Daily
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

pipecat_ai-0.0.9/PKG-INFO

@@ -0,0 +1,274 @@
+Metadata-Version: 2.1
+Name: pipecat-ai
+Version: 0.0.9
+Summary: An open source framework for voice (and multimodal) assistants
+License: BSD 2-Clause License
+Project-URL: Source, https://github.com/pipecat-ai/pipecat
+Project-URL: Website, https://pipecat.ai
+Keywords: webrtc,audio,video,ai
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Topic :: Communications :: Conferencing
+Classifier: Topic :: Multimedia :: Sound/Audio
+Classifier: Topic :: Multimedia :: Video
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: aiohttp~=3.9.5
+Requires-Dist: numpy~=1.26.4
+Requires-Dist: loguru~=0.7.0
+Requires-Dist: Pillow~=10.3.0
+Requires-Dist: typing-extensions~=4.11.0
+Provides-Extra: anthropic
+Requires-Dist: anthropic~=0.25.7; extra == "anthropic"
+Provides-Extra: azure
+Requires-Dist: azure-cognitiveservices-speech~=1.37.0; extra == "azure"
+Provides-Extra: daily
+Requires-Dist: daily-python~=0.7.4; extra == "daily"
+Provides-Extra: examples
+Requires-Dist: python-dotenv~=1.0.0; extra == "examples"
+Requires-Dist: flask~=3.0.3; extra == "examples"
+Requires-Dist: flask_cors~=4.0.1; extra == "examples"
+Provides-Extra: fal
+Requires-Dist: fal-client~=0.4.0; extra == "fal"
+Provides-Extra: fireworks
+Requires-Dist: openai~=1.26.0; extra == "fireworks"
+Provides-Extra: local
+Requires-Dist: pyaudio~=0.2.0; extra == "local"
+Provides-Extra: moondream
+Requires-Dist: einops~=0.8.0; extra == "moondream"
+Requires-Dist: timm~=0.9.16; extra == "moondream"
+Requires-Dist: transformers~=4.40.2; extra == "moondream"
+Provides-Extra: openai
+Requires-Dist: openai~=1.26.0; extra == "openai"
+Provides-Extra: playht
+Requires-Dist: pyht~=0.0.28; extra == "playht"
+Provides-Extra: silero
+Requires-Dist: torch~=2.3.0; extra == "silero"
+Requires-Dist: torchaudio~=2.3.0; extra == "silero"
+Provides-Extra: websocket
+Requires-Dist: websockets~=12.0; extra == "websocket"
+Provides-Extra: whisper
+Requires-Dist: faster-whisper~=1.0.2; extra == "whisper"
+
+<div align="center">
+ <img alt="pipecat" width="300px" height="auto" src="pipecat.png">
+</div>
+
+# Pipecat
+
+[![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)
+
+`pipecat` is a framework for building voice (and multimodal) conversational agents. Things like personal coaches, meeting assistants, story-telling toys for kids, customer support bots, and snarky social companions.
+
+Build things like this:
+
+[![AI-powered voice patient intake for healthcare](https://img.youtube.com/vi/lDevgsp9vn0/0.jpg)](https://www.youtube.com/watch?v=lDevgsp9vn0)
+
+## Getting started with voice agents
+
+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.
+
+```shell
+# install the module
+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:
+
+```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`
+
+## A simple voice agent running locally
+
+If you’re doing AI-related stuff, you probably have an OpenAI API key.
+
+To generate voice output, one service that’s easy to get started with is ElevenLabs. If you don’t already have an ElevenLabs developer account, you can sign up for one [here].
+
+So let’s run a really simple agent that’s just a GPT-4 prompt, wired up to voice input and speaker output.
+
+You can change the prompt, in the code. The current prompt is “Tell me something interesting about the Roman Empire.”
+
+`cd examples/getting-started` to run the following examples …
+
+```shell
+# Talk to a local pipecat process with your voice. Specify GPT-4 as the LLM.
+
+export OPENAI_API_KEY=...
+export ELEVENLABS_API_KEY=...
+python ./local-mic.py | ./pipecat-pipes-gpt-4.py | ./local-speaker.py
+```
+
+## WebSockets instead of pipes
+
+To run your agent in the cloud, you can switch the Pipecat transport layer to use a WebSocket instead of Unix pipes.
+
+```shell
+# Talk to a local pipecat process with your voice. Specify GPT-4 as the LLM.
+
+export OPENAI_API_KEY=...
+export ELEVENLABS_API_KEY=...
+python ./local-mic-and-speaker-wss.py wss://localhost:8088
+```
+
+## 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.])
+
+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. Then run the examples, this time connecting via WebRTC instead of a WebSocket.
+
+```shell
+# 1. Run the pipecat process. Provide your Daily API key and a Daily room
+export DAILY_API_KEY=...
+export OPENAI_API_KEY=...
+export ELEVENLABS_API_KEY=...
+python pipecat-daily-gpt-4.py --daily-room https://example.daily.co/pipecat
+
+# 2. Visit the Daily room link in any web browser to talk to the pipecat process.
+#    You'll want to use a Daily SDK to embed the client-side code into your own
+#    app. But visiting the room URL in a browser is a quick way to start building
+#    agents because you can focus on just the agent code at first.
+open -a "Google Chrome" https://example.daily.co/pipecat
+```
+
+## Deploy your agent to the cloud
+Now that you’ve decoupled client and server, and have a Pipecat process that can run anywhere you can run Python, you can deploy this example agent to the cloud.
+
+`TBC`
+
+## Taking it further
+
+### Add a telephone number
+Daily supports telephone connections in addition to WebRTC streams. You can add a telephone number to your Daily room with the following REST API call. Once you’ve done that, you can call your agent on the phone.
+
+You’ll need to add a credit card to your Daily account to enable telephone numbers.
+
+`TBC`
+
+
+### Add image output
+
+Daily supports telephone connections in addition to WebRTC streams. You can add a telephone number to your Daily room with the following REST API call. Once you’ve done that, you can call your agent on the phone.
+
+You’ll need to add a credit card to your Daily account to enable telephone numbers.
+
+`TBC`
+
+### Add video output
+
+
+`TBC`
+
+
+## Code examples
+
+There are two directories of examples:
+
+- [foundational](https://github.com/daily-co/pipecat/tree/main/examples/foundational) — examples that build on each other, introducing one or two concepts at a time
+- [starter apps](https://github.com/daily-co/pipecat/tree/main/examples/starter-apps) — complete applications that you can use as starting points for development
+
+Before running the examples you need to install the dependencies (which will install all the dependencies to run all of the examples):
+
+```
+pip install -r {env}-requirements.txt
+```
+
+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:
+
+```
+python examples/foundational/02-llm-say-one-thing.py
+```
+
+## 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:_
+
+```
+python3 -m venv venv
+source venv/bin/activate
+```
+
+From the root of this repo, run the following:
+
+```
+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
+
+```
+pip install --editable .
+```
+
+If you want to use this package from another directory, you can run:
+
+```
+pip install path_to_this_repo
+```
+
+### Running tests
+
+From the root directory, run:
+
+```
+pytest --doctest-modules --ignore-glob="*to_be_updated*" src tests
+```
+
+## Setting up your editor
+
+This project uses strict [PEP 8](https://peps.python.org/pep-0008/) formatting.
+
+### Emacs
+
+You can use [use-package](https://github.com/jwiegley/use-package) to install [py-autopep8](https://codeberg.org/ideasman42/emacs-py-autopep8) package and configure `autopep8` arguments:
+
+```elisp
+(use-package py-autopep8
+  :ensure t
+  :defer t
+  :hook ((python-mode . py-autopep8-mode))
+  :config
+  (setq py-autopep8-options '("-a" "-a", "--max-line-length=100")))
+```
+
+`autopep8` was installed in the `venv` environment described before, so you should be able to use [pyvenv-auto](https://github.com/ryotaro612/pyvenv-auto) to automatically load that environment inside Emacs.
+
+```elisp
+(use-package pyvenv-auto
+  :ensure t
+  :defer t
+  :hook ((python-mode . pyvenv-auto-run)))
+
+```
+
+### Visual Studio Code
+
+Install the
+[autopep8](https://marketplace.visualstudio.com/items?itemName=ms-python.autopep8) extension. Then edit the user settings (_Ctrl-Shift-P_ `Open User Settings (JSON)`) and set it as the default Python formatter, enable formatting on save and configure `autopep8` arguments:
+
+```json
+"[python]": {
+    "editor.defaultFormatter": "ms-python.autopep8",
+    "editor.formatOnSave": true
+},
+"autopep8.args": [
+    "-a",
+    "-a",
+    "--max-line-length=100"
+],
+```