Merge pull request #706 from pipecat-ai/jpt/modal-example

barebones modal.com deployment example

examples/deployment/modal-example/.gitignore

@@ -0,0 +1,91 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+dist/
+*.egg-info/
+*.egg
+.installed.cfg
+.eggs/
+downloads/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+MANIFEST
+
+# Virtual Environments
+venv/
+env/
+.env
+.venv/
+ENV/
+env.bak/
+venv.bak/
+
+# IDE
+.idea/
+.vscode/
+.spyderproject
+.spyproject
+.ropeproject
+
+# Testing and Coverage
+.coverage
+.coverage.*
+htmlcov/
+.pytest_cache/
+.tox/
+.nox/
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+cover/
+
+# Logs and Databases
+*.log
+*.db
+db.sqlite3
+db.sqlite3-journal
+pip-log.txt
+
+# System Files
+.DS_Store
+Thumbs.db
+desktop.ini
+*.swp
+*.swo
+*.bak
+*.tmp
+*~
+
+# Build and Documentation
+docs/_build/
+.pybuilder/
+target/
+instance/
+.webassets-cache
+.pdm.toml
+.pdm-python
+.pdm-build/
+__pypackages__/
+
+# Other
+*.mo
+*.pot
+*.sage.py
+.mypy_cache/
+.dmypy.json
+dmypy.json
+.pyre/
+.pytype/
+cython_debug/
+.ipynb_checkpoints

examples/deployment/modal-example/README.md

@@ -0,0 +1,37 @@
+# Deploying Pipecat to Modal.com
+
+Barebones deployment example for [modal.com](https://www.modal.com)
+
+1. Install dependencies
+
+```bash
+python -m venv venv
+source venv/bin/active # or OS equivalent
+pip install -r requirements.txt
+```
+
+2. Setup .env
+
+```bash
+cp env.example .env
+```
+
+Alternatively, you can configure your Modal app to use [secrets](https://modal.com/docs/guide/secrets)
+
+3. Test the app locally
+
+```bash
+modal serve app.py
+```
+
+4. Deploy to production
+
+```bash
+modal deploy app.py
+```
+
+## Configuration options
+
+This app sets some sensible defaults for reducing cold starts, such as `minkeep_warm=1`, which will keep at least 1 warm instance ready for your bot function.
+
+It has been configured to only allow a concurrency of 1 (`max_inputs=1`) as each user will require their own running function.

examples/deployment/modal-example/app.py

@@ -0,0 +1,75 @@
+import os
+
+import aiohttp
+import modal
+from fastapi import HTTPException
+from fastapi.responses import JSONResponse
+from loguru import logger
+
+from bot import _voice_bot_process
+
+MAX_SESSION_TIME = 15 * 60  # 15 minutes
+
+app = modal.App("pipecat-modal")
+
+
+image = modal.Image.debian_slim(python_version="3.12").pip_install_from_requirements(
+    "requirements.txt"
+)
+
+
+@app.function(
+    image=image,
+    cpu=1.0,
+    secrets=[modal.Secret.from_dotenv()],
+    keep_warm=1,
+    enable_memory_snapshot=True,
+    max_inputs=1,  # Do not reuse instances across requests
+    retries=0,
+)
+def launch_bot_process(room_url: str, token: str):
+    _voice_bot_process(room_url, token)
+
+
+@app.function(
+    image=image,
+    secrets=[modal.Secret.from_dotenv()],
+)
+@modal.web_endpoint(method="POST")
+async def start():
+    from pipecat.transports.services.helpers.daily_rest import (
+        DailyRESTHelper,
+        DailyRoomParams,
+    )
+
+    logger.info("Request received")
+
+    async with aiohttp.ClientSession() as session:
+        daily_rest_helper = DailyRESTHelper(
+            daily_api_key=os.getenv("DAILY_API_KEY", ""),
+            daily_api_url=os.getenv("DAILY_API_URL", "https://api.daily.co/v1"),
+            aiohttp_session=session,
+        )
+
+        # Create new Daily room
+        room = await daily_rest_helper.create_room(DailyRoomParams())
+        if not room.url:
+            raise HTTPException(
+                status_code=500,
+                detail="Unable to create room",
+            )
+        logger.info(f"Created room: {room.url}")
+
+        # Create bot token for room
+        token = await daily_rest_helper.get_token(room.url, MAX_SESSION_TIME)
+        if not token:
+            raise HTTPException(status_code=500, detail=f"Failed to get token for room: {room.url}")
+
+        logger.info(f"Bot token created: {token}")
+
+        # Spawn a new bot process
+        launch_bot_process.spawn(room_url=room.url, token=token)
+
+        # Return room URL to the user to join
+        # Note: in production, you would want to return a token to the user
+        return JSONResponse(content={"room_url": room.url, token: token})

examples/deployment/modal-example/bot.py

@@ -0,0 +1,90 @@
+import asyncio
+import os
+import sys
+
+from dotenv import load_dotenv
+from loguru import logger
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main(room_url: str, token: str):
+    from pipecat.audio.vad.silero import SileroVADAnalyzer
+    from pipecat.frames.frames import EndFrame, LLMMessagesFrame
+    from pipecat.pipeline.pipeline import Pipeline
+    from pipecat.pipeline.runner import PipelineRunner
+    from pipecat.pipeline.task import PipelineParams, PipelineTask
+    from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+    from pipecat.services.cartesia import CartesiaTTSService
+    from pipecat.services.openai import OpenAILLMService
+    from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+    transport = DailyTransport(
+        room_url,
+        token,
+        "bot",
+        DailyParams(
+            audio_out_enabled=True,
+            transcription_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+        ),
+    )
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY", ""), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22"
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
+
+    @transport.event_handler("on_first_participant_joined")
+    async def on_first_participant_joined(transport, participant):
+        await transport.capture_participant_transcription(participant["id"])
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMMessagesFrame(messages)])
+
+    @transport.event_handler("on_participant_left")
+    async def on_participant_left(transport, participant, reason):
+        await task.queue_frame(EndFrame())
+
+    runner = PipelineRunner()
+
+    await runner.run(task)
+
+
+def _voice_bot_process(room_url: str, token: str):
+    asyncio.run(main(room_url, token))

examples/deployment/modal-example/env.example

@@ -0,0 +1,3 @@
+DAILY_API_KEY=
+OPENAI_API_KEY=
+CARTESIA_API_KEY=

examples/deployment/modal-example/requirements.txt

@@ -0,0 +1,5 @@
+python-dotenv==1.0.1
+modal==0.65.48
+pipecat-ai[daily,silero,cartesia,openai]==0.0.48
+fastapi==0.115.4
+aiohttp==3.10.10