From eb9ec292c47dabf97126ee40335fb156e8215439 Mon Sep 17 00:00:00 2001
From: Mert Sefa AKGUN <git@msakg.com>
Date: Tue, 7 Jan 2025 13:44:24 +0300
Subject: [PATCH] feat(examples): add Gemini multimodal live text example

Introduce a new example `26d-gemini-multimodal-live-text.py` to
demonstrate the use of GeminiMultimodalLiveLLMService with text-only
responses. This example sets up a pipeline for audio input via DailyTransport,
processing with Gemini, and output via Cartesia TTS.
---
 .../26d-gemini-multimodal-live-text.py        | 85 +++++++++++++++++++
 1 file changed, 85 insertions(+)
 create mode 100644 examples/foundational/26d-gemini-multimodal-live-text.py

diff --git a/examples/foundational/26d-gemini-multimodal-live-text.py b/examples/foundational/26d-gemini-multimodal-live-text.py
new file mode 100644
index 000000000..5e43e19bb
--- /dev/null
+++ b/examples/foundational/26d-gemini-multimodal-live-text.py
@@ -0,0 +1,85 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
+from agent.services.tts.cartesia_multilingual import CartesiaMultiLingualTTSService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_in_sample_rate=16000,
+                audio_out_sample_rate=24000,
+                audio_out_enabled=True,
+                vad_enabled=True,
+                vad_audio_passthrough=True,
+                # set stop_secs to something roughly similar to the internal setting
+                # of the Multimodal Live api, just to align events. This doesn't really
+                # matter because we can only use the Multimodal Live API's phrase
+                # endpointing, for now.
+                vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+            ),
+        )
+
+        llm = GeminiMultimodalLiveLLMService(
+            api_key=os.getenv("GOOGLE_API_KEY"),
+            # system_instruction="Talk like a pirate."
+        )
+        llm.set_model_only_text()  # This forces model to produce text only responses
+
+        tts = CartesiaMultiLingualTTSService(api_key=os.getenv("CARTESIA_API_KEY"))
+
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                llm,
+                tts,
+                transport.output(),
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+            ),
+        )
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())