examples: document how to log chats

examples/voice-assistant/log_transcriptions.py

@@ -0,0 +1,84 @@
+import asyncio
+from datetime import datetime
+
+from aiofile import async_open as open
+from dotenv import load_dotenv
+from livekit import rtc
+from livekit.agents import AutoSubscribe, JobContext, WorkerOptions, cli, llm
+from livekit.agents.voice_assistant import VoiceAssistant
+from livekit.plugins import deepgram, openai, silero
+
+load_dotenv()
+
+
+async def entrypoint(ctx: JobContext):
+    initial_ctx = llm.ChatContext().append(
+        role="system",
+        text=(
+            "You are a voice assistant created by LiveKit. Your interface with users will be voice. "
+            "You should use short and concise responses, and avoiding usage of unpronouncable punctuation."
+        ),
+    )
+
+    await ctx.connect(auto_subscribe=AutoSubscribe.AUDIO_ONLY)
+
+    assistant = VoiceAssistant(
+        vad=silero.VAD.load(),
+        stt=deepgram.STT(),
+        llm=openai.LLM(),
+        tts=openai.TTS(),
+        chat_ctx=initial_ctx,
+    )
+    assistant.start(ctx.room)
+
+    # listen to incoming chat messages, only required if you'd like the agent to
+    # answer incoming messages from Chat
+    chat = rtc.ChatManager(ctx.room)
+
+    async def answer_from_text(txt: str):
+        chat_ctx = assistant.chat_ctx.copy()
+        chat_ctx.append(role="user", text=txt)
+        stream = assistant.llm.chat(chat_ctx=chat_ctx)
+        await assistant.say(stream)
+
+    @chat.on("message_received")
+    def on_chat_received(msg: rtc.ChatMessage):
+        if msg.message:
+            asyncio.create_task(answer_from_text(msg.message))
+
+    log_queue = asyncio.Queue()
+
+    @assistant.on("user_speech_committed")
+    def on_user_speech_committed(msg: llm.ChatMessage):
+        # convert string lists to strings, drop images
+        if isinstance(msg.content, list):
+            msg.content = "\n".join(
+                "[image]" if isinstance(x, llm.ChatImage) else x for x in msg
+            )
+        log_queue.put_nowait(f"[{datetime.now()}] USER:\n{msg.content}\n\n")
+
+    @assistant.on("agent_speech_committed")
+    def on_agent_speech_committed(msg: llm.ChatMessage):
+        log_queue.put_nowait(f"[{datetime.now()}] AGENT:\n{msg.content}\n\n")
+
+    async def write_transcription():
+        async with open("transcriptions.log", "w") as f:
+            while True:
+                msg = await log_queue.get()
+                if msg is None:
+                    break
+                await f.write(msg)
+
+    write_task = asyncio.create_task(write_transcription())
+
+    async def finish_queue():
+        log_queue.put_nowait(None)
+        await write_task
+
+    ctx.add_shutdown_callback(finish_queue)
+
+    await assistant.say("Hey, how can I help you today?", allow_interruptions=True)
+
+
+if __name__ == "__main__":
+    cli.run_app(WorkerOptions(entrypoint_fnc=entrypoint))

examples/voice-assistant/requirements.txt

@@ -2,4 +2,5 @@ livekit-agents>=0.8.8
 livekit-plugins-openai>=0.8.1
 livekit-plugins-deepgram>=0.6.5
 livekit-plugins-silero>=0.6.4
-python-dotenv~=1.0
+python-dotenv~=1.0
+aiofile~=3.8.8