Service for together.ai, including Llama 3.1 function calling support

examples/foundational/19c-tools-togetherai.py

@@ -0,0 +1,137 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+import json
+
+from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.services.cartesia import CartesiaTTSService
+
+from pipecat.services.together import TogetherLLMService, TogetherContextAggregatorPair
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+
+
+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 get_current_weather(function_name, tool_call_id, arguments, context, result_callback):
+    logger.debug("IN get_current_weather")
+    location = arguments["location"]
+    await result_callback(f"The weather in {location} is currently 72 degrees and sunny.")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond 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",  # British Lady
+            sample_rate=16000,
+        )
+
+        llm = TogetherLLMService(
+            api_key=os.getenv("TOGETHER_API_KEY"),
+            model=os.getenv("TOGETHER_MODEL"),
+        )
+        llm.register_function("get_current_weather", get_current_weather)
+
+        weatherTool = {
+            "name": "get_current_weather",
+            "description": "Get the current weather in a given location",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "string",
+                        "description": "The city and state, e.g. San Francisco, CA",
+                    },
+                },
+                "required": ["location"],
+            },
+        }
+
+        system_prompt = f"""\
+You have access to the following functions:
+
+Use the function '{weatherTool["name"]}' to '{weatherTool["description"]}':
+{json.dumps(weatherTool)}
+
+If you choose to call a function ONLY reply in the following format with no prefix or suffix:
+
+<function=example_function_name>{{\"example_name\": \"example_value\"}}</function>
+
+Reminder:
+- Function calls MUST follow the specified format, start with <function= and end with </function>
+- Required parameters MUST be specified
+- Only call one function at a time
+- Put the entire function call reply on one line
+- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls
+
+"""
+
+        messages = [{"role": "system",
+                     "content": system_prompt},
+                    {"role": "user",
+                     "content": "Wait for the user to say something."}]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline([
+            transport.input(),               # Transport user input
+            context_aggregator.user(),       # User speech to text
+            llm,                             # LLM
+            tts,                             # TTS
+            transport.output(),              # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses and tool context
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
+
+        @ 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.
+            await task.queue_frames([LLMMessagesFrame(messages)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())