Anthropic tool use core Pipecat pieces refactored (#369)

* processors(rtvi): rtvi 0.1 message protocol * added a single function call handler * wip - function calling * fixup * fixup * fixup * processors(rtvi): no need for configure_on_start() * processors(rtvi): add new option values if they haven't been set yet * Add the model name to the LLM usage metrics * wip - anthropic tool calling * still wip - anthropic tool use and vision * anthropic tools and vision working * anthropic tool calling and vision * Cartesia error handling * Anthropic tool use core Pipecat pieces refactored as per plan * aleix has good ideas * Usage metrics for Anthropic LLMs * fix function call result state not getting cleared bug * Pass **kwargs through from AnthropicLLMService constructor * about to tinker with anthropic * added openai function calling * openai function calling * fixup --------- Co-authored-by: Aleix Conchillo Flaqué <aleix@daily.co> Co-authored-by: Chad Bailey <chadbailey@gmail.com> Co-authored-by: mattie ruth backman <mattieruth@gmail.com> Co-authored-by: chadbailey59 <chadbailey59@users.noreply.github.com>
2024-08-13 11:01:24 -07:00
parent a42d0c9907
commit 29ca1b7855
13 changed files with 1009 additions and 142 deletions
--- a/examples/foundational/19a-tools-anthropic.py
+++ b/examples/foundational/19a-tools-anthropic.py
@@ -0,0 +1,120 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+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.anthropic import AnthropicLLMService, AnthropicUserContextAggregator, AnthropicAssistantContextAggregator
+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_weather(function_name, tool_call_id, arguments, context, result_callback):
+    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 = AnthropicLLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="claude-3-5-sonnet-20240620"
+        )
+        llm.register_function("get_weather", get_weather)
+
+        tools = [
+            {
+                "name": "get_weather",
+                "description": "Get the current weather in a given location",
+                "input_schema": {
+                    "type": "object",
+                    "properties": {
+                        "location": {
+                            "type": "string",
+                            "description": "The city and state, e.g. San Francisco, CA",
+                        }
+                    },
+                    "required": ["location"],
+                },
+            }
+        ]
+
+        # todo: test with very short initial user message
+
+        messages = [{"role": "system",
+                     "content": "You are a helpful assistant who can report the weather in any location in the universe. Respond concisely. Your response will be turned into speech so use only simple words and punctuation."},
+                    {"role": "user",
+                     "content": " Start the conversation by introducing yourself."}]
+
+        context = OpenAILLMContext(messages, tools)
+        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())