wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

function calling testing and improvements

Browse Source
This commit is contained in:
Kwindla Hultman Kramer
2024-09-30 20:59:28 -07:00
parent 47b943a117
commit 0d5cb84531
8 changed files with 167 additions and 447 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
examples/foundational/07l-interruptible-together.py
View File

@@ -67,7 +67,7 @@ async def main():
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.",
"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 in plain language. Respond to what the user said in a creative and helpful way.",
},
]
@@ -87,7 +87,12 @@ async def main():
]
)
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
task = PipelineTask(
pipeline,
PipelineParams(
allow_interruptions=True, enable_metrics=True, enable_usage_metrics=True
),
)
@transport.event_handler("on_first_participant_joined")
async def on_first_participant_joined(transport, participant):

7
examples/foundational/14-function-calling.py
View File

@@ -9,11 +9,9 @@ import aiohttp
import os
import sys
from pipecat.frames.frames import TextFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.processors.logger import FrameLogger
from pipecat.services.cartesia import CartesiaTTSService
from pipecat.services.openai import OpenAILLMContext, OpenAILLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
@@ -72,9 +70,6 @@ async def main():
# sent to the same callback with an additional function_name parameter.
llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)
fl_in = FrameLogger("Inner")
fl_out = FrameLogger("Outer")
tools = [
ChatCompletionToolParam(
type="function",
@@ -111,11 +106,9 @@ async def main():
pipeline = Pipeline(
[
# fl_in,
transport.input(),
context_aggregator.user(),
llm,
# fl_out,
tts,
transport.output(),
context_aggregator.assistant(),

0
examples/foundational/19a-tools-anthropic.py → examples/foundational/14a-function-calling-anthropic.py
View File

0
examples/foundational/19b-tools-video-anthropic.py → examples/foundational/14b-function-calling-anthropic-video.py
View File

136
examples/foundational/14c-function-calling-together.py Normal file
View File

@@ -0,0 +1,136 @@
#
# Copyright (c) 2024, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import asyncio
import aiohttp
import os
import sys
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.services.cartesia import CartesiaTTSService
from pipecat.services.openai import OpenAILLMContext
from pipecat.services.together import TogetherLLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
from pipecat.vad.silero import SileroVADAnalyzer
from openai.types.chat import ChatCompletionToolParam
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 start_fetch_weather(function_name, llm, context):
# note: we can't push a frame to the LLM here. the bot
# can interrupt itself and/or cause audio overlapping glitches.
# possible question for Aleix and Chad about what the right way
# to trigger speech is, now, with the new queues/async/sync refactors.
# await llm.push_frame(TextFrame("Let me check on that."))
logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
await result_callback({"conditions": "nice", "temperature": "75"})
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
)
llm = TogetherLLMService(
api_key=os.getenv("TOGETHER_API_KEY"),
model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
)
# Register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.
llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)
tools = [
ChatCompletionToolParam(
type="function",
function={
"name": "get_current_weather",
"description": "Get the current weather",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Infer this from the users location.",
},
},
"required": ["location", "format"],
},
},
)
]
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, tools)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
llm,
tts,
transport.output(),
context_aggregator.assistant(),
]
)
task = PipelineTask(pipeline)
@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 tts.say("Hi! Ask me about the weather in San Francisco.")
runner = PipelineRunner()
await runner.run(task)
if __name__ == "__main__":
asyncio.run(main())

137
examples/foundational/19c-tools-togetherai.py
View File

@@ -1,137 +0,0 @@
#
# 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.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia import CartesiaTTSService
from pipecat.services.together import TogetherLLMService
from pipecat.transports.services.daily import DailyParams, DailyTransport
from pipecat.vad.silero import SileroVADAnalyzer
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, llm, 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
)
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())