AI Agents Loop异步执行可视化Tutorial 借助AgentBoard工具可视化工作流

            prompt = "Can you give me an example of python code usage of async await functions"
            messages.append({"role": "user", "content": prompt})

            completion = client.chat.completions.create(
                model="gpt-3.5-turbo",
                messages=[
                    {"role": "system", "content": "You are a helpful assistant."},
                    {"role": "user", "content": prompt}
                ]
            )
            response_message = completion.choices[0].message
            print(response_message) # {"role":"xxx", "content":"xxx"}

            messages.append(response_message)

    client = Anthropic()
    MODEL_NAME = "claude-3-opus-20240229"

    
    response = client.messages.create(
                model=MODEL_NAME,
                max_tokens=4096,
                messages=[
                    {"role": "user", "content": user_message},
                    {"role": "assistant", "content": message.content},
                    {
                        "role": "user",
                        "content": [
                            {
                                "type": "tool_result",
                                "tool_use_id": tool_use.id,
                                "content": tool_result,
                            }
                        ],
                    },
                ],
                tools=tools,
            )

    async def run_loop(self):

        try:
            print ("%s|%s|run_loop start|0" % (self.name, get_current_datetime()))

            plan_duration = await self.plan()
            print ("%s|%s|Plan Complete|%s" % (self.name, get_current_datetime(), plan_duration))

            act_duration = await self.act()
            print ("%s|%s|Act Complete|%s" % (self.name, get_current_datetime(), act_duration))

            reflect_duration = await self.reflect()
            print ("%s|%s|Reflect Complete|%s" % (self.name, get_current_datetime(), reflect_duration))

            total_duration = plan_duration + act_duration + reflect_duration

            return "%s|%s|run_loop complete|%s" % (self.name, get_current_datetime(), total_duration)
        except Exception as e:
            print (e)
            print (traceback.print_exc())
            return "%s|%s|run_loop complete|%s" % (self.name, get_current_datetime(), 0)

import time
import agentboard as ab
from agentboard.utils import function_to_schema

from AutoAgent.core import AsyncAgent, AsyncAutoEnv
from AutoAgent.utils import get_current_datetime

class AutoAgentWorkflow(AsyncAgent):
    """
        Agent who can plan a day and write blog/posts videos on the website
        execute cycle: plan->act->reflect
    """
    async def run_loop(self):

        try:

            ## PLAN
            plan_duration = await self.plan()
            print ("%s|%s|PLAN Complete|%s" % (self.name, get_current_datetime(), plan_duration))

            ## ACT 
            act_duration = await self.act()
            print ("%s|%s|ACT Complete|%s" % (self.name, get_current_datetime(), act_duration))

            ## REFLECT
            reflect_duration = await self.reflect()
            print ("%s|%s|REFLECTION Complete|%s" % (self.name, get_current_datetime(), reflect_duration))

            total_duration = plan_duration + act_duration + reflect_duration
            print ("%s|%s|END|%s" % (self.name, get_current_datetime(), 0))

            return "%s|%s|run_loop complete|%s" % (self.name, get_current_datetime(), total_duration)
        except Exception as e:
            print (e)
            return "%s|%s|run_loop complete|%s" % (self.name, get_current_datetime(), 0)

def get_openai_client():
    from openai import OpenAI
    client = OpenAI(api_key="")
    return client

def run_async_agents_env_agentboard():
    """
    """

    agent1_prompt = """You are playing the role of a Web admin agent... """
    agent2_prompt = """You are playing the role of a Automatic reply agent..."""

    agent_1 = AutoAgentWorkflow(name="agent 1", instructions=agent1_prompt)
    agent_2 = AutoAgentWorkflow(name="agent 2", instructions=agent2_prompt)

    agents = [agent_1, agent_2]
    env = AsyncAutoEnv(get_openai_client(), agents=agents)
    results = env.run()

if __name__ == "__main__":
    run_async_agents_env_agentboard()

ab.summary.agent_loop(name="START", data="This is start stage of %s" % self.name, agent_name = self.name, process_id="START", workflow_type="start", duration = 0)
ab.summary.agent_loop(name="END", data="This is end stage of %s" % self.name, process_id="END", agent_name = self.name, workflow_type="end", duration = total_duration)

## ACT stage
ab.summary.agent_loop(name="INPUT", data="This is Act Input of %s" % self.name, agent_name = self.name, process_id="ACT", duration = 0)

act_duration = await self.act()

ab.summary.agent_loop(name="EXECUTION", data="This is ACT Execution Input of %s" % self.name, agent_name = self.name, process_id="ACT", duration = act_duration)

ab.summary.agent_loop(name="OUTPUT", data="This is ACT Output of %s" % self.name, agent_name = self.name, process_id="ACT", duration = 0)

## add a decision node log
ab.summary.agent_loop(name="DECISION", data="This is decision stage of %s" % self.name, process_id="DECISION", agent_name = self.name, workflow_type = "decision", duration = 0)

## 执行异步流程，打印到本地日志 ./log 目录下
python run_agentboard_autoagent.py

## 命令行启动agentboard 可视化流程置顶 logdir
agentboard --logdir=./log