mirror of
https://github.com/FoundationAgents/MetaGPT.git
synced 2026-04-25 16:56:26 +02:00
1. SummarizeCode动作:用于基于代码进行总结,思考bug、逻辑、todo
2. CodeReview动作优化:目前强制要求回答问题,有更高的成功率了
1. 增加了LGTM/LBTM的回答,在LGTM时会及时停止,不重写代码
2. 目前增加了设置中的参数code_review_k_times,与reflexion类似,设置为2
3. 仍然有概率发生指令不遵循,尤其是会有比较高的概率发生同时review多个代码文件,还没想好怎么解决 #FIXME
3. 增加了env到Action结构中,现在可以直接调用环境接口了
4. WriteDesign:去除了对project_name的纠正代码,现在引导下可以一次生成对
1. 修改了提示词中的##格式,改为了JSON格式
2. 数据结构
1. Document的标准化:Env->Repo->Document,其中Document/Asset/Code都是Document
1. 原用于检索的Document改为IndexableDocument
2. Repo结构引入:用于Document装载与元数据装载
3. RepoParser引入:写了一个简单的AST parser(后续可能要换tree-sitter),给出了整库symbol
4. Env中增加了set/get/set_doc/get_doc接口,用于set/get单个变量或者一个Document。这个逻辑后续或许会进一步简化
3. 配置优化
1. 默认更换为gpt-4-1106-preview,以获得最好的效果与成本
2. 提供~/.metagpt作为配置最高优先级目录,从中读取config.yaml
3. workspace可以灵活指定了,在config中配置
4. project_name可以由命令行指定,并且改为由ProductManager生成
4. metagpt作为默认命令行,而非python startup.py
metagpt --help
metagpt --project-name game_2048 "make a 2048 game"
metagpt "make a 2048 game"
metagpt --project-name game_2048 --inc "将2048改为4096"
metagpt --project-name game_2048 --auto-inc "make a 2048 game"
1. 使用新的METAGPT_ROOT生成方式,而非寻找git,以便cli安装
2. 命令行由fire换为了typer,它会带来相对更好的体验
3. project_name可以灵活指定了,在metagpt命令行输入中配置
5. 其他
1. 现在支持多国语言了,中文已测试
2. BossRequirement -> UserRequirement
3. 大量错误文本的修正,增加了可读性
4. 中量提示词优化,稍微提升了一些准确率
5. 暂时屏蔽了LongtermMemory相关逻辑,这个逻辑底层调用了langchain的FAISS,会带来~5秒加载耗时
6. 修复了安装包中的部分描述错误
7. 去除了config中在openai_proxy设定时对base的重复修改,这个修改应该在openai初始化时发生
8. 修复了JSON在中文存储时的特定问题,ensure_ascii=False
109 lines
3.6 KiB
Python
109 lines
3.6 KiB
Python
'''
|
|
Filename: MetaGPT/examples/debate.py
|
|
Created Date: Tuesday, September 19th 2023, 6:52:25 pm
|
|
Author: garylin2099
|
|
'''
|
|
import asyncio
|
|
import platform
|
|
import fire
|
|
|
|
from metagpt.team import Team
|
|
from metagpt.actions import Action, UserRequirement
|
|
from metagpt.roles import Role
|
|
from metagpt.schema import Message
|
|
from metagpt.logs import logger
|
|
|
|
class SpeakAloud(Action):
|
|
"""Action: Speak out aloud in a debate (quarrel)"""
|
|
|
|
PROMPT_TEMPLATE = """
|
|
## BACKGROUND
|
|
Suppose you are {name}, you are in a debate with {opponent_name}.
|
|
## DEBATE HISTORY
|
|
Previous rounds:
|
|
{context}
|
|
## YOUR TURN
|
|
Now it's your turn, you should closely respond to your opponent's latest argument, state your position, defend your arguments, and attack your opponent's arguments,
|
|
craft a strong and emotional response in 80 words, in {name}'s rhetoric and viewpoints, your will argue:
|
|
"""
|
|
|
|
def __init__(self, name="SpeakAloud", context=None, llm=None):
|
|
super().__init__(name, context, llm)
|
|
|
|
async def run(self, context: str, name: str, opponent_name: str):
|
|
|
|
prompt = self.PROMPT_TEMPLATE.format(context=context, name=name, opponent_name=opponent_name)
|
|
# logger.info(prompt)
|
|
|
|
rsp = await self._aask(prompt)
|
|
|
|
return rsp
|
|
|
|
class Debator(Role):
|
|
def __init__(
|
|
self,
|
|
name: str,
|
|
profile: str,
|
|
opponent_name: str,
|
|
**kwargs,
|
|
):
|
|
super().__init__(name, profile, **kwargs)
|
|
self._init_actions([SpeakAloud])
|
|
self._watch([UserRequirement, SpeakAloud])
|
|
self.name = name
|
|
self.opponent_name = opponent_name
|
|
|
|
async def _observe(self) -> int:
|
|
await super()._observe()
|
|
# accept messages sent (from opponent) to self, disregard own messages from the last round
|
|
self._rc.news = [msg for msg in self._rc.news if msg.send_to == self.name]
|
|
return len(self._rc.news)
|
|
|
|
async def _act(self) -> Message:
|
|
logger.info(f"{self._setting}: ready to {self._rc.todo}")
|
|
todo = self._rc.todo # An instance of SpeakAloud
|
|
|
|
memories = self.get_memories()
|
|
context = "\n".join(f"{msg.sent_from}: {msg.content}" for msg in memories)
|
|
# print(context)
|
|
|
|
rsp = await todo.run(context=context, name=self.name, opponent_name=self.opponent_name)
|
|
|
|
msg = Message(
|
|
content=rsp,
|
|
role=self.profile,
|
|
cause_by=type(todo),
|
|
sent_from=self.name,
|
|
send_to=self.opponent_name,
|
|
)
|
|
|
|
self._rc.memory.add(msg)
|
|
|
|
return msg
|
|
|
|
async def debate(idea: str, investment: float = 3.0, n_round: int = 5):
|
|
"""Run a team of presidents and watch they quarrel. :) """
|
|
Biden = Debator(name="Biden", profile="Democrat", opponent_name="Trump")
|
|
Trump = Debator(name="Trump", profile="Republican", opponent_name="Biden")
|
|
team = Team()
|
|
team.hire([Biden, Trump])
|
|
team.invest(investment)
|
|
team.run_project(idea, send_to="Biden") # send debate topic to Biden and let him speak first
|
|
await team.run(n_round=n_round)
|
|
|
|
|
|
def main(idea: str, investment: float = 3.0, n_round: int = 10):
|
|
"""
|
|
:param idea: Debate topic, such as "Topic: The U.S. should commit more in climate change fighting"
|
|
or "Trump: Climate change is a hoax"
|
|
:param investment: contribute a certain dollar amount to watch the debate
|
|
:param n_round: maximum rounds of the debate
|
|
:return:
|
|
"""
|
|
if platform.system() == "Windows":
|
|
asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
|
|
asyncio.run(debate(idea, investment, n_round))
|
|
|
|
|
|
if __name__ == '__main__':
|
|
fire.Fire(main)
|