Merge branch 'main' into main

README.md

@@ -53,6 +53,24 @@ # Step 3: Clone the repository to your local machine, and install it.
 python setup.py install
 ```
 
+**Note:**
+
+- If already have Chrome, Chromium, or MS Edge installed, you can skip downloading Chromium by setting the environment variable
+`PUPPETEER_SKIP_CHROMIUM_DOWNLOAD` to `true`.
+
+- Some people are [having issues](https://github.com/mermaidjs/mermaid.cli/issues/15) installing this tool globally. Installing it locally is an alternative solution,
+
+    ```bash
+    npm install @mermaid-js/mermaid-cli
+    ```
+
+- don't forget to the configuration for mmdc in config.yml
+
+    ```yml
+    PUPPETEER_CONFIG: "./config/puppeteer-config.json"
+    MMDC: "./node_modules/.bin/mmdc"
+    ```
+
 ### Installation by Docker
 
 ```bash
@@ -120,7 +138,12 @@ # Use code review will cost more money, but will opt for better code quality.
 ```
 
 After running the script, you can find your new project in the `workspace/` directory.
+### Preference of Platform or Tool 
 
+You can tell which platform or tool you want to use when stating your requirements.
+```shell
+python startup.py "Write a cli snake game based on pygame"
+```
 ### Usage
 
 ```

docs/README_CN.md

@@ -1,4 +1,4 @@
-# MetaGPT：多智能体元编程框架
+# MetaGPT: 多智能体框架
 
 <p align="center">
 <a href=""><img src="resources/MetaGPT-logo.jpeg" alt="MetaGPT logo: 使 GPT 以软件公司的形式工作，协作处理更复杂的任务" width="150px"></a>
@@ -37,6 +37,8 @@ ## 示例（均由 GPT-4 生成）
 
 ## 安装
 
+### 传统安装
+
 ```bash
 # 第 1 步：确保您的系统上安装了 NPM。并使用npm安装mermaid-js
 npm --version
@@ -51,13 +53,56 @@ # 第 3 步：克隆仓库到您的本地机器，并进行安装。
 python setup.py install
 ```
 
+### Docker安装
+
+```bash
+# 步骤1: 下载metagpt官方镜像并准备好config.yaml
+docker pull metagpt/metagpt:v0.3
+mkdir -p /opt/metagpt/{config,workspace}
+docker run --rm metagpt/metagpt:v0.3 cat /app/metagpt/config/config.yaml > /opt/metagpt/config/config.yaml
+vim /opt/metagpt/config/config.yaml # 修改config
+
+# 步骤2: 使用容器运行metagpt演示
+docker run --rm \
+    --privileged \
+    -v /opt/metagpt/config:/app/metagpt/config \
+    -v /opt/metagpt/workspace:/app/metagpt/workspace \
+    metagpt/metagpt:v0.3 \
+    python startup.py "Write a cli snake game"
+
+# 您也可以启动一个容器并在其中执行命令
+docker run --name metagpt -d \
+    --privileged \
+    -v /opt/metagpt/config:/app/metagpt/config \
+    -v /opt/metagpt/workspace:/app/metagpt/workspace \
+    metagpt/metagpt:v0.3
+
+docker exec -it metagpt /bin/bash
+$ python startup.py "Write a cli snake game"
+```
+
+`docker run ...`做了以下事情:
+
+- 以特权模式运行，有权限运行浏览器
+- 将主机目录 `/opt/metagpt/config` 映射到容器目录`/app/metagpt/config`
+- 将主机目录 `/opt/metagpt/workspace` 映射到容器目录 `/app/metagpt/workspace`
+- 执行演示命令 `python startup.py "Write a cli snake game"`
+
+### 自己构建镜像
+
+```bash
+# 您也可以自己构建metagpt镜像
+git clone https://github.com/geekan/MetaGPT.git
+cd MetaGPT && docker build -t metagpt:v0.3 .
+```
+
 ## 配置
 
 - 在 `config/key.yaml / config/config.yaml / env` 中配置您的 `OPENAI_API_KEY`
 - 优先级顺序：`config/key.yaml > config/config.yaml > env`
 
 ```bash
-# 复制配置文件并进行必要的修改。
+# 复制配置文件并进行必要的修改
 cp config/config.yaml config/key.yaml
 ```
 
@@ -71,10 +116,47 @@ ## 示例：启动一个创业公司
 ```shell
 python startup.py "写一个命令行贪吃蛇"
 # 开启code review模式会会花费更多的money, 但是会提升代码质量和成功率
-python startup.py "写一个命令行贪吃蛇" --code_review True 
+python startup.py "写一个命令行贪吃蛇" --code_review True
 ```
 
 运行脚本后，您可以在 `workspace/` 目录中找到您的新项目。
+### 平台或工具的倾向性
+可以在阐述需求时说明想要使用的平台或工具。
+例如：
+
+```shell
+python startup.py "写一个基于pygame的命令行贪吃蛇"
+```
+
+### 使用
+
+```
+名称
+    startup.py - 我们是一家AI软件创业公司。通过投资我们，您将赋能一个充满无限可能的未来。
+
+概要
+    startup.py IDEA <flags>
+
+描述
+    我们是一家AI软件创业公司。通过投资我们，您将赋能一个充满无限可能的未来。
+
+位置参数
+    IDEA
+        类型: str
+        您的创新想法，例如"写一个命令行贪吃蛇。"
+
+标志
+    --investment=INVESTMENT
+        类型: float
+        默认值: 3.0
+        作为投资者，您有机会向这家AI公司投入一定的美元金额。
+    --n_round=N_ROUND
+        类型: int
+        默认值: 5
+
+备注
+    您也可以用`标志`的语法，来处理`位置参数`
+```
 
 ### 代码实现
 
@@ -108,6 +190,8 @@ ## 演示
 
 ## 加入微信讨论群
 
-- 群已满，加人进群
+<img src="resources/MetaGPT-WeChat-Group4.jpeg" width = "30%" height = "30%" alt="MetaGPT WeChat Discuss Group" align=center />
 
-<img src="resources/MetaGPT-WeChat-Personal.jpeg" width = "30%" height = "30%" alt="MetaGPT WeChat Discuss Group" align=center />
+如果群已满，请添加负责人微信，会邀请进群
+
+<img src="resources/MetaGPT-WeChat-Personal.jpeg" width = "30%" height = "30%" alt="MetaGPT WeChat Discuss Group" align=center />

docs/README_JA.md

@@ -53,6 +53,24 @@ # ステップ 3: リポジトリをローカルマシンにクローンし、
 python setup.py install
 ```
 
+**注:**
+
+- すでに Chrome、Chromium、MS Edge がインストールされている場合は、環境変数 `PUPPETEER_SKIP_CHROMIUM_DOWNLOAD` を `true` に設定することで、
+Chromium のダウンロードをスキップすることができます。
+
+- このツールをグローバルにインストールする[問題を抱えている](https://github.com/mermaidjs/mermaid.cli/issues/15)人もいます。ローカルにインストールするのが代替の解決策です、
+
+    ```bash
+    npm install @mermaid-js/mermaid-cli
+    ```
+
+- config.yml に mmdc のコンフィギュレーションを記述するのを忘れないこと
+
+    ```yml
+    PUPPETEER_CONFIG: "./config/puppeteer-config.json"
+    MMDC: "./node_modules/.bin/mmdc"
+    ```
+
 ### Docker によるインストール
 
 ```bash
@@ -120,6 +138,12 @@ # コードレビューを利用すれば、コストはかかるが、より良
 ```
 
 スクリプトを実行すると、`workspace/` ディレクトリに新しいプロジェクトが見つかります。
+### プラットフォームまたはツールの設定
+
+要件を述べるときに、どのプラットフォームまたはツールを使用するかを指定できます。
+```shell
+python startup.py "Write a cli snake game based on pygame"
+```
 
 ### 使用方法
 

examples/search_with_specific_engine.py

@@ -6,11 +6,11 @@ from metagpt.tools import SearchEngineType
 
 async def main():
     # Serper API
-    await Searcher(engine=SearchEngineType.SERPER_GOOGLE).run("What are some good sun protection products?")
-    # Serper API
-    # await Searcher(engine=SearchEngineType.SERPAPI_GOOGLE).run("What are the best ski brands for skiers?")
+    #await Searcher(engine = SearchEngineType.SERPER_GOOGLE).run(["What are some good sun protection products?","What are some of the best beaches?"])
+    # SerpAPI
+    #await Searcher(engine=SearchEngineType.SERPAPI_GOOGLE).run("What are the best ski brands for skiers?")
     # Google API
-    # await Searcher(engine=SearchEngineType.DIRECT_GOOGLE).run("What are the most interesting human facts?")
+    await Searcher(engine=SearchEngineType.DIRECT_GOOGLE).run("What are the most interesting human facts?")
 
 if __name__ == '__main__':
     asyncio.run(main())

metagpt/config.py

@@ -30,7 +30,7 @@ class Config(metaclass=Singleton):
     """
     Regular usage method:
     config = Config("config.yaml")
-    secret_key = config.get("MY_SECRET_KEY")
+    secret_key = config.get_key("MY_SECRET_KEY")
     print("Secret key:", secret_key)
     """
 
@@ -79,6 +79,9 @@ class Config(metaclass=Singleton):
         self.total_cost = 0.0
         self.puppeteer_config = self._get("PUPPETEER_CONFIG","")
         self.mmdc = self._get("MMDC","mmdc")
+        self.update_costs = self._get("UPDATE_COSTS",True)
+        self.calc_usage = self._get("CALC_USAGE",True)
+
 
     def _init_with_config_files_and_env(self, configs: dict, yaml_file):
         """Load from config/key.yaml, config/config.yaml, and env in decreasing order of priority"""

metagpt/roles/role.py

@@ -77,7 +77,7 @@ class RoleContext(BaseModel):
     def check(self, role_id: str):
         if hasattr(CONFIG, "long_term_memory") and CONFIG.long_term_memory:
             self.long_term_memory.recover_memory(role_id, self)
-            self.memory = self.long_term_memory  # use memory to act as long_term_memory for unified operation
+            self.memory = self.long_term_memory  # use memory to act as long_term_memory for unify operation
 
     @property
     def important_memory(self) -> list[Message]:
@@ -158,85 +158,85 @@ class Role:
             next_state = "0"
         self._set_state(int(next_state))
 
-async def _act(self) -> Message:
-    # prompt = self.get_prefix()
-    # prompt += ROLE_TEMPLATE.format(name=self.profile, state=self.states[self.state], result=response,
-    #                                history=self.history)
+    async def _act(self) -> Message:
+        # prompt = self.get_prefix()
+        # prompt += ROLE_TEMPLATE.format(name=self.profile, state=self.states[self.state], result=response,
+        #                                history=self.history)
 
-    logger.info(f"{self._setting}: ready to {self._rc.todo}")
-    response = await self._rc.todo.run(self._rc.important_memory)
-    # logger.info(response)
-    if isinstance(response, ActionOutput):
-        msg = Message(content=response.content, instruct_content=response.instruct_content,
-                      role=self.profile, cause_by=type(self._rc.todo))
-    else:
-        msg = Message(content=response, role=self.profile, cause_by=type(self._rc.todo))
-    self._rc.memory.add(msg)
-    # logger.debug(f"{response}")
+        logger.info(f"{self._setting}: ready to {self._rc.todo}")
+        response = await self._rc.todo.run(self._rc.important_memory)
+        # logger.info(response)
+        if isinstance(response, ActionOutput):
+            msg = Message(content=response.content, instruct_content=response.instruct_content,
+                        role=self.profile, cause_by=type(self._rc.todo))
+        else:
+            msg = Message(content=response, role=self.profile, cause_by=type(self._rc.todo))
+        self._rc.memory.add(msg)
+        # logger.debug(f"{response}")
 
-    return msg
+        return msg
 
-async def _observe(self) -> int:
-    """Observe from the environment, obtain important information, and add it to memory"""
-    if not self._rc.env:
-        return 0
-    env_msgs = self._rc.env.memory.get()
+    async def _observe(self) -> int:
+        """Observe from the environment, obtain important information, and add it to memory"""
+        if not self._rc.env:
+            return 0
+        env_msgs = self._rc.env.memory.get()
 
-    observed = self._rc.env.memory.get_by_actions(self._rc.watch)
+        observed = self._rc.env.memory.get_by_actions(self._rc.watch)
 
-    news = self._rc.memory.remember(observed)  # remember recent exact or similar memories
+        news = self._rc.memory.remember(observed)  # remember recent exact or similar memories
 
-    for i in env_msgs:
-        self.recv(i)
+        for i in env_msgs:
+            self.recv(i)
 
-    news_text = [f"{i.role}: {i.content[:20]}..." for i in news]
-    if news_text:
-        logger.debug(f'{self._setting} observed: {news_text}')
-    return len(news)
+        news_text = [f"{i.role}: {i.content[:20]}..." for i in news]
+        if news_text:
+            logger.debug(f'{self._setting} observed: {news_text}')
+        return len(news)
 
-def _publish_message(self, msg):
-    """If the role belongs to env, then the role's messages will be broadcast to env"""
-    if not self._rc.env:
-        # If env does not exist, do not publish the message
-        return
-    self._rc.env.publish_message(msg)
+    def _publish_message(self, msg):
+        """If the role belongs to env, then the role's messages will be broadcast to env"""
+        if not self._rc.env:
+            # If env does not exist, do not publish the message
+            return
+        self._rc.env.publish_message(msg)
 
-async def _react(self) -> Message:
-    """Think first, then act"""
-    await self._think()
-    logger.debug(f"{self._setting}: {self._rc.state=}, will do {self._rc.todo}")
-    return await self._act()
+    async def _react(self) -> Message:
+        """Think first, then act"""
+        await self._think()
+        logger.debug(f"{self._setting}: {self._rc.state=}, will do {self._rc.todo}")
+        return await self._act()
 
-def recv(self, message: Message) -> None:
-    """add message to history."""
-    # self._history += f"\n{message}"
-    # self._context = self._history
-    if message in self._rc.memory.get():
-        return
-    self._rc.memory.add(message)
+    def recv(self, message: Message) -> None:
+        """add message to history."""
+        # self._history += f"\n{message}"
+        # self._context = self._history
+        if message in self._rc.memory.get():
+            return
+        self._rc.memory.add(message)
 
-async def handle(self, message: Message) -> Message:
-    """Receive information and reply with actions"""
-    # logger.debug(f"{self.name=}, {self.profile=}, {message.role=}")
-    self.recv(message)
+    async def handle(self, message: Message) -> Message:
+        """Receive information and reply with actions"""
+        # logger.debug(f"{self.name=}, {self.profile=}, {message.role=}")
+        self.recv(message)
 
-    return await self._react()
+        return await self._react()
 
-async def run(self, message=None):
-    """Observe, and think and act based on the results of the observation"""
-    if message:
-        if isinstance(message, str):
-            message = Message(message)
-        if isinstance(message, Message):
-            self.recv(message)
-        if isinstance(message, list):
-            self.recv(Message("\n".join(message)))
-    elif not await self._observe():
-        # If there is no new information, suspend and wait
-        logger.debug(f"{self._setting}: no news. waiting.")
-        return
+    async def run(self, message=None):
+        """Observe, and think and act based on the results of the observation"""
+        if message:
+            if isinstance(message, str):
+                message = Message(message)
+            if isinstance(message, Message):
+                self.recv(message)
+            if isinstance(message, list):
+                self.recv(Message("\n".join(message)))
+        elif not await self._observe():
+            # If there is no new information, suspend and wait
+            logger.debug(f"{self._setting}: no news. waiting.")
+            return
 
-    rsp = await self._react()
-    # Publish the reply to the environment, waiting for the next subscriber to process
-    self._publish_message(rsp)
-    return rsp
+        rsp = await self._react()
+        # Publish the reply to the environment, waiting for the next subscriber to process
+        self._publish_message(rsp)
+        return rsp