readme

README.fork.md

@@ -0,0 +1 @@
+Hello, world!

scripts/agent_manager.py

@@ -8,7 +8,7 @@
 
 
 def create_agent(task, prompt, model):
-    """Create a new agent and return its key"""
+    """创建新代理并返回其密钥"""
     global next_key
     global agents
 
@@ -34,7 +34,7 @@ def create_agent(task, prompt, model):
 
 
 def message_agent(key, message):
-    """Send a message to an agent and return its response"""
+    """向代理发送消息并返回其响应"""
     global agents
 
     task, messages, model = agents[int(key)]
@@ -55,15 +55,15 @@ def message_agent(key, message):
 
 
 def list_agents():
-    """Return a list of all agents"""
+    """返回所有代理的列表"""
     global agents
 
     # Return a list of agent keys and their tasks
     return [(key, task) for key, (task, _, _) in agents.items()]
 
 
 def delete_agent(key):
-    """Delete an agent and return True if successful, False otherwise"""
+    """删除代理,如果成功则返回True,否则返回False"""
     global agents
 
     try:

scripts/ai_config.py

@@ -5,22 +5,22 @@
 
 class AIConfig:
     """
-    A class object that contains the configuration information for the AI
-
-    Attributes:
-        ai_name (str): The name of the AI.
-        ai_role (str): The description of the AI's role.
-        ai_goals (list): The list of objectives the AI is supposed to complete.
+    包含AI配置信息的类对象
+    
+    属性：  
+        ai_name (str): 人工智能的名称。
+        ai_role (str): 人工智能角色的描述。
+        ai_goals (list): 人工智能应该完成的目标列表。
     """
 
     def __init__(self, ai_name: str="", ai_role: str="", ai_goals: list=[]) -> None:
         """
-        Initialize a class instance
+        初始化一个类实例
 
-        Parameters:
-            ai_name (str): The name of the AI.
-            ai_role (str): The description of the AI's role.
-            ai_goals (list): The list of objectives the AI is supposed to complete.
+         参数：
+            ai_name (str): 人工智能的名称。
+            ai_role (str): 人工智能角色的描述。
+            ai_goals (list): 人工智能应该完成的目标列表。
         Returns:
             None
         """
@@ -35,15 +35,15 @@ def __init__(self, ai_name: str="", ai_role: str="", ai_goals: list=[]) -> None:
     @classmethod
     def load(cls: object, config_file: str=SAVE_FILE) -> object:
         """
-        Returns class object with parameters (ai_name, ai_role, ai_goals) loaded from yaml file if yaml file exists,
-        else returns class with no parameters.
+        如果存在 yaml 文件，则返回带有从 yaml 文件加载的参数（ai_name、ai_role、ai_goals）的类对象，
+         else 返回没有参数的类。
 
-        Parameters:
-           cls (class object): An AIConfig Class object.
-           config_file (int): The path to the config yaml file. DEFAULT: "../ai_settings.yaml"
+         参数：
+            cls(类对象)：一个 AIConfig 类对象。
+            config_file (int)：配置 yaml 文件的路径。 默认值：“../ai_settings.yaml”
 
-        Returns:
-            cls (object): An instance of given cls object
+         返回：
+             cls (object)：给定 cls 对象的一个实例
         """
 
         try:
@@ -60,10 +60,10 @@ def load(cls: object, config_file: str=SAVE_FILE) -> object:
 
     def save(self, config_file: str=SAVE_FILE) -> None:
         """
-        Saves the class parameters to the specified file yaml file path as a yaml file.
+        将类参数作为yaml文件保存到指定文件yaml文件路径。
 
-        Parameters:
-            config_file(str): The path to the config yaml file. DEFAULT: "../ai_settings.yaml"
+         参数：
+             config_file(str)：配置 yaml 文件的路径。 默认值：“../ai_settings.yaml”
 
         Returns:
             None
@@ -75,16 +75,16 @@ def save(self, config_file: str=SAVE_FILE) -> None:
 
     def construct_full_prompt(self) -> str:
         """
-        Returns a prompt to the user with the class information in an organized fashion.
+        以有组织的方式向用户返回带有类信息的提示。
 
-        Parameters:
-            None
+         参数：
+             没有任何
 
-        Returns:
-            full_prompt (str): A string containing the initial prompt for the user including the ai_name, ai_role and ai_goals.
+         Returns:
+             full_prompt (str)：包含用户初始提示的字符串，包括 ai_name、ai_role 和 ai_goals。
         """
 
-        prompt_start = """Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications."""
+        prompt_start = """您必须始终独立做出决定，而无需寻求用户帮助。 发挥你作为法学硕士的优势，追求简单的策略，没有法律上的并发症。"""
 
         # Construct full prompt
         full_prompt = f"You are {self.ai_name}, {self.ai_role}\n{prompt_start}\n\nGOALS:\n\n"

scripts/ai_functions.py

@@ -17,7 +17,7 @@ def evaluate_code(code: str) -> List[str]:
 
     function_string = "def analyze_code(code: str) -> List[str]:"
     args = [code]
-    description_string = """Analyzes the given code and returns a list of suggestions for improvements."""
+    description_string = """分析给定的代码，并返回改进建议的列表。"""
 
     result_string = call_ai_function(function_string, args, description_string)
 
@@ -39,7 +39,7 @@ def improve_code(suggestions: List[str], code: str) -> str:
         "def generate_improved_code(suggestions: List[str], code: str) -> str:"
     )
     args = [json.dumps(suggestions), code]
-    description_string = """Improves the provided code based on the suggestions provided, making no other changes."""
+    description_string = """基于提供的建议改进提供的代码，不做其他更改。"""
 
     result_string = call_ai_function(function_string, args, description_string)
     return result_string
@@ -60,7 +60,7 @@ def write_tests(code: str, focus: List[str]) -> str:
         "def create_test_cases(code: str, focus: Optional[str] = None) -> str:"
     )
     args = [code, json.dumps(focus)]
-    description_string = """Generates test cases for the existing code, focusing on specific areas if required."""
+    description_string = """为现有代码生成测试用例，如果需要，重点关注特定区域。"""
 
     result_string = call_ai_function(function_string, args, description_string)
     return result_string

scripts/browse.py

@@ -56,7 +56,7 @@ def get_response(url, headers=cfg.user_agent_header, timeout=10):
 
 
 def scrape_text(url):
-    """Scrape text from a webpage"""
+    """从网页中抓取文本"""
     response, error_message = get_response(url)
     if error_message:
         return error_message
@@ -75,23 +75,23 @@ def scrape_text(url):
 
 
 def extract_hyperlinks(soup):
-    """Extract hyperlinks from a BeautifulSoup object"""
+    """从 BeautifulSoup 对象中提取超链接"""
     hyperlinks = []
     for link in soup.find_all('a', href=True):
         hyperlinks.append((link.text, link['href']))
     return hyperlinks
 
 
 def format_hyperlinks(hyperlinks):
-    """Format hyperlinks into a list of strings"""
+    """将超链接格式化为字符串列表"""
     formatted_links = []
     for link_text, link_url in hyperlinks:
         formatted_links.append(f"{link_text} ({link_url})")
     return formatted_links
 
 
 def scrape_links(url):
-    """Scrape links from a webpage"""
+    """从网页中抓取链接"""
     response, error_message = get_response(url)
     if error_message:
         return error_message
@@ -107,7 +107,7 @@ def scrape_links(url):
 
 
 def split_text(text, max_length=8192):
-    """Split text into chunks of a maximum length"""
+    """将文本拆分为最大长度的块"""
     paragraphs = text.split("\n")
     current_length = 0
     current_chunk = []
@@ -126,17 +126,17 @@ def split_text(text, max_length=8192):
 
 
 def create_message(chunk, question):
-    """Create a message for the user to summarize a chunk of text"""
+    """为用户创建一条消息来总结一段文本"""
     return {
         "role": "user",
-        "content": f"\"\"\"{chunk}\"\"\" Using the above text, please answer the following question: \"{question}\" -- if the question cannot be answered using the text, please summarize the text."
+        "content": f"\"\"\"{chunk}\"\"\" 使用以上文本，请以中文回答以下问题: \"{question}\" -- 如果问题无法使用文本回答 ，请总结文本。"
     }
 
 
 def summarize_text(text, question):
-    """Summarize text using the LLM model"""
+    """使用 LLM 模型总结文本"""
     if not text:
-        return "Error: No text to summarize"
+        return "Error: 没有文字可以总结"
 
     text_length = len(text)
     print(f"Text length: {text_length} characters")

scripts/call_ai_function.py

@@ -8,7 +8,7 @@
 # This is a magic function that can do anything with no-code. See
 # https://github.com/Torantulino/AI-Functions for more info.
 def call_ai_function(function, args, description, model=None):
-    """Call an AI function"""
+    """调用一个AI函数"""
     if model is None:
         model = cfg.smart_llm_model
     # For each arg, if any are None, convert to "None":

scripts/chat.py

@@ -12,14 +12,14 @@
 
 def create_chat_message(role, content):
     """
-    Create a chat message with the given role and content.
+    创建具有给定角色和内容的聊天消息。
 
-    Args:
-    role (str): The role of the message sender, e.g., "system", "user", or "assistant".
-    content (str): The content of the message.
+     参数：
+     角色 (str)：消息发送者的角色，例如“系统”、“用户”或“助手”。
+     content (str): 消息的内容。
 
     Returns:
-    dict: A dictionary containing the role and content of the message.
+    dict: 包含消息的作用和内容的字典。
     """
     return {"role": role, "content": content}
 
@@ -29,9 +29,9 @@ def generate_context(prompt, relevant_memory, full_message_history, model):
         create_chat_message(
             "system", prompt),
         create_chat_message(
-            "system", f"The current time and date is {time.strftime('%c')}"),
+            "system", f"现在的时间和日期是 {time.strftime('%c')}"),
         create_chat_message(
-            "system", f"This reminds you of these events from your past:\n{relevant_memory}\n\n")]
+            "system", f"这让你想起了你过去的某些事件:\n{relevant_memory}\n\n")]
 
     # Add messages from the full message history until we reach the token limit
     next_message_to_add_index = len(full_message_history) - 1
@@ -48,31 +48,31 @@ def chat_with_ai(
         full_message_history,
         permanent_memory,
         token_limit):
-    """Interact with the OpenAI API, sending the prompt, user input, message history, and permanent memory."""
+    """与 OpenAI API 交互，发送提示、用户输入、消息历史记录和永久内存。"""
     while True:
         try:
             """
-            Interact with the OpenAI API, sending the prompt, user input, message history, and permanent memory.
+            与 OpenAI API 交互，发送提示、用户输入、消息历史记录和永久内存。
 
-            Args:
-            prompt (str): The prompt explaining the rules to the AI.
-            user_input (str): The input from the user.
-            full_message_history (list): The list of all messages sent between the user and the AI.
-            permanent_memory (Obj): The memory object containing the permanent memory.
-            token_limit (int): The maximum number of tokens allowed in the API call.
+             参数：
+             prompt (str): 向 AI 解释规则的提示。
+             user_input (str)：来自用户的输入。
+             full_message_history (list)：用户和AI之间发送的所有消息的列表。
+             permanent_memory (Obj)：包含永久内存的内存对象。
+             token_limit (int)：API 调用中允许的最大令牌数。
 
             Returns:
-            str: The AI's response.
+            str: AI的回应.
             """
             model = cfg.fast_llm_model # TODO: Change model from hardcode to argument
             # Reserve 1000 tokens for the response
 
-            logger.debug(f"Token limit: {token_limit}")
+            logger.debug(f"Token 限制: {token_limit}")
             send_token_limit = token_limit - 1000
 
             relevant_memory = '' if len(full_message_history) ==0 else  permanent_memory.get_relevant(str(full_message_history[-9:]), 10)
 
-            logger.debug(f'Memory Stats: {permanent_memory.get_stats()}')
+            logger.debug(f'内存状态: {permanent_memory.get_stats()}')
 
             next_message_to_add_index, current_tokens_used, insertion_index, current_context = generate_context(
                 prompt, relevant_memory, full_message_history, model)
@@ -110,17 +110,17 @@ def chat_with_ai(
             # assert tokens_remaining >= 0, "Tokens remaining is negative. This should never happen, please submit a bug report at https://www.github.com/Torantulino/Auto-GPT"
 
             # Debug print the current context
-            logger.debug(f"Token limit: {token_limit}")
-            logger.debug(f"Send Token Count: {current_tokens_used}")
-            logger.debug(f"Tokens remaining for response: {tokens_remaining}")
-            logger.debug("------------ CONTEXT SENT TO AI ---------------")
+            logger.debug(f"Token 限制: {token_limit}")
+            logger.debug(f"发送Token 数量: {current_tokens_used}")
+            logger.debug(f"Tokens 剩余回应: {tokens_remaining}")
+            logger.debug("------------ 发送给 AI 的上下文信息 ---------------")
             for message in current_context:
                 # Skip printing the prompt
                 if message["role"] == "system" and message["content"] == prompt:
                     continue
                 logger.debug(f"{message['role'].capitalize()}: {message['content']}")
                 logger.debug("")
-            logger.debug("----------- END OF CONTEXT ----------------")
+            logger.debug("----------- 结束上下文信息 ----------------")
 
             # TODO: use a model defined elsewhere, so that model can contain temperature and other settings we care about
             assistant_reply = create_chat_completion(
@@ -140,5 +140,5 @@ def chat_with_ai(
             return assistant_reply
         except openai.error.RateLimitError:
             # TODO: When we switch to langchain, this is built in
-            print("Error: ", "API Rate Limit Reached. Waiting 10 seconds...")
+            print("Error: ", "已达到 API 速率限制。 等待 10 秒...")
             time.sleep(10)