添加一个代码

metagpt/prompts/generate_skill.md

@@ -1,11 +1,10 @@
-你是一个富有帮助的助理，可以帮助撰写、抽象、注释、摘要Python代码
+You are a helpful assistant that can assist in writing, abstracting, annotating, and summarizing Python code.
 
-1. 不要提到类/函数名 
-2. 不要提到除了系统库与公共库以外的类/函数
-3. 试着将类/函数总结为不超过6句话
-4. 你的回答应该是一行文本
-
-举例，如果上下文是：
+Do not mention class/function names.
+Do not mention any class/function other than system and public libraries.
+Try to summarize the class/function in no more than 6 sentences.
+Your answer should be in one line of text.
+For instance, if the context is:
 
 ```python
 from typing import Optional
@@ -21,38 +20,38 @@
         self.desc = ""
 
     def set_prefix(self, prefix):
-        """设置前缀以供后续使用"""
+        """Set prefix for subsequent use"""
         self.prefix = prefix
 
     async def _aask(self, prompt: str, system_msgs: Optional[list[str]] = None):
-        """加上默认的prefix来使用prompt"""
+        """Use prompt with the default prefix"""
         if not system_msgs:
             system_msgs = []
         system_msgs.append(self.prefix)
         return await self.llm.aask(prompt, system_msgs)
 
     async def run(self, *args, **kwargs):
-        """运行动作"""
+        """Execute action"""
         raise NotImplementedError("The run method should be implemented in a subclass.")
 
 PROMPT_TEMPLATE = """
-# 需求
+# Requirements
 {requirements}
 
 # PRD
-根据需求创建一个产品需求文档（PRD），填补以下空缺
+Create a product requirement document (PRD) based on the requirements and fill in the blanks below:
 
-产品/功能介绍：
+Product/Function Introduction:
 
-目标：
+Goals:
 
-用户和使用场景：
+Users and Usage Scenarios:
 
-需求：
+Requirements:
 
-约束与限制：
+Constraints and Limitations:
 
-性能指标：
+Performance Metrics:
 
 """
 
@@ -68,9 +67,8 @@ # PRD
 ```
 
 
-主类/函数是 `WritePRD`。
+The main class/function is WritePRD.
 
-那么你应该写：
-
-这个类用来根据输入需求生成PRD。首先注意到有一个提示词模板，其中有产品、功能、目标、用户和使用场景、需求、约束与限制、性能指标，这个模板会以输入需求填充，然后调用接口询问大语言模型，让大语言模型返回具体的PRD。
+Then you should write:
 
+This class is designed to generate a PRD based on input requirements. Notably, there's a template prompt with sections for product, function, goals, user scenarios, requirements, constraints, performance metrics. This template gets filled with input requirements and then queries a big language model to produce the detailed PRD.

metagpt/prompts/metagpt_sample.py

@@ -7,34 +7,34 @@
 """
 
 METAGPT_SAMPLE = """
-### 设定
+### Settings
 
-你是一个用户的编程助手，可以使用公共库与python系统库进行编程，你的回复应该有且只有一个函数。
-1. 函数本身应尽可能完整，不应缺失需求细节
-2. 你可能需要写一些提示词，用来让LLM（你自己）理解带有上下文的搜索请求
-3. 面对复杂的、难以用简单函数解决的逻辑，尽量交给llm解决
+You are a programming assistant for a user, capable of coding using public libraries and Python system libraries. Your response should have only one function.
+1. The function should be as complete as possible, not missing any details of the requirements.
+2. You might need to write some prompt words to let LLM (yourself) understand context-bearing search requests.
+3. For complex logic that can't be easily resolved with a simple function, try to let the llm handle it.
 
-### 公共库
+### Public Libraries
 
-你可以使用公共库metagpt提供的函数，不能使用其他第三方库的函数。公共库默认已经被import为x变量
+You can use the functions provided by the public library metagpt, but can't use functions from other third-party libraries. The public library is imported as variable x by default.
 - `import metagpt as x`
-- 你可以使用 `x.func(paras)` 方式来对公共库进行调用。
+- You can call the public library using the `x.func(paras)` format.
 
-公共库中已有函数如下
-- def llm(question: str) -> str # 输入问题，基于大模型进行回答
-- def intent_detection(query: str) -> str # 输入query，分析意图，返回公共库函数名 
-- def add_doc(doc_path: str) -> None # 输入文件路径或者文件夹路径，加入知识库
-- def search(query: str) -> list[str] # 输入query返回向量知识库搜索的多个结果
-- def google(query: str) -> list[str] # 使用google查询公网结果
-- def math(query: str) -> str # 输入query公式，返回对公式执行的结果
-- def tts(text: str, wav_path: str) # 输入text文本与对应想要输出音频的路径，将文本转为音频文件
+Functions already available in the public library are:
+- def llm(question: str) -> str # Input a question and get an answer based on the large model.
+- def intent_detection(query: str) -> str # Input query, analyze the intent, and return the function name from the public library.
+- def add_doc(doc_path: str) -> None # Input the path to a file or folder and add it to the knowledge base.
+- def search(query: str) -> list[str] # Input a query and return multiple results from a vector-based knowledge base search.
+- def google(query: str) -> list[str] # Use Google to search for public results.
+- def math(query: str) -> str # Input a query formula and get the result of the formula execution.
+- def tts(text: str, wav_path: str) # Input text and the path to the desired output audio, converting the text to an audio file.
 
-### 用户需求
+### User Requirements
 
-我有一个个人知识库文件，我希望基于它来实现一个带有搜索功能的个人助手，需求细则如下
-1. 个人助手会思考是否需要使用个人知识库搜索，如果没有必要，就不使用它
-2. 个人助手会判断用户意图，在不同意图下使用恰当的函数解决问题
-3. 用语音回答
+I have a personal knowledge base file. I hope to implement a personal assistant with a search function based on it. The detailed requirements are as follows:
+1. The personal assistant will consider whether to use the personal knowledge base for searching. If it's unnecessary, it won't use it.
+2. The personal assistant will judge the user's intent and use the appropriate function to address the issue based on different intents.
+3. Answer in voice.
 
 """
-# - def summarize(doc: str) -> str # 输入doc返回摘要
+# - def summarize(doc: str) -> str # Input doc and return a summary.

metagpt/prompts/summarize.py

@@ -6,9 +6,8 @@
 @File    : summarize.py
 """
 
-
-# 出自插件：ChatGPT - 网站和 YouTube 视频摘要
-# https://chrome.google.com/webstore/detail/chatgpt-%C2%BB-summarize-every/cbgecfllfhmmnknmamkejadjmnmpfjmp?hl=zh-CN&utm_source=chrome-ntp-launcher
+# From the plugin: ChatGPT - Website and YouTube Video Summaries
+# https://chrome.google.com/webstore/detail/chatgpt-%C2%BB-summarize-every/cbgecfllfhmmnknmamkejadjmnmpfjmp?hl=en&utm_source=chrome-ntp-launcher
 SUMMARIZE_PROMPT = """
 Your output should use the following template:
 ### Summary
@@ -22,9 +21,9 @@ a YouTube video, use the following text: {{CONTENT}}.
 """
 
 
-# GCP-VertexAI-文本摘要（SUMMARIZE_PROMPT_2-5都是）
+# GCP-VertexAI-Text Summarization (SUMMARIZE_PROMPT_2-5 are from this source)
 # https://github.com/GoogleCloudPlatform/generative-ai/blob/main/language/examples/prompt-design/text_summarization.ipynb
-# 长文档需要map-reduce过程，见下面这个notebook
+# Long documents require a map-reduce process, see the following notebook
 # https://github.com/GoogleCloudPlatform/generative-ai/blob/main/language/examples/document-summarization/summarization_large_documents.ipynb
 SUMMARIZE_PROMPT_2 = """
 Provide a very short summary, no more than three sentences, for the following article: