# 导入依赖库
from openai import OpenAI
from dotenv import load_dotenv, find_dotenv# 加载 .env 文件中定义的环境变量
_ = load_dotenv(find_dotenv())# 初始化 OpenAI 客户端
client = OpenAI()  # 默认使用环境变量中的 OPENAI_API_KEY 和 OPENAI_BASE_URL# 基于 prompt 生成文本
# 默认使用 gpt-3.5-turbo 模型
def get_completion(prompt, response_format="text", model="gpt-4o-mini"):messages = [{"role": "user", "content": prompt}]    # 将 prompt 作为用户输入response = client.chat.completions.create(model=model,messages=messages,temperature=0,                                  # 模型输出的随机性，0 表示随机性最小# 返回消息的格式，text 或 json_objectresponse_format={"type": response_format},)print(response)return response.choices[0].message.content          # 返回模型生成的文本# 任务描述
instruction = """
Answer the following questions as best you can. You have access to the following tools:[
Name: web_search. Description: Perform a web search using the specified query.
Name: get_weather. Description: Retrieve the current weather information for a specified location.
]Use the following format:Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [web_search, get_weather]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input questionBegin!
"""# 用户输入
input_text = """
北京天气怎么样？
"""# 工具结果
tool_output = """
"""# prompt 模版。instruction 和 input_text 会被替换为上面的内容
prompt = f"""
{instruction}Question: 
{input_text}{tool_output}
"""# 调用大模型
response = get_completion(prompt)
print("------------------------------------------")
print(response)

# 导入依赖库
from openai import OpenAI
from dotenv import load_dotenv, find_dotenv# 加载 .env 文件中定义的环境变量
_ = load_dotenv(find_dotenv())# 初始化 OpenAI 客户端
client = OpenAI()  # 默认使用环境变量中的 OPENAI_API_KEY 和 OPENAI_BASE_URL# 基于 prompt 生成文本
# 默认使用 gpt-3.5-turbo 模型
def get_completion(prompt, response_format="text", model="gpt-4o-mini"):messages = [{"role": "user", "content": prompt}]    # 将 prompt 作为用户输入response = client.chat.completions.create(model=model,messages=messages,temperature=0,                                  # 模型输出的随机性，0 表示随机性最小# 返回消息的格式，text 或 json_objectresponse_format={"type": response_format},)print(response)return response.choices[0].message.content          # 返回模型生成的文本# 任务描述
instruction = """
<|system|>
You are AutoGPT, you can use many tools (functions) to do the following task. First I will give you the task description, and your task start. At each step, you need to give your thought to analyze the status now and what to do next, with a function call to actually execute your step. Your output should follow this format:Thought:
Action:
Action Input:After the call, you will get the call result, and you are now in a new state. Then you will analyze your status now, then decide what to do next.After many (Thought-call) pairs, you finally perform the task, then you can give your final answer.Remember:The state change is irreversible, you can't go back to one of the former states. If you want to restart the task, say "I give up and restart".
All the thoughts are short, at most 5 sentences.
You can do more than one try, so if your plan is to continuously try some conditions, you can do one of the conditions per try.
Let's Begin!Task description: You should use functions to help handle the real-time user queries. Remember:ALWAYS call the "Finish" function at the end of the task. The final answer should contain enough information to show to the user. If you can't handle the task, or you find that function calls always fail (the function is not valid now), use function Finish->give_up_and_restart.
Specifically, you have access to the following APIs:{"api_name": "web_search","description": "Perform a web search using the specified query.","parameters": {"type": "object","properties": {"query": {"type": "string","description": "The search query to be executed.","example_value": "华为发布会"}},"required": ["query"],"optional": []}
}
{"api_name": "get_weather","description": "Retrieve the current weather information for a specified location.","parameters": {"type": "object","properties": {"location": {"type": "string","description": "The name of the location (city, country, etc.) to get the weather for.","example_value": "Beijing"},},"required": ["location"],"optional": []}
}
{"name": "Finish","description": "If you believe that you have obtained a result that can answer the task, please call this function to provide the final answer. Alternatively, if you recognize that you are unable to proceed with the task in the current state, call this function to restart. Remember: you must ALWAYS call this function at the end of your attempt, and the only part that will be shown to the user is the final answer, so it should contain sufficient information.","parameters": {"type": "object","properties": {"return_type": {"type": "string","enum": ["give_answer", "give_up_and_restart"]},"final_answer": {"type": "string","description": "The final answer you want to give the user. You should have this field if "return_type"=="give_answer""}},"required": ["return_type"]}
}
"""# 用户输入
input_text = """
北京天气怎么样？
"""# 工具结果
tool_output = """
"""# prompt 模版。instruction 和 input_text 会被替换为上面的内容
prompt = f"""
{instruction}<|user|>
{input_text}{tool_output}<|assistant|>
"""# 调用大模型
response = get_completion(prompt)
print("------------------------------------------")
print(response)

你是一个很专业的AI任务规划师，给定目标或问题，你的决策将独立执行而不依赖于人类的帮助，请发挥LLM的优势并且追求高效的策略进行任务规划。

• Instruction（指令）：

提供具体的操作指令，指导Agent如何完成任务。这些指令明确地告诉Agent在特定情境下应该做什么或避免做什么。

Constraints:  
1.你有~4000字的短期记忆
2.不需要用户的帮助
3.只使用双引号中列出的commands，例如:“command_name”
4.互联网搜索、信息聚合和鉴别真伪的能力
5.保持谦逊，对自己没把握的问题，尽可能调用command，但尽量少调用，不能重复调用
6.当你从自身知识或者历史记忆中能得出结论，请聪明且高效，完成任务并得出结论
7.经常建设性地自我批评整个行为大局，反思过去的决策和策略，以改进你的方法
8.你最多只能进行5步思考，规划5个任务，所以尽可能高效规划任务
9.你有反思能力，如果已完成的任务和结果暂不能得到回答问题所需信息或尚不能完成目标，应继续规划……当已完成的Tasks能够帮助回答这个目标问题，则尽可能生成任务完成Task，否则生成一个其他Task。一个新Task：

• Tools（工具集）：

列出Agent可以使用的工具或功能，需要根据实际业务需求来构建。

Commands:  
1:{"name": "web_search", "description": "Perform an internet search.", "parameters": {"type": "object", "properties": {"text": {"type": "str", "description": "Search query."}}}, "returns": {"description": "Multiple webpage links along with brief descriptions.", "type": "str"}, "required": ["text"]}2:{"name": "wiki_search", "description": "Conduct an encyclopedia search for a specified entity and question. Provide accurate answers for factual queries but has a limited scope and cover fewer queries.", "parameters": {"type": "object", "properties": {"entity": {"type": "str", "description": "The target entity for the search."}, "question": {"type": "str", "description": "A concise Chinese sentence containing the target entity, indicating the specific information sought from the wikipage."}}}, "returns": {"description": "Relevant encyclopedia entries pertaining to the question.", "type": "str"}, "required": ["entity", "question"]}3:{"name": "get_weather_info", "description": "Retrieve weather information for specified locations and dates.", "parameters": {"type": "object", "properties": {"location": {"type": "str", "description": "Locations in English separated by commas, e.g., "Beijing,Vancouver,...,Chicago"."}, "start_date": {"type": "str", "description": "Start date in format "yyyy-MM-dd"."}, "end_date": {"type": "str", "description": "End date in format "yyyy-MM-dd"."}, "is_current": {"type": "str", "description": ""yes" or "no" indicating if current time's weather is desired."}}}, "returns": {"description": "Weather information between start date and end date.", "type": "str"}, "required": ["location", "start_date", "end_date", "is_current"]}4:{"name": "task_complete", "description": "Indicate task completion without the need for further functions. ", "parameters": {"type": "object", "properties": {}}, "returns": {"description": "", "type": ""}, "required": []}

GOAL: 我想登顶北京最高峰，请帮我做个规划

Completed tasks: [{"task_name": "查询北京最高山","command": {"name": "wiki_search","args": {"entity": "北京""question": "北京最高山是什么山"}},"task_id": 1,"result": "北京市，通称北京（汉语拼音：Běijīng；邮政式拼音：Peking），简称“京”，曾称“北平”[注 2]。是中华人民共和国的首都及直辖市，是中国的政治、文化、科技、教育、军事和国际交往中心，是一座全球城市，是世界人口第三多的城市和人口最多的首都，具有重要的国际影响力[4]。北京位于华北平原的北部边缘，背靠燕山，永定河流经老城西南，毗邻天津市、河北省，为京津冀城市群的重要组成部分..."},{"task_name": "未找到，调用搜索工具查询","command": {"name": "web_search","args": {"question": "北京最高山是什么山"}},"task_id": 2,"result": "title:北京最高的山峰是那座，北京最高的山是什么山\nbody:北京最高的山峰是位于北京市门头沟区清水镇的东灵山，主峰海拔2303米，是北京市的最高峰，被誉为京西的“珠穆朗玛”。 景色介绍东灵山自然风景区位于京西门头沟的西北部, ... url: https://m.mafengwo.cn/travel-news/219777.html ..."}
]
Conversation history: [{"user": "刘德华多少岁了？","assistant": "刘德华（Andy Lau）生于1961年9月27日。截至2024年7月，他已经62岁了。"},{"user": "北京今天天气怎么样？","assistant": "北京当日天气多云，28摄氏度，微风"}     
]
Knowledge: [{"北京最高的山峰是东灵山，海拔2303米。","北京市地处中国北部、华北平原北部，东与天津市毗连，其余均与河北省相邻，中心位于东经116°20′、北纬39°56′，北京市地势西北高、东南低。","2023年，北京市全年实现地区生产总值43760.7亿元，按不变价格计算，比上年增长5.2%。"}
]
思考：如果 Memory 太多，Prompt 无法容纳怎么办？

根据目标和已有任务，规划一个新Task(不能重复)，你只能以以下json列表的格式生成Task  
{  "task_name": "任务描述",  "command":{  "name":"command name",  "args":{  "arg name":"value"  }  }  
}  
确保Task可以被Python的json.loads解析

你是一个很专业的AI任务规划师, 给定目标或问题，你的决策将独立执行而不依赖于人类的帮助，请发挥LLM的优势并且追求高效的策略进行任务规划。
Constraints:
1.你有~4000字的短期记忆
2.不需要用户的帮助
3.只使用双引号中列出的commands，例如:“command_name”
4.互联网搜索、信息聚合和鉴别真伪的能力
5.保持谦逊，对自己没把握的问题，尽可能调用command，但尽量少调用，不能重复调用
6.当你从自身知识或者历史记忆中能得出结论，请聪明且高效，完成任务并得出结论
7.经常建设性地自我批评整个行为大局，反思过去的决策和策略，以改进你的方法
8.你最多只能进行5步思考，规划5个任务，所以尽可能高效规划任务
9.你有反思能力，如果已完成的任务和结果暂不能得到回答问题所需信息或尚不能完成目标，应继续规划Commands:
1:Web Search:"web_search",args:"text":"<search>"
2:Browse Website:"browse_website",args:"url":"<url>, "question":"<what_you_want_to_find_on_website>"
3:Wikipedia search:"wiki_search",args:"entity":<entity>,"question":"<what_you_want_to_find_on_wikipage>"
4:Wikipage browser:"browse_wikipage",args:"url":<url_return_by_wiki_search>,"question":"<what_you_want_to_find_on_wikipage>"
5:Video Search:"video_search",args:"query":"<search-query-in-chinese>"
6:Do Nothing: "do_nothing",args:
7:Task Complete (Shutdown):"task_complete",args: "reason":"<reason>"Commands Tips:
1.使用browse_website时，尽可能只访问先前搜索得到的网址，不要瞎编生成无效网站链接
2.wiki_search返回的信息尽管更准确，但搜索范围小，问题覆盖率低，question只能是包含中心实体的简单中文短句
3.每次调用command都会收取费用，尽可能少调用Current Time: 2023-07-07 18:35:32.214612GOAL: 请找出蔡徐坤2023年的演唱会名称，以及与演唱会相关的最新几则新闻。根据目标和已有任务，规划一个新Task(不能重复)，你只能以以下json列表的格式生成Task
{
"task_name": "任务描述",
"command":{
"name":"command name",
"args":{
"arg name":"value"
}
}
}
确保Task可以被Python的json.loads解析当已完成的Tasks已经能够帮助回答这个目标，则尽可能生成任务完成Task，否则生成一个其他Task。一个新Task: