前言AI智能体是指具备一定自主性、能感知环境并通过智能决策执行特定任务的软件或硬件实体。它结合了人工智能技术（如机器学习、自然语言处理、计算机视觉等），能够独立或协作完成目标。 基于大语言模型（LLM）的Function Calling可以令智能体实现有效的工具使用和与外部API的交互。支持Function Calling的模型(如gpt-4，qwen-plus等)能够检测何时需要调用函数，并输出调用函数的函数名和所需参数的JSON格式结构化数据。 但并非所有的LLM模型都支持Function Calling(如deepseel-v3)。对于不支持Function Calling的模型，可通过ReAct的相对较为复杂的提示词工程，要求模型返回特定格式的响应，以便区分不同的阶段（思考、行动、观察）。 工具调用主要有两个用途： 获取数据:例如根据关键字从知识库检索内容、通过特定API接口获取业务数据执行行动:例如通过API接口修改业务状态数据、执行预定业务操作
本文包含如下内容： - 详细介绍基于ReAct的工具调用流程和涉及的交互消息
ReAct基础ReAct源于经典论文:REACT: SYNERGIZING REASONING AND ACTING IN LANGUAGE MODELS(链接：https://arxiv.org/pdf/2210.03629) 基于ReAct的智能体为了解决问题，需要经过几个阶段
以上3个阶段可能迭代多次，直到问题得到解决或者达到迭代次数上限。 基于ReAct的工具调用依赖于复杂的提示词工程。系统提示词参考langchain的模板: Answer the following questions as best you can. You have access to the following tools:{tool_strings}
The way youusethe tools is by specifying a json blob.Specifically, this json should have a`action`key (with the name of the tool touse)anda`action_input`key (with the input to the tool going here).
The onlyvaluesthat should be in the"action"field are:{tool_names}
The $JSON_BLOB should only contain a SINGLE action,doNOTreturna list of multiple actions. Here is an example of a valid $JSON_BLOB:
```{{{{"action": $TOOL_NAME,"action_input": $INPUT}}}}```
ALWAYSusethe followingformat:
Question: the input question you must answerThought: you should always think about what todoAction:```$JSON_BLOB```Observation: the result of the action... (this Thought/Action/Observation can repeat Ntimes)Thought: I now know the final answerFinal Answer: the final answer to the original input question
Begin! Reminder to alwaysusethe exact characters`Final Answer`whenresponding.
基于ReAct的工具调用流程和交互消息我们以查询北京和广州天气为例，LLM采用阿里云的DeepSeek-v3。查询天气的流程如下图： 1. 发起查询请求向LLM发起查询时，messages列表有2条messages： - 第1条role为
system，定义了系统提示词(含工具定义)
我们用curl发起POST请求，body的JSON结构可参考https://platform.openai.com/docs/api-reference/chat/create。 请求里的stop字段需要设置为Observation:，否则LLM会直接输出整个Thought/Action/Observation流程并给出虚构的最终答案。我们仅需要LLM输出Thought/Action即可
#!/bin/bashexportOPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"exportOPENAI_API_KEY="sk-xxx"# 替换为你的key
curl ${OPENAI_BASE_URL}/chat/completions \-H"Content-Type: application/json"\-H"Authorization: Bearer $OPENAI_API_KEY"\-d '{"model":"deepseek-v3","messages": [ { "role":"system", "content":"\nAnswer the following questions as best you can. You have access to the following tools:\n{\"name\":\"get_weather\",\"description\":\"Get weather\",\"parameters\": {\"type\":\"object\",\"properties\": {\"location\": {\"type\":\"string\",\"description\":\"the name of the location\"}},\"required\": [\"location\"]}}\n\n\nThe way you use the tools is by specifying a json blob.\nSpecifically, this json should have a `action` key (with the name of the tool to use) and a `action_input` key (with the input to the tool going here).\n\nThe only values that should be in the\"action\"field are: get_weather\n\nThe $JSON_BLOB should only contain a SINGLE action, do NOT return a list of multiple actions. Here is an example of a valid $JSON_BLOB:\n\n```\n{{\n\"action\": $TOOL_NAME,\n\"action_input\": $INPUT\n}}\n```\n\nALWAYS use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction:\n```\n$JSON_BLOB\n```\nObservation: the result of the action\n... (this Thought/Action/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\n\nBegin! Reminder to always use the exact characters `Final Answer` when responding.\n" }, { "role":"user", "content":"Question: 北京和广州天气怎么样\n\n" } ],"stop":"Observation:"}'
2. LLM返回Action获取北京天气LLM经过推理，发现需要先调用函数获取北京天气。 Thought:我需要获取北京和广州的天气信息。首先，我将获取北京的天气。Action:```{"action":"get_weather","action_input":{"location":"北京"}}```完整的JSON响应如下： {"choices":[{"message":{"content":"Thought:我需要获取北京和广州的天气信息。首先，我将获取北京的天气。\n\nAction:\n```\n{\n\"action\":\"get_weather\",\n\"action_input\":{\n\"location\":\"北京\"\n}\n}\n```","role":"assistant"},"finish_reason":"stop","index":0,"logprobs":null}],"object":"chat.completion","usage":{"prompt_tokens":305,"completion_tokens":49,"total_tokens":354},"created":1745651748,"system_fingerprint":null,"model":"deepseek-v3","id":"chatcmpl-697b0627-4fca-975b-954c-7304386ac224"}
3. 处理函数调用获取北京天气解析处理LLM的Action获得函数名和参数列表，调用相应的API接口获得结果。 例如：通过http://weather.cma.cn/api/now/54511可获得北京的天气情况。 完整的JSON响应如下： {"msg":"success","code":0,"data":{"location":{"id":"54511","name":"北京","path":"中国,北京,北京"},"now":{"precipitation":0.0,"temperature":23.4,"pressure":1005.0,"humidity":43.0,"windDirection":"西南风","windDirectionDegree":216.0,"windSpeed":2.7,"windScale":"微风","feelst":23.1},"alarm":[],"jieQi":"","lastUpdate":"2025/04/2615:00"}}
4. 把上下文信息以及函数调用结果发给LLM发给LLM的messages列表有2条messages： - 第1条role为
system，定义了系统提示词(含工具定义) - Thought: 我需要获取北京和广州的天气信息。首先，我将获取北京的天气
- Action: {"action":"get_weather","action_input":{"location":"北京"}}
- Observation: 工具调用
get_weather('北京')的结果
#!/bin/bashexportOPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"exportOPENAI_API_KEY="sk-xxx"# 替换为你的key
curl ${OPENAI_BASE_URL}/chat/completions \-H"Content-Type: application/json"\-H"Authorization: Bearer $OPENAI_API_KEY"\-d '{"model":"deepseek-v3","messages": [ { "role":"system", "content":"\nAnswer the following questions as best you can. You have access to the following tools:\n{\"name\":\"get_weather\",\"description\":\"Get weather\",\"parameters\": {\"type\":\"object\",\"properties\": {\"location\": {\"type\":\"string\",\"description\":\"the name of the location\"}},\"required\": [\"location\"]}}\n\n\nThe way you use the tools is by specifying a json blob.\nSpecifically, this json should have a `action` key (with the name of the tool to use) and a `action_input` key (with the input to the tool going here).\n\nThe only values that should be in the\"action\"field are: get_weather\n\nThe $JSON_BLOB should only contain a SINGLE action, do NOT return a list of multiple actions. Here is an example of a valid $JSON_BLOB:\n\n```\n{{\n\"action\": $TOOL_NAME,\n\"action_input\": $INPUT\n}}\n```\n\nALWAYS use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction:\n```\n$JSON_BLOB\n```\nObservation: the result of the action\n... (this Thought/Action/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\n\nBegin! Reminder to always use the exact characters `Final Answer` when responding.\n" }, { "role":"user", "content":"Question: 北京和广州天气怎么样\n\nThought: 我需要获取北京和广州的天气信息。首先，我将获取北京的天气。\n\nAction:\n```\n{\n\"action\":\"get_weather\",\n\"action_input\": {\n\"location\":\"北京\"\n}\n}\n```\nObservation: {\"msg\":\"success\",\"code\":0,\"data\":{\"location\":{\"id\":\"54511\",\"name\":\"北京\",\"path\":\"中国, 北京, 北京\"},\"now\":{\"precipitation\":0.0,\"temperature\":23.4,\"pressure\":1005.0,\"humidity\":43.0,\"windDirection\":\"西南风\",\"windDirectionDegree\":216.0,\"windSpeed\":2.7,\"windScale\":\"微风\",\"feelst\":23.1},\"alarm\":[],\"jieQi\":\"\",\"lastUpdate\":\"2025/04/26 15:00\"}}\n" } ],"stop":"Observation:"}'
5. LLM返回Action获取广州天气LLM经过推理，发现还需要调用函数获取广州天气。 Thought:我已经获取了北京的天气信息。接下来，我将获取广州的天气信息。Action:```{"action":"get_weather","action_input":{"location":"广州"}}```
完整的JSON响应如下： {"choices":[{"message":{"content":"Thought:我已经获取了北京的天气信息。接下来，我将获取广州的天气信息。\n\nAction:\n```\n{\n\"action\":\"get_weather\",\n\"action_input\":{\n\"location\":\"广州\"\n}\n}\n```\nObservation","role":"assistant"},"finish_reason":"stop","index":0,"logprobs":null}],"object":"chat.completion","usage":{"prompt_tokens":472,"completion_tokens":46,"total_tokens":518},"created":1745651861,"system_fingerprint":null,"model":"deepseek-v3","id":"chatcmpl-a822b8d7-9105-9dc2-8e98-4327afb50b3a"}
6. 处理函数调用获取广州天气解析处理LLM的Action获得函数名和参数列表，调用相应的API接口获得结果。 例如：通过http://weather.cma.cn/api/now/59287可获得广州的天气情况。 完整的JSON响应如下： {"msg":"success","code":0,"data":{"location":{"id":"59287","name":"广州","path":"中国,广东,广州"},"now":{"precipitation":0.0,"temperature":24.2,"pressure":1005.0,"humidity":79.0,"windDirection":"东北风","windDirectionDegree":31.0,"windSpeed":1.3,"windScale":"微风","feelst":27.1},"alarm":[],"jieQi":"","lastUpdate":"2025/04/2615:00"}}
7. 把上下文信息以及函数调用结果发给LLM发给LLM的messages列表有2条messages： - 第1条role为
system，定义了系统提示词(含工具定义) - Thought: 我需要获取北京和广州的天气信息。首先，我将获取北京的天气
- Action: {"action":"get_weather","action_input":{"location":"北京"}}
- Observation: 工具调用
get_weather('北京')的结果 - Thought: 现在我已经获取了北京的天气信息，接下来我将获取广州的天气信息。
- Action: {"action":"get_weather","action_input":{"location":"广州"}}
- Observation: 工具调用
get_weather('广州')的结果
#!/bin/bashexportOPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"exportOPENAI_API_KEY="sk-xxx"# 替换为你的key
curl ${OPENAI_BASE_URL}/chat/completions \-H"Content-Type: application/json"\-H"Authorization: Bearer $OPENAI_API_KEY"\-d '{"model":"deepseek-v3","messages": [ { "role":"system", "content":"\nAnswer the following questions as best you can. You have access to the following tools:\n{\"name\":\"get_weather\",\"description\":\"Get weather\",\"parameters\": {\"type\":\"object\",\"properties\": {\"location\": {\"type\":\"string\",\"description\":\"the name of the location\"}},\"required\": [\"location\"]}}\n\n\nThe way you use the tools is by specifying a json blob.\nSpecifically, this json should have a `action` key (with the name of the tool to use) and a `action_input` key (with the input to the tool going here).\n\nThe only values that should be in the\"action\"field are: get_weather\n\nThe $JSON_BLOB should only contain a SINGLE action, do NOT return a list of multiple actions. Here is an example of a valid $JSON_BLOB:\n\n```\n{{\n\"action\": $TOOL_NAME,\n\"action_input\": $INPUT\n}}\n```\n\nALWAYS use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction:\n```\n$JSON_BLOB\n```\nObservation: the result of the action\n... (this Thought/Action/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\n\nBegin! Reminder to always use the exact characters `Final Answer` when responding.\n" }, { "role":"user", "content":"Question: 北京和广州天气怎么样\n\nThought: 我需要获取北京和广州的天气信息。首先，我将获取北京的天气。\n\nAction:\n```\n{\n\"action\":\"get_weather\",\n\"action_input\": {\n\"location\":\"北京\"\n}\n}\n```\nObservation: {\"msg\":\"success\",\"code\":0,\"data\":{\"location\":{\"id\":\"54511\",\"name\":\"北京\",\"path\":\"中国, 北京, 北京\"},\"now\":{\"precipitation\":0.0,\"temperature\":23.4,\"pressure\":1005.0,\"humidity\":43.0,\"windDirection\":\"西南风\",\"windDirectionDegree\":216.0,\"windSpeed\":2.7,\"windScale\":\"微风\",\"feelst\":23.1},\"alarm\":[],\"jieQi\":\"\",\"lastUpdate\":\"2025/04/26 15:00\"}}\nThought: 现在我已经获取了北京的天气信息，接下来我将获取广州的天气信息。\n\nAction:\n```\n{\n\"action\":\"get_weather\",\n\"action_input\": {\n\"location\":\"广州\"\n}\n}\n```\nObservation\nObservation: {\"msg\":\"success\",\"code\":0,\"data\":{\"location\":{\"id\":\"59287\",\"name\":\"广州\",\"path\":\"中国, 广东, 广州\"},\"now\":{\"precipitation\":0.0,\"temperature\":24.2,\"pressure\":1005.0,\"humidity\":79.0,\"windDirection\":\"东北风\",\"windDirectionDegree\":31.0,\"windSpeed\":1.3,\"windScale\":\"微风\",\"feelst\":27.1},\"alarm\":[],\"jieQi\":\"\",\"lastUpdate\":\"2025/04/26 15:00\"}}\n" } ],"stop":"Observation:"}'
8. LLM生成最终回复LLM生成最终的回复： Thought: 我已经获取了北京和广州的天气信息，现在可以回答用户的问题了。
FinalAnswer: 北京的天气温度为23.4°C，湿度为43%，风向为西南风，风速为2.7米/秒。广州 的天气温度为24.2°C，湿度为79%，风向为东北风，风速为1.3米/秒。
完整的JSON响应如下： {"choices":[{"message":{"content":"Thought:我已经获取了北京和广州的天气信息，现在可以回答用户的问题了。\n\nFinalAnswer:北京的天气温度为23.4°C，湿度为43%，风向为西南风，风速为2.7米/秒。广州的天气温度为24.2°C，湿度为79%，风向为东北风，风速为1.3米/秒。","role":"assistant"},"finish_reason":"stop","index":0,"logprobs":null}],"object":"chat.completion","usage":{"prompt_tokens":641,"completion_tokens":79,"total_tokens":720},"created":1745652025,"system_fingerprint":null,"model":"deepseek-v3","id":"chatcmpl-d9b85f31-589e-9c6f-8694-cf813344e464"}
手搓Agent代码实现基于ReAct的工具调用1. 创建python环境uv init agent
cdagent
uv venv
.venv\Scripts\activate
uvaddopenai requests python-dotenv
2. 设置API Key创建.env，.env内容如下（注意修改OPENAI_API_KEY为您的key） OPENAI_API_KEY=your_api_key_here
OPENAI_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
把.env添加到.gitignore 3. 实现Agent代码基于openai sdk实现ReAct agent的伪代码主体逻辑如下： maxIter=5#最大迭代次数agent_scratchpad=""#agent思考过程(Thought/Action/Observation)foriterSeqinrange(1,maxIter+1):构造chatcompletion请求messages有2条第1条为系统提示词消息(含工具定义)第2条为用户消息：Question+agent思考过程(Thought/Action/Observation)stop参数设置为"Observation:"获取chatcompletion结果如果chatcompletion结果带有"FinalAnswer:"返回最终答案如果chatcompletion结果带有Action解析并调用相应函数更新agent思考过程：把本次LLM的输出(Though/Action)和工具调用结果(Observation)添加到agent_scratchpad继续迭代
完整的main.py代码如下： importjsonimportreimportrequestsimporturllib.parsefromtypingimportIterablefromopenaiimportOpenAIfromopenai.types.chat.chat_completion_message_paramimportChatCompletionMessageParamfromopenai.types.chat.chat_completion_user_message_paramimport( ChatCompletionUserMessageParam,)fromopenai.types.chat.chat_completion_system_message_paramimport( ChatCompletionSystemMessageParam,)
# 加载环境变量fromdotenvimportload_dotenvload_dotenv()
client = OpenAI()model ="deepseek-v3"
# 工具定义tools = [ { "type":"function", "function": { "name":"get_weather", "description":"Get weather", "parameters": { "type":"object", "properties": { "location": {"type":"string","description":"location"} }, "required": ["location"], }, }, }]
# 系统提示词defget_system_prompt(): tool_strings ="\n".join([json.dumps(tool["function"])fortoolintools]) tool_names =", ".join([tool["function"]["name"]fortoolintools]) systemPromptFormat ="""Answer the following questions as best you can. You have access to the following tools:{tool_strings}
The way you use the tools is by specifying a json blob.Specifically, this json should have a `action` key (with the name of the tool to use) and a `action_input` key (with the input to the tool going here).
The only values that should be in the "action" field are: {tool_names}
The $JSON_BLOB should only contain a SINGLE action, do NOT return a list of multiple actions. Here is an example of a valid $JSON_BLOB:
```{{{{"action": $TOOL_NAME,"action_input": $INPUT}}}}```
ALWAYS use the following format:
Question: the input question you must answerThought: you should always think about what to doAction:```$JSON_BLOB```Observation: the result of the action... (this Thought/Action/Observation can repeat N times)Thought: I now know the final answerFinal Answer: the final answer to the original input question
Begin! Reminder to always use the exact characters `Final Answer` when responding.""" returnsystemPromptFormat.format(tool_strings=tool_strings, tool_names=tool_names)
# 实现获取天气defget_weather(location:str) ->str: url ="http://weather.cma.cn/api/autocomplete?q="+ urllib.parse.quote(location) response = requests.get(url) data = response.json() ifdata["code"] !=0: return"没找到该位置的信息" location_code ="" foritemindata["data"]: str_array = item.split("|") if( str_array[1] == location orstr_array[1] +"市"== location orstr_array[2] == location ): location_code = str_array[0] break iflocation_code =="": return"没找到该位置的信息" url =f"http://weather.cma.cn/api/now/{location_code}" returnrequests.get(url).text
# 实现工具调用definvoke_tool(toolName:str, toolParamaters) ->str: result ="" iftoolName =="get_weather": result = get_weather(toolParamaters["location"]) else: result =f"函数{toolName}未定义" returnresult
defmain(): query ="北京和广州天气怎么样" systemMsg = ChatCompletionSystemMessageParam( role="system", content=get_system_prompt() ) maxIter =5# 最大迭代次数 agent_scratchpad =""# agent思考过程 action_pattern = re.compile(r"\nAction:\n`{3}(?:json)?\n(.*?)`{3}.*?$", re.DOTALL) foriterSeqinrange(1, maxIter +1): messages: Iterable[ChatCompletionMessageParam] =list() messages.append(systemMsg) messages.append( ChatCompletionUserMessageParam( role="user", content=f"Question:{query}\n\n{agent_scratchpad}" ) ) print(f">> iterSeq:{iterSeq}") print(f">>> messages:{json.dumps(messages)}") # 向LLM发起请求，注意需要设置stop参数 chat_completion = client.chat.completions.create( messages=messages, model=model, stop="Observation:", ) content = chat_completion.choices[0].message.content print(f">>> content:\n{content}") final_answer_match = re.search(r"\nFinal Answer:\s*(.*)", content) iffinal_answer_match: final_answer = final_answer_match.group(1) print(f">>> 最终答案:{final_answer}") return action_match = action_pattern.search(content) ifaction_match: obj = json.loads(action_match.group(1)) toolName = obj["action"] toolParameters = obj["action_input"] print(f">>> tool name:{toolName}") print(f">>> tool parameters:{toolParameters}") result = invoke_tool(toolName, toolParameters) print(f">>> tool result:{result}") # 把本次LLM的输出(Though/Action)和工具调用结果(Observation)添加到agent_scratchpad agent_scratchpad += content +f"\nObservation:{result}\n" else: print(">>> ERROR: detect invalid response") return print(">>> 迭代次数达到上限，我无法得到最终答案")
main()
运行代码：uv run .\main.py >>iterSeq:1>>>messages: [{"role":"system","content":"\nAnswer the following questions as best you can. You have access to the following tools:\n{\"name\":\"get_weather\",\"description\":\"Get weather\",\"parameters\": {\"type\":\"object\",\"properties\": {\"location\": {\"type\":\"string\",\"description\":\"the name of the location\"}},\"required\": [\"location\"]}}\n\n\nThe way you use the tools is by specifying a json blob.\nSpecifically, this json should have a `action` key (with the name of the tool to use) and a `action_input` key (with the input to the tool going here).\n\nThe only values that should be in the\"action\"field are: get_weather\n\nThe $JSON_BLOB should only contain a SINGLE action, do NOT return a list of multiple actions. Here is an example of a valid $JSON_BLOB:\n\n```\n{{\n\"action\": $TOOL_NAME,\n\"action_input\": $INPUT\n}}\n```\n\nALWAYS use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction:\n```\n$JSON_BLOB\n```\nObservation: the result of the action\n... (this Thought/Action/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\n\nBegin! Reminder to always use the exact characters `Final Answer` when responding.\n"}, {"role":"user","content":"Question: \u5317\u4eac\u548c\u5e7f\u5dde\u5929\u6c14\u600e\u4e48\u6837\n\n"}]>>>content:Thought: 我需要获取北京和广州的天气信息。首先，我将获取北京的天气。
Action:```{"action":"get_weather","action_input": {"location":"北京"}}```>>>tool name:get_weather>>>tool parameters:{'location': '北京'}>>>tool result: {"msg":"success","code":0,"data":{"location":{"id":"54511","name":"北京","path":"中国, 北京, 北京"},"now":{"precipitation":0.0,"temperature":23.4,"pressure":1005.0,"humidity":43.0,"windDirection":"西南风","windDirectionDegree":216.0,"windSpeed":2.7,"windScale":"微风","feelst":23.1},"alarm":[],"jieQi":"","lastUpdate":"2025/04/26 15:00"}}>>iterSeq:2>>>messages: [{"role":"system","content":"\nAnswer the following questions as best you can. You have access to the following tools:\n{\"name\":\"get_weather\",\"description\":\"Get weather\",\"parameters\": {\"type\":\"object\",\"properties\": {\"location\": {\"type\":\"string\",\"description\":\"the name of the location\"}},\"required\": [\"location\"]}}\n\n\nThe way you use the tools is by specifying a json blob.\nSpecifically, this json should have a `action` key (with the name of the tool to use) and a `action_input` key (with the input to the tool going here).\n\nThe only values that should be in the\"action\"field are: get_weather\n\nThe $JSON_BLOB should only contain a SINGLE action, do NOT return a list of multiple actions. Here is an example of a valid $JSON_BLOB:\n\n```\n{{\n\"action\": $TOOL_NAME,\n\"action_input\": $INPUT\n}}\n```\n\nALWAYS use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction:\n```\n$JSON_BLOB\n```\nObservation: the result of the action\n... (this Thought/Action/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\n\nBegin! Reminder to always use the exact characters `Final Answer` when responding.\n"}, {"role":"user","content":"Question: \u5317\u4eac\u548c\u5e7f\u5dde\u5929\u6c14\u600e\u4e48\u6837\n\nThought: \u6211\u9700\u8981\u83b7\u53d6\u5317\u4eac\u548c\u5e7f\u5dde\u7684\u5929\u6c14\u4fe1\u606f\u3002\u9996\u5148\uff0c\u6211\u5c06\u83b7\u53d6\u5317\u4eac\u7684\u5929\u6c14\u3002\n\nAction:\n```\n{\n\"action\":\"get_weather\",\n\"action_input\": {\n\"location\":\"\u5317\u4eac\"\n}\n}\n```\nObservation: {\"msg\":\"success\",\"code\":0,\"data\":{\"location\":{\"id\":\"54511\",\"name\":\"\u5317\u4eac\",\"path\":\"\u4e2d\u56fd, \u5317\u4eac, \u5317\u4eac\"},\"now\":{\"precipitation\":0.0,\"temperature\":23.4,\"pressure\":1005.0,\"humidity\":43.0,\"windDirection\":\"\u897f\u5357\u98ce\",\"windDirectionDegree\":216.0,\"windSpeed\":2.7,\"windScale\":\"\u5fae\u98ce\",\"feelst\":23.1},\"alarm\":[],\"jieQi\":\"\",\"lastUpdate\":\"2025/04/26 15:00\"}}\n"}]>>>content:Thought: 现在我已经获取了北京的天气信息，接下来我将获取广州的天气信息。
Action:```{"action":"get_weather","action_input": {"location":"广州"}}```Observation>>>tool name:get_weather>>>tool parameters:{'location': '广州'}>>>tool result: {"msg":"success","code":0,"data":{"location":{"id":"59287","name":"广州","path":"中国, 广东, 广州"},"now":{"precipitation":0.0,"temperature":24.2,"pressure":1005.0,"humidity":79.0,"windDirection":"东北风","windDirectionDegree":31.0,"windSpeed":1.3,"windScale":"微风","feelst":27.1},"alarm":[],"jieQi":"","lastUpdate":"2025/04/26 15:00"}}>>iterSeq:3>>>messages: [{"role":"system","content":"\nAnswer the following questions as best you can. You have access to the following tools:\n{\"name\":\"get_weather\",\"description\":\"Get weather\",\"parameters\": {\"type\":\"object\",\"properties\": {\"location\": {\"type\":\"string\",\"description\":\"the name of the location\"}},\"required\": [\"location\"]}}\n\n\nThe way you use the tools is by specifying a json blob.\nSpecifically, this json should have a `action` key (with the name of the tool to use) and a `action_input` key (with the input to the tool going here).\n\nThe only values that should be in the\"action\"field are: get_weather\n\nThe $JSON_BLOB should only contain a SINGLE action, do NOT return a list of multiple actions. Here is an example of a valid $JSON_BLOB:\n\n```\n{{\n\"action\": $TOOL_NAME,\n\"action_input\": $INPUT\n}}\n```\n\nALWAYS use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction:\n```\n$JSON_BLOB\n```\nObservation: the result of the action\n... (this Thought/Action/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\n\nBegin! Reminder to always use the exact characters `Final Answer` when responding.\n"}, {"role":"user","content":"Question: \u5317\u4eac\u548c\u5e7f\u5dde\u5929\u6c14\u600e\u4e48\u6837\n\nThought: \u6211\u9700\u8981\u83b7\u53d6\u5317\u4eac\u548c\u5e7f\u5dde\u7684\u5929\u6c14\u4fe1\u606f\u3002\u9996\u5148\uff0c\u6211\u5c06\u83b7\u53d6\u5317\u4eac\u7684\u5929\u6c14\u3002\n\nAction:\n```\n{\n\"action\":\"get_weather\",\n\"action_input\": {\n\"location\":\"\u5317\u4eac\"\n}\n}\n```\nObservation: {\"msg\":\"success\",\"code\":0,\"data\":{\"location\":{\"id\":\"54511\",\"name\":\"\u5317\u4eac\",\"path\":\"\u4e2d\u56fd, \u5317\u4eac, \u5317\u4eac\"},\"now\":{\"precipitation\":0.0,\"temperature\":23.4,\"pressure\":1005.0,\"humidity\":43.0,\"windDirection\":\"\u897f\u5357\u98ce\",\"windDirectionDegree\":216.0,\"windSpeed\":2.7,\"windScale\":\"\u5fae\u98ce\",\"feelst\":23.1},\"alarm\":[],\"jieQi\":\"\",\"lastUpdate\":\"2025/04/26 15:00\"}}\nThought: \u73b0\u5728\u6211\u5df2\u7ecf\u83b7\u53d6\u4e86\u5317\u4eac\u7684\u5929\u6c14\u4fe1\u606f\uff0c\u63a5\u4e0b\u6765\u6211\u5c06\u83b7\u53d6\u5e7f\u5dde\u7684\u5929\u6c14\u4fe1\u606f\u3002\n\nAction:\n```\n{\n\"action\":\"get_weather\",\n\"action_input\": {\n\"location\":\"\u5e7f\u5dde\"\n}\n}\n```\nObservation\nObservation: {\"msg\":\"success\",\"code\":0,\"data\":{\"location\":{\"id\":\"59287\",\"name\":\"\u5e7f\u5dde\",\"path\":\"\u4e2d\u56fd, \u5e7f\u4e1c, \u5e7f\u5dde\"},\"now\":{\"precipitation\":0.0,\"temperature\":24.2,\"pressure\":1005.0,\"humidity\":79.0,\"windDirection\":\"\u4e1c\u5317\u98ce\",\"windDirectionDegree\":31.0,\"windSpeed\":1.3,\"windScale\":\"\u5fae\u98ce\",\"feelst\":27.1},\"alarm\":[],\"jieQi\":\"\",\"lastUpdate\":\"2025/04/26 15:00\"}}\n"}]>>>content:Thought: 我已经获取了北京和广州的天气信息，现在可以回答用户的问题了。
FinalAnswer: 北京的天气情况为：温度23.4°C，湿度43%，西南风，风速2.7米/秒，微风。广州的天气情况为：温度24.2°C，湿度79%，东北风，风速1.3米/秒，微风。>>>最终答案: 北京的天气情况为：温度23.4°C，湿度43%，西南风，风速2.7米/秒，微风。广州的天气情况为：温度24.2°C，湿度79%，东北风，风速1.3米/秒，微风。
总结基于Function Calling和基于ReAct的工具调用有各自的优缺点： 1. Function Calling- 无需设定系统提示词，LLM根据tools定义即可触发工具调用，token消耗较少
- 模型参数量相对较大。模型的训练数据必须包含Function Calling相关的内容，以确保模型能够理解和生成结构化输出，结构化输出更稳定
2. ReAct- 输出结果处理比Function Calling复杂
END |
