秒懂Function Call：DeepSeek大模型的隐藏超能力，让AI从会聊天变会做事

# 定义一个天气查询函数def get_weather(location, date):"""查询指定地点和日期的天气
参数:location (str): 城市名称date (str): 日期，格式为YYYY-MM-DD
返回:dict: 包含天气信息的字典"""# 实际应用中，这里会调用天气APIimport requests
api_url = f"https://weather-api.example.com/forecast?location={location}&date={date}"response = requests.get(api_url)
if response.status_code == 200:return response.json()else:return {"error": "无法获取天气信息"}
# DeepSeek如何使用Function Calldef deepseek_with_function_call(user_query):# 1. 模型理解用户查询天气的意图if "天气" in user_query:# 2. 提取地点和时间信息location = extract_location(user_query)# 假设这个函数能提取位置date = extract_date(user_query)# 假设这个函数能提取日期
# 3. 调用天气函数weather_data = get_weather(location, date)
# 4. 格式化回复response = f"{location}{date}天气为{weather_data['condition']}，"response += f"温度在{weather_data['min_temp']}°C至{weather_data['max_temp']}°C之间，"response += f"降水概率{weather_data['precipitation_chance']}%。"
return response
# 其他类型的查询...return "我无法理解您的问题。"

# 商品搜索函数def search_products(product_type, color=None, max_price=None, min_price=None):"""搜索符合条件的商品
参数:product_type (str): 商品类型color (str, optional): 颜色max_price (float, optional): 最高价格min_price (float, optional): 最低价格
返回:list: 符合条件的商品列表"""# 实际中会调用电商平台API# 这里用模拟数据演示all_products = [{"id": 1, "name": "夏季红色连衣裙", "color": "红色", "price": 259.00},{"id": 2, "name": "优雅红色长裙", "color": "红色", "price": 329.00},{"id": 3, "name": "简约红色连衣裙", "color": "红色", "price": 199.00}]
results = []for product in all_products:if product_type in product["name"] and \ (color is None or product["color"] == color) and \ (max_price is None or product["price"] <= max_price) and \ (min_price is None or product["price"] >= min_price):results.append(product)
return results
# DeepSeek处理购物查询def handle_shopping_query(query):# 提取查询信息if "连衣裙" in query and "红色" in query:# 解析价格条件max_price = 300# 从查询中提取"低于300元"
# 调用商品搜索函数products = search_products("连衣裙", color="红色", max_price=max_price)
# 格式化回复if products:response = f"我找到了{len(products)}款符合条件的红色连衣裙：\n"for p in products:response += f"- {p['name']}，售价{p['price']}元\n"else:response = "抱歉，没有找到符合条件的商品。"
return response

# 注册可用函数available_functions = {"get_weather": {"description": "获取指定地点和日期的天气信息","parameters": {"type": "object","properties": {"location": {"type": "string","description": "城市名称，如'北京'、'上海'"},"date": {"type": "string","description": "日期，格式为YYYY-MM-DD"}},"required": ["location"]}},"search_products": {"description": "搜索符合条件的商品","parameters": {"type": "object","properties": {"product_type": {"type": "string","description": "商品类型，如'连衣裙'、'手机'"},"color": {"type": "string","description": "商品颜色"},"max_price": {"type": "number","description": "最高价格"}},"required": ["product_type"]}}}

def process_user_query(user_query):# 模拟DeepSeek分析用户意图的过程
# 假设这是模型的思考过程"""用户问"上海明天天气怎么样"，明显是查询天气信息。需要的信息：城市=上海，日期=明天(2025-02-27)应该调用get_weather函数"""
# 模型决定调用get_weather函数function_call = {"name": "get_weather","arguments": {"location": "上海","date": "2025-02-27"}}
return function_call

def deepseek_complete_response(user_query):# 1. 确定需要调用的函数function_call = process_user_query(user_query)
# 2. 执行函数调用if function_call["name"] == "get_weather":args = function_call["arguments"]weather_data = get_weather(args["location"], args["date"])
# 3. 将函数结果融入自然语言回答response = f"{args['location']}在{args['date']}的天气预报：\n"response += f"天气状况: {weather_data['condition']}\n"response += f"温度范围: {weather_data['min_temp']}°C - {weather_data['max_temp']}°C\n"response += f"降水概率: {weather_data['precipitation_chance']}%\n"
if weather_data['precipitation_chance'] > 50:response += "建议您出门携带雨伞！"
return response
# 其他函数调用类似处理...

# 传统API调用 - 开发者必须硬编码逻辑def traditional_weather_app(user_input):if "天气" in user_input and extract_location(user_input):location = extract_location(user_input)date = extract_date(user_input) or "today"try:weather_data = weather_api.get_forecast(location, date)return format_weather_response(weather_data)except ApiError as e:return f"获取天气失败: {e}"else:return "我不理解您的问题"
# Function Call - 模型自主决策def function_call_assistant(user_input):# 模型分析输入，自主决定是否需要天气信息function_decision = model.analyze(user_input)
if function_decision.needs_function_call:# 模型自动生成结构化参数function_name = function_decision.function_name# 可能是"get_weather"或其他function_args = function_decision.arguments# 模型提取的参数
try:result = call_function(function_name, function_args)except Exception as e:# 模型能理解错误并尝试修正参数后重试corrected_args = model.correct_arguments(function_args, error=str(e))result = call_function(function_name, corrected_args)
# 模型融合函数结果生成回答return model.generate_response(user_input, function_result=result)else:# 模型判断不需要调用外部函数return model.generate_response(user_input)