【大语言模型LLM】-基于大语言模型搭建客服助手（2）

发布于：2024-05-04 ⋅ 阅读:(28) ⋅ 点赞:(0)

在这里插入图片描述

🔥博客主页：西瓜WiFi

🎥系列专栏：《大语言模型》

很多非常有趣的模型，值得收藏，满足大家的收集癖！ 如果觉得有用，请三连👍⭐❤️，谢谢！

长期不定时更新，欢迎watch和fork！❤️❤️❤️

❤️感谢大家点赞👍 收藏⭐ 评论⭐

🎥大语言模型LLM基础-系列文章：

【大语言模型LLM】- AI工具收录集合，一篇就够了！
【大语言模型LLM】-大语言模型如何编写Prompt?
【大语言模型LLM】-如何使用大语言模型提高工作效率？
【大语言模型LLM】-使用大语言模型搭建点餐机器人
【大语言模型LLM】-基础语言模型和指令微调的语言模型
【大语言模型LLM】-基于ChatGPT搭建客服助手（1）

⭐持续更新中…

接上一篇【大语言模型LLM】-基于ChatGPT搭建客服助手（1），本篇我们将不局限于使用ChatGPT的API，还将调用使用Ollama+LLM部署在本地的大语言模型，实现机器人助手的私有化搭建。这部分内容融合了我们前面几篇的全部内容。并且加入了评估步骤。以下是该系统的核心操作流程：

  1. 根据用户输入，获取相关产品信息。
  2. 若产品搜索成功，我们将继续寻找相关的详细产品信息。
  3. 我们使用模型针对用户的问题进行回答。
  4. 最后，让模型自己评估回答是否符合用户需求。

最终，将审核通过的答案呈现给用户。

第一部分 根据用户的输入获取产品列表

import json
from collections import defaultdict


# 获取商品和目录
def get_products_and_category(products_file):
    try:
        with open(products_file, 'r') as file:
            products = json.load(file)
    except FileNotFoundError:
        print('产品文件不存在！')
        return None
    except json.JSONDecodeError:
        print('产品文件格式错误！')
        return None
    # 利用 defaultdict 创建一个空列表，用于存放不同类别的产品信息
    products_by_category = defaultdict(list)
    # 循环遍历产品信息
    for product_name, product_info in products.items():
        # 获取产品类别的信息
        category = product_info.get('category')
        # 如果产品类别存在，则将产品名称添加到对应的列表中
        if category:
            products_by_category[category].append(product_info.get('name'))
    # 返回产品按类别分组的信息
    return dict(products_by_category)


# 将字符串转换为列表
def read_string_to_list(input_string):
    if input_string is None:
        return None

    try:
        # 将单引号替换为双引号以生成有效的 JSON
        input_string = input_string.replace("'", "\"")  
        data = json.loads(input_string)
        return data
    except json.JSONDecodeError:
        print(input_string)
        print("错误：非法的 Json 格式")
        return None


# 获取目录和产品
def find_category_and_product_only(user_input,products_and_category):
    delimiter = "####"
    system_message = f"""
    您将获得客户服务查询。
    客户服务查询将使用{delimiter}字符作为分隔符。
    请仅输出一个可解析的Python列表，列表每一个元素是一个JSON对象，每个对象具有以下格式：
    'category': <包括以下几个类别：Computers and Laptops、Smartphones and Accessories、Televisions and Home Theater Systems、Gaming Consoles and Accessories、Audio Equipment、Cameras and Camcorders>,
    以及
    'products': <必须是下面的允许产品列表中找到的产品列表>

    类别和产品必须在客户服务查询中找到。
    如果提到了某个产品，它必须与允许产品列表中的正确类别关联。
    如果未找到任何产品或类别，则输出一个空列表。
    除了列表外，不要输出其他任何信息！

    允许的产品：

    Computers and Laptops category:
    TechPro Ultrabook
    BlueWave Gaming Laptop
    PowerLite Convertible
    TechPro Desktop
    BlueWave Chromebook

    Smartphones and Accessories category:
    SmartX ProPhone
    MobiTech PowerCase
    SmartX MiniPhone
    MobiTech Wireless Charger
    SmartX EarBuds

    Televisions and Home Theater Systems category:
    CineView 4K TV
    SoundMax Home Theater
    CineView 8K TV
    SoundMax Soundbar
    CineView OLED TV

    Gaming Consoles and Accessories category:
    GameSphere X
    ProGamer Controller
    GameSphere Y
    ProGamer Racing Wheel
    GameSphere VR Headset

    Audio Equipment category:
    AudioPhonic Noise-Canceling Headphones
    WaveSound Bluetooth Speaker
    AudioPhonic True Wireless Earbuds
    WaveSound Soundbar
    AudioPhonic Turntable

    Cameras and Camcorders category:
    FotoSnap DSLR Camera
    ActionCam 4K
    FotoSnap Mirrorless Camera
    ZoomMaster Camcorder
    FotoSnap Instant Camera

    只输出对象列表，不包含其他内容。
    """
    messages =  [  
    {'role':'system', 'content': system_message},    
    {'role':'user', 'content': f"{delimiter}{user_input}{delimiter}"},  
    ] 
    return get_gemma_response(messages)


# 商品和目录的数据文件
products_file = 'products.json'
categories_file = 'categories.json'

# 获取目录和产品
category_and_product_response = find_category_and_product_only('你好，有电视机嘛？',products_and_category)

# 将字符串转换为列表
category_and_product_list = read_string_to_list(category_and_product_response)

print("第一步：抽取出商品列表")
print('- '*65)
print(category_and_product_list)

输出结果：

第一步：抽取出商品列表
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
[{'category': 'Televisions and Home Theater Systems', 'products': ['CineView 4K TV', 'CineView 8K TV', 'CineView OLED TV']}]

第二部分 根据商品列表抽取商品信息

# 商品信息的搜索
def get_product_by_name(name):
    products = get_products()
    return products.get(name, None)


# 根据商品列表抽取商品信息
def generate_output_string(data_list):
    """
    根据商品列表抽取商品信息并生成输出字符串。

    参数：
        data_list：包含商品信息的列表。

    返回：
        输出字符串。
    """

    output_string = ""

    # 如果输入列表为 None，则返回空字符串。
    if data_list is None:
        return output_string

    # 循环遍历数据列表中的每个项目。
    for data in data_list:
        try:
            # 如果项目包含 "products" 字段，则获取产品列表并循环遍历产品名称。
            if "products" in data:
                products_list = data["products"]
                for product_name in products_list:
                    # 获取产品名称对应的产品对象。
                    product = get_product_by_name(product_name)
                    # 如果产品存在，则将其转换为 JSON 字符串并将其追加到输出字符串中。
                    if product:
                        output_string += json.dumps(product, indent=4) + "\n"
                    # 如果产品不存在，则打印错误信息。
                    else:
                        print(f"错误: 商品 '{product_name}' 没有找到")
            # 如果项目包含 "category" 字段，则获取该类别的产品列表并循环遍历产品。
            elif "category" in data:
                category_name = data["category"]
                category_products = get_products_by_category(category_name)
                for product in category_products:
                    output_string += json.dumps(product, indent=4) + "\n"
            # 如果数据格式不正确，则打印错误信息。
            else:
                print("错误：非法的商品格式")
        # 捕获所有异常并打印错误信息。
        except Exception as e:
            print(f"Error: {e}")

    return output_string

product_information = generate_output_string(category_and_product_list)

print("第二步：抽取商品信息")
print('- '*65)
print(product_information)

输出结果：

第二步：抽取商品信息
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
{
    "name": "CineView 4K TV",
    "category": "Televisions and Home Theater Systems",
    "brand": "CineView",
    "model_number": "CV-4K55",
    "warranty": "2 years",
    "rating": 4.8,
    "features": [
        "55-inch display",
        "4K resolution",
        "HDR",
        "Smart TV"
    ],
    "description": "A stunning 4K TV with vibrant colors and smart features.",
    "price": 599.99
}
{
    "name": "CineView 8K TV",
    "category": "Televisions and Home Theater Systems",
    "brand": "CineView",
    "model_number": "CV-8K65",
    "warranty": "2 years",
    "rating": 4.9,
    "features": [
        "65-inch display",
        "8K resolution",
        "HDR",
        "Smart TV"
    ],
    "description": "Experience the future of television with this stunning 8K TV.",
    "price": 2999.99
}
{
    "name": "CineView OLED TV",
    "category": "Televisions and Home Theater Systems",
    "brand": "CineView",
    "model_number": "CV-OLED55",
    "warranty": "2 years",
    "rating": 4.7,
    "features": [
        "55-inch display",
        "4K resolution",
        "HDR",
        "Smart TV"
    ],
    "description": "Experience true blacks and vibrant colors with this OLED TV.",
    "price": 1499.99
}

第三部分 根据信息生成回答

def get_assistant_response(user_input,all_messages):
    # 分隔符
    delimiter = '''```'''
    system_message = f"""
            您是一家大型电子商店的客户服务助理。\
            请以友好和乐于助人的语气回答问题，并提供详细的答案。\
            请确保向用户提出相关的后续问题。
            """
    # 插入 message
    messages = [
        {'role': 'system', 'content': system_message},
        {'role': 'user', 'content': f"{delimiter}{user_input}{delimiter}"},
        {'role': 'assistant', 'content': f"相关商品信息:\n{product_information}"}
    ]
#     print(messages)
    # 获取 LLM 的回答
    # 通过附加 all_messages 实现多轮对话
    final_response = get_gemma_response(all_messages + messages)
    # 将该轮信息加入到历史信息中
    all_messages = all_messages + messages[1:]
    return final_response

final_response = get_assistant_response('你好，有电视机嘛？',[])
print("第三步：获取助手回答")
print('- '*65)
print(final_response)

第四部分 检查模型是否很好的回答了问题

def check_assistant_reponse(final_response,all_messages,debug = True):
    # 分隔符
    delimiter = '''```'''
    system_message = f"""
            您是一家大型电子商店的客户服务助理。\
            请以友好和乐于助人的语气回答问题，并提供简洁明了的答案。\
            请确保向用户提出相关的后续问题。
        """
    user_message = f"""
    用户信息: {delimiter}{user_input}{delimiter}
    代理回复: {delimiter}{final_response}{delimiter}

    回复是否足够回答问题
    如果足够，回答 Y
    如果不足够，回答 N
    仅回答上述字母即可
    """
    print(user_message)
    messages = [
        {'role': 'system', 'content': system_message},
        {'role': 'user', 'content': user_message}
    ]
    # 要求模型评估回答
    evaluation_response = get_gemma_response(messages)
    print(evaluation_response)
    if debug: print("第四步：模型评估该回答")

    # 第七步：如果评估为 Y，输出回答；如果评估为 N，反馈将由人工修正答案
    # 使用 in 来避免模型可能生成 Yes
    if "Y" in evaluation_response:  
        if debug: print("第五步：模型赞同了该回答.")
        return final_response, all_messages
    else:
        if debug: print("第六步：模型不赞成该回答.")
        neg_str = "很抱歉，我无法提供您所需的信息。我将为您转接到一位人工客服代表以获取进一步帮助。"
        return neg_str, all_messages
        
check_response_result = check_assistant_reponse(final_response,[])

print(check_response_result )

输出结果：

用户信息: ```请告诉我关于 smartx pro phone 和 the fotosnap camera 的信息。另外，请告诉我关于你们的tvs的情况。```
    代理回复: ```...

请问您对哪种电视机感兴趣？```

    回复是否足够回答问题
    如果足够，回答 Y
    如果不足够，回答 N
    仅回答上述字母即可
    
N
第四步：模型评估该回答
第六步：模型不赞成该回答.
('很抱歉，我无法提供您所需的信息。我将为您转接到一位人工客服代表以获取进一步帮助。', [])

这里模型的回答没有通过自己的检查，我们需要注意到，在中文的理解和处理方面，由于模型的特性，我们可能会偶尔遇到不理想的结果。在这种情况下，可以多尝试几次，或者进行深入的研究，以找到更稳定的方法。

第五部分 客服助手全部代码

import json
import requests
from collections import defaultdict


# 商品和目录的数据文件
products_file = 'products.json'
categories_file = 'categories.json'

# 分隔符
delimiter = "####"
# 第二步（抽取商品）系统信息文本
step_2_system_message_content = f"""
您将获得一次客户服务对话。最近的用户查询将使用{delimiter}字符进行分隔。

输出一个Python对象列表，其中每个对象具有以下格式：
'category': <包括以下几个类别：Computers and Laptops、martphones and Accessories、elevisions and Home Theater Systems、elevisions and Home Theater Systems、elevisions and Home Theater Systems、'category': <包括以下几个类别：Computers and Laptops、martphones and Accessories、elevisions and Home Theater Systems、elevisions and Home Theater Systems、elevisions and Home Theater Systems、相机和摄像机>,
或者
'products': <必须是下面的允许产品列表中找到的产品>

类别和产品必须在客户服务查询中找到。
如果提到了产品，它必须与下面的允许产品列表中的正确类别相关联。
如果未找到任何产品或类别，请输出一个空列表。
只列出之前对话的早期部分未提及和讨论的产品和类别。

允许的产品：

Computers and Laptops类别：

TechPro Ultrabook
BlueWave Gaming Laptop
PowerLite Convertible
TechPro Desktop
BlueWave Chromebook

Smartphones and Accessories类别：
SmartX ProPhone
MobiTech PowerCase
SmartX MiniPhone
MobiTech Wireless Charger
SmartX EarBuds

Televisions and Home Theater Systems类别：
CineView 4K TV
SoundMax Home Theater
CineView 8K TV
SoundMax Soundbar
CineView OLED TV

Gaming Consoles and Accessories类别：
GameSphere X
ProGamer Controller
GameSphere Y
ProGamer Racing Wheel
GameSphere VR Headset

Audio Equipment类别：
AudioPhonic Noise-Canceling Headphones
WaveSound Bluetooth Speaker
AudioPhonic True Wireless Earbuds
WaveSound Soundbar
AudioPhonic Turntable

Cameras and Camcorders类别：
FotoSnap DSLR Camera
ActionCam 4K
FotoSnap Mirrorless Camera
ZoomMaster Camcorder
FotoSnap Instant Camera

只输出对象列表，不包含其他内容。
"""

step_2_system_message = {'role':'system', 'content': step_2_system_message_content}    

# 第四步（生成用户回答）的系统信息
step_4_system_message_content = f"""
    你是一家大型电子商店的客户服务助理。
    以友好和乐于助人的语气回答，回答保持简洁明了。
    确保让用户提出相关的后续问题。
"""

step_4_system_message = {'role':'system', 'content': step_4_system_message_content}    

# 第六步（验证模型回答）的系统信息
step_6_system_message_content = f"""
    你是一个助手，评估客户服务代理的回答是否足够回答客户的问题，并验证助手从产品信息中引用的所有事实是否正确。
    对话历史、产品信息、用户和客户服务代理的消息将用```进行分隔。
    请用一个字母回答，不带标点符号：
    Y - 如果输出足够回答问题，并且回答正确使用了产品信息
    N - 输出不足够回答问题，或者没有正确使用产品信息

    只输出一个字母。
"""

step_6_system_message = {'role':'system', 'content': step_6_system_message_content}    


def get_gemma_response(messages,model='llama3'): 
    '''
    prompt: 对应的提示词
    
    Data 参数：
        model：（必需）模型名称
        messages：聊天消息，这可用于保持聊天记忆
        消息对象具有以下字段：

        role：消息的角色，可以是system、user或assistant
        content：消息的内容
        images（可选）：要包含在消息中的图像列表（用于多模态模型，如llava）
        高级参数（可选）：

        format：返回响应的格式。当前唯一接受的值是json
        options：在Modelfile文档中列出的额外模型参数，如temperature
        stream：如果为false，则响应将作为单个响应对象返回，而不是对象流
        keep_alive：控制模型在请求后保持加载到内存中的时间（默认值：5m）
    '''
    # Ollama 本地 API 接口
    url = 'http://localhost:11434/api/chat'
    # 定义请求的数据
    data = {
        "model": model,
        "messages": messages,
        "stream": False
    }
    # 发送 POST 请求
    response = requests.post(url, json=data)
    response_data = response.json()
    return response_data['message']['content']


# 创建目录（如果没有本地目录文件，需要创建一份）
def create_categories():
    categories_dict = {
      'Billing': [
                'Unsubscribe or upgrade',
                'Add a payment method',
                'Explanation for charge',
                'Dispute a charge'],
      'Technical Support':[
                'General troubleshooting',
                'Device compatibility',
                'Software updates'],
      'Account Management':[
                'Password reset',
                'Update personal information',
                'Close account',
                'Account security'],
      'General Inquiry':[
                'Product information',
                'Pricing',
                'Feedback',
                'Speak to a human']
    }

    with open(categories_file, 'w') as file:
        json.dump(categories_dict, file)
        
    return categories_dict

# 获取目录数据
def get_categories():
    with open(categories_file, 'r') as file:
            categories = json.load(file)
    return categories

# 获取商品列表
def get_product_list():
    products = get_products()
    product_list = []
    for product in products.keys():
        product_list.append(product)
    
    return product_list

# 获取商品和目录
def get_products_and_category():
    # 获取所有商品
    products = get_products()
    # 使用 defaultdict初始化一个空字典，用于将商品分组到目录中
    products_by_category = defaultdict(list)
    # 遍历所有商品
    for product_name, product_info in products.items():
        # 获取商品的目录
        category = product_info.get('category')
        # 如果目录存在，则将商品名称添加到该目录的列表中
        if category:
            products_by_category[category].append(product_info.get('name'))
    
    # 返回商品按目录分组的字典
    return dict(products_by_category)

# 从商品数据中获取
def get_products():
    with open(products_file, 'r') as file:
        products = json.load(file)
    return products

# 从用户问题中抽取商品和类别
def find_category_and_product(user_input,products_and_category):
    delimiter = "####"
    system_message = f"""
    您将获得客户服务查询。
    客户服务查询将使用{delimiter}字符分隔。
    输出一个可解析的Python列表，列表每一个元素是一个JSON对象，每个对象具有以下格式：
    'category': <包括以下几个类别：Computers and Laptops，Smartphones and Accessories，Televisions and Home Theater Systems，Gaming Consoles and Accessories，Audio Equipment，Cameras and Camcorders>
    以及
    'products': <必须是下面的允许产品列表中找到的产品列表>

    其中类别和产品必须在客户服务查询中找到。
    如果提到了产品，则必须将其与允许产品列表中的正确类别关联。
    如果未找到任何产品或类别，则输出一个空列表。
    除了列表外，不要输出其他任何信息！

    允许的产品以JSON格式提供。
    每个项的键表示类别。
    每个项的值是该类别中的产品列表。
    允许的产品：{products_and_category}
    
    """
    messages =  [  
    {'role':'system', 'content': system_message},    
    {'role':'user', 'content': f"{delimiter}{user_input}{delimiter}"},  
    ] 
    return get_gemma_response(messages)

# 相比上一个函数，可获取的商品直接在 template 中限定
def find_category_and_product_only(user_input,products_and_category):
    delimiter = "####"
    system_message = f"""
    您将获得客户服务查询。
    客户服务查询将使用{delimiter}字符作为分隔符。
    请仅输出一个可解析的Python列表，列表每一个元素是一个JSON对象，每个对象具有以下格式：
    'category': <包括以下几个类别：Computers and Laptops、Smartphones and Accessories、Televisions and Home Theater Systems、Gaming Consoles and Accessories、Audio Equipment、Cameras and Camcorders>,
    以及
    'products': <必须是下面的允许产品列表中找到的产品列表>

    类别和产品必须在客户服务查询中找到。
    如果提到了某个产品，它必须与允许产品列表中的正确类别关联。
    如果未找到任何产品或类别，则输出一个空列表。
    除了列表外，不要输出其他任何信息！

    允许的产品：

    Computers and Laptops category:
    TechPro Ultrabook
    BlueWave Gaming Laptop
    PowerLite Convertible
    TechPro Desktop
    BlueWave Chromebook

    Smartphones and Accessories category:
    SmartX ProPhone
    MobiTech PowerCase
    SmartX MiniPhone
    MobiTech Wireless Charger
    SmartX EarBuds

    Televisions and Home Theater Systems category:
    CineView 4K TV
    SoundMax Home Theater
    CineView 8K TV
    SoundMax Soundbar
    CineView OLED TV

    Gaming Consoles and Accessories category:
    GameSphere X
    ProGamer Controller
    GameSphere Y
    ProGamer Racing Wheel
    GameSphere VR Headset

    Audio Equipment category:
    AudioPhonic Noise-Canceling Headphones
    WaveSound Bluetooth Speaker
    AudioPhonic True Wireless Earbuds
    WaveSound Soundbar
    AudioPhonic Turntable

    Cameras and Camcorders category:
    FotoSnap DSLR Camera
    ActionCam 4K
    FotoSnap Mirrorless Camera
    ZoomMaster Camcorder
    FotoSnap Instant Camera

    只输出对象列表，不包含其他内容。
    """
    messages =  [  
    {'role':'system', 'content': system_message},    
    {'role':'user', 'content': f"{delimiter}{user_input}{delimiter}"},  
    ] 
    return get_gemma_response(messages)

# 从问题中抽取商品
def get_products_from_query(user_msg):
    products_and_category = get_products_and_category()
    delimiter = "####"
    system_message = f"""
    您将获得客户服务查询。
    客户服务查询将使用{delimiter}字符作为分隔符。
    请仅输出一个可解析的Python列表，列表每一个元素是一个JSON对象，每个对象具有以下格式：
    'category': <包括以下几个类别：Computers and Laptops、Smartphones and Accessories、Televisions and Home Theater Systems、Gaming Consoles and Accessories、Audio Equipment、Cameras and Camcorders>,
    以及
    'products': <必须是下面的允许产品列表中找到的产品列表>

    类别和产品必须在客户服务查询中找到。
    如果提到了某个产品，它必须与允许产品列表中的正确类别关联。
    如果未找到任何产品或类别，则输出一个空列表。
    除了列表外，不要输出其他任何信息！

    允许的产品以JSON格式提供。
    每个项目的键表示类别。
    每个项目的值是该类别中的产品列表。

    以下是允许的产品：{products_and_category}

    """
    
    messages =  [  
    {'role':'system', 'content': system_message},    
    {'role':'user', 'content': f"{delimiter}{user_msg}{delimiter}"},  
    ] 
    category_and_product_response = get_gemma_response(messages)
    
    return category_and_product_response


# 商品信息的搜索
def get_product_by_name(name):
    products = get_products()
    return products.get(name, None)

def get_products_by_category(category):
    products = get_products()
    return [product for product in products.values() if product["category"] == category]

# 获取提及的商品信息
def get_mentioned_product_info(data_list):
    # 初始化一个空列表来保存商品信息
    product_info_l = []

    # 如果输入列表为空，则返回空列表
    if data_list is None:
        return product_info_l

    # 遍历数据列表
    for data in data_list:
        try:
            # 检查数据中是否存在 "products" 字段，如果是则获取商品列表
            if "products" in data:
                products_list = data["products"]
                # 遍历商品列表
                for product_name in products_list:
                    # 获取商品信息，并将其添加到商品信息列表中
                    product = get_product_by_name(product_name)
                    if product:
                        product_info_l.append(product)
                    # 如果商品未找到，则打印错误信息
                    else:
                        print(f"错误: 商品 '{product_name}' 未找到")
            # 检查数据中是否存在 "category" 字段，如果是则获取该类别的商品信息
            elif "category" in data:
                category_name = data["category"]
                # 获取该类别的商品信息
                category_products = get_products_by_category(category_name)
                # 遍历商品信息列表并将其添加到商品信息列表中
                for product in category_products:
                    product_info_l.append(product)
            # 如果数据格式非法，则打印错误信息
            else:
                print("错误：非法的商品格式")
        # 捕获任何异常并打印错误信息
        except Exception as e:
            print(f"Error: {e}")

    # 返回商品信息列表
    return product_info_l


def read_string_to_list(input_string):
    if input_string is None:
        return None

    try:
        input_string = input_string.replace("'", "\"")  # Replace single quotes with double quotes for valid JSON
        data = json.loads(input_string)
        return data
    except json.JSONDecodeError:
        print(input_string)
        print("错误：非法的 Json 格式")
        return None

# 生成输出字符串
def generate_output_string(data_list):
    """
    从数据列表中生成输出字符串。

    参数：
        data_list：包含商品或目录信息的列表。

    返回：
        输出字符串。
    """

    output_string = ""

    # 如果数据列表为空，则返回空字符串。
    if data_list is None:
        return output_string

    # 遍历数据列表。
    for data in data_list:
        try:
            # 检查数据是否包含 "products" 或 "category" 字段。
            if "products" in data:
                # 获取产品列表。
                products_list = data["products"]

                # 遍历产品列表。
                for product_name in products_list:
                    # 获取商品信息。
                    product = get_product_by_name(product_name)

                    # 如果商品存在，则将其转换为 JSON 字符串并添加到输出字符串中。
                    if product:
                        output_string += json.dumps(product, indent=4) + "\n"
                    else:
                        # 如果商品不存在，则打印错误信息。
                        print(f"错误: 商品 '{product_name}' 没有找到")
            elif "category" in data:
                # 获取目录名称。
                category_name = data["category"]

                # 获取该目录下的所有商品。
                category_products = get_products_by_category(category_name)

                # 遍历商品列表。
                for product in category_products:
                    output_string += json.dumps(product, indent=4) + "\n"
            else:
                # 打印错误信息。
                print("错误：非法的商品格式")
        except Exception as e:
            # 打印错误信息。
            print(f"Error: {e}")

    # 返回输出字符串。
    return output_string

# Example usage:
#product_information_for_user_message_1 = generate_output_string(category_and_product_list)
#print(product_information_for_user_message_1)
# 回答用户问题
def answer_user_msg(user_msg,product_info):
    """
    代码参见第五节课
    """
    delimiter = "####"
    system_message = f"""
    您是一家大型电子商店的客户服务助理。\
    请用友好和乐于助人的口吻回答问题，提供简洁明了的答案。\
    确保向用户提出相关的后续问题。
    """
    # user_msg = f"""
    # tell me about the smartx pro phone and the fotosnap camera, the dslr one. Also what tell me about your tvs"""
    messages =  [  
    {'role':'system', 'content': system_message},   
    {'role':'user', 'content': f"{delimiter}{user_msg}{delimiter}"},  
    {'role':'assistant', 'content': f"相关产品信息:\n{product_info}"},   
    ] 
    response = get_gemma_response(messages)
    return response

# 创建并存入商品数据
def create_products():
    # product information
    # fun fact: all these products are fake and were generated by a language model
    products = {
        "TechPro Ultrabook": {
            "name": "TechPro Ultrabook",
            "category": "Computers and Laptops",
            "brand": "TechPro",
            "model_number": "TP-UB100",
            "warranty": "1 year",
            "rating": 4.5,
            "features": ["13.3-inch display", "8GB RAM", "256GB SSD", "Intel Core i5 processor"],
            "description": "A sleek and lightweight ultrabook for everyday use.",
            "price": 799.99
        },
        "BlueWave Gaming Laptop": {
            "name": "BlueWave Gaming Laptop",
            "category": "Computers and Laptops",
            "brand": "BlueWave",
            "model_number": "BW-GL200",
            "warranty": "2 years",
            "rating": 4.7,
            "features": ["15.6-inch display", "16GB RAM", "512GB SSD", "NVIDIA GeForce RTX 3060"],
            "description": "A high-performance gaming laptop for an immersive experience.",
            "price": 1199.99
        },
        "PowerLite Convertible": {
            "name": "PowerLite Convertible",
            "category": "Computers and Laptops",
            "brand": "PowerLite",
            "model_number": "PL-CV300",
            "warranty": "1 year",
            "rating": 4.3,
            "features": ["14-inch touchscreen", "8GB RAM", "256GB SSD", "360-degree hinge"],
            "description": "A versatile convertible laptop with a responsive touchscreen.",
            "price": 699.99
        },
        "TechPro Desktop": {
            "name": "TechPro Desktop",
            "category": "Computers and Laptops",
            "brand": "TechPro",
            "model_number": "TP-DT500",
            "warranty": "1 year",
            "rating": 4.4,
            "features": ["Intel Core i7 processor", "16GB RAM", "1TB HDD", "NVIDIA GeForce GTX 1660"],
            "description": "A powerful desktop computer for work and play.",
            "price": 999.99
        },
        "BlueWave Chromebook": {
            "name": "BlueWave Chromebook",
            "category": "Computers and Laptops",
            "brand": "BlueWave",
            "model_number": "BW-CB100",
            "warranty": "1 year",
            "rating": 4.1,
            "features": ["11.6-inch display", "4GB RAM", "32GB eMMC", "Chrome OS"],
            "description": "A compact and affordable Chromebook for everyday tasks.",
            "price": 249.99
        },
        "SmartX ProPhone": {
            "name": "SmartX ProPhone",
            "category": "Smartphones and Accessories",
            "brand": "SmartX",
            "model_number": "SX-PP10",
            "warranty": "1 year",
            "rating": 4.6,
            "features": ["6.1-inch display", "128GB storage", "12MP dual camera", "5G"],
            "description": "A powerful smartphone with advanced camera features.",
            "price": 899.99
        },
        "MobiTech PowerCase": {
            "name": "MobiTech PowerCase",
            "category": "Smartphones and Accessories",
            "brand": "MobiTech",
            "model_number": "MT-PC20",
            "warranty": "1 year",
            "rating": 4.3,
            "features": ["5000mAh battery", "Wireless charging", "Compatible with SmartX ProPhone"],
            "description": "A protective case with built-in battery for extended usage.",
            "price": 59.99
        },
        "SmartX MiniPhone": {
            "name": "SmartX MiniPhone",
            "category": "Smartphones and Accessories",
            "brand": "SmartX",
            "model_number": "SX-MP5",
            "warranty": "1 year",
            "rating": 4.2,
            "features": ["4.7-inch display", "64GB storage", "8MP camera", "4G"],
            "description": "A compact and affordable smartphone for basic tasks.",
            "price": 399.99
        },
        "MobiTech Wireless Charger": {
            "name": "MobiTech Wireless Charger",
            "category": "Smartphones and Accessories",
            "brand": "MobiTech",
            "model_number": "MT-WC10",
            "warranty": "1 year",
            "rating": 4.5,
            "features": ["10W fast charging", "Qi-compatible", "LED indicator", "Compact design"],
            "description": "A convenient wireless charger for a clutter-free workspace.",
            "price": 29.99
        },
        "SmartX EarBuds": {
            "name": "SmartX EarBuds",
            "category": "Smartphones and Accessories",
            "brand": "SmartX",
            "model_number": "SX-EB20",
            "warranty": "1 year",
            "rating": 4.4,
            "features": ["True wireless", "Bluetooth 5.0", "Touch controls", "24-hour battery life"],
            "description": "Experience true wireless freedom with these comfortable earbuds.",
            "price": 99.99
        },

        "CineView 4K TV": {
            "name": "CineView 4K TV",
            "category": "Televisions and Home Theater Systems",
            "brand": "CineView",
            "model_number": "CV-4K55",
            "warranty": "2 years",
            "rating": 4.8,
            "features": ["55-inch display", "4K resolution", "HDR", "Smart TV"],
            "description": "A stunning 4K TV with vibrant colors and smart features.",
            "price": 599.99
        },
        "SoundMax Home Theater": {
            "name": "SoundMax Home Theater",
            "category": "Televisions and Home Theater Systems",
            "brand": "SoundMax",
            "model_number": "SM-HT100",
            "warranty": "1 year",
            "rating": 4.4,
            "features": ["5.1 channel", "1000W output", "Wireless subwoofer", "Bluetooth"],
            "description": "A powerful home theater system for an immersive audio experience.",
            "price": 399.99
        },
        "CineView 8K TV": {
            "name": "CineView 8K TV",
            "category": "Televisions and Home Theater Systems",
            "brand": "CineView",
            "model_number": "CV-8K65",
            "warranty": "2 years",
            "rating": 4.9,
            "features": ["65-inch display", "8K resolution", "HDR", "Smart TV"],
            "description": "Experience the future of television with this stunning 8K TV.",
            "price": 2999.99
        },
        "SoundMax Soundbar": {
            "name": "SoundMax Soundbar",
            "category": "Televisions and Home Theater Systems",
            "brand": "SoundMax",
            "model_number": "SM-SB50",
            "warranty": "1 year",
            "rating": 4.3,
            "features": ["2.1 channel", "300W output", "Wireless subwoofer", "Bluetooth"],
            "description": "Upgrade your TV's audio with this sleek and powerful soundbar.",
            "price": 199.99
        },
        "CineView OLED TV": {
            "name": "CineView OLED TV",
            "category": "Televisions and Home Theater Systems",
            "brand": "CineView",
            "model_number": "CV-OLED55",
            "warranty": "2 years",
            "rating": 4.7,
            "features": ["55-inch display", "4K resolution", "HDR", "Smart TV"],
            "description": "Experience true blacks and vibrant colors with this OLED TV.",
            "price": 1499.99
        },

        "GameSphere X": {
            "name": "GameSphere X",
            "category": "Gaming Consoles and Accessories",
            "brand": "GameSphere",
            "model_number": "GS-X",
            "warranty": "1 year",
            "rating": 4.9,
            "features": ["4K gaming", "1TB storage", "Backward compatibility", "Online multiplayer"],
            "description": "A next-generation gaming console for the ultimate gaming experience.",
            "price": 499.99
        },
        "ProGamer Controller": {
            "name": "ProGamer Controller",
            "category": "Gaming Consoles and Accessories",
            "brand": "ProGamer",
            "model_number": "PG-C100",
            "warranty": "1 year",
            "rating": 4.2,
            "features": ["Ergonomic design", "Customizable buttons", "Wireless", "Rechargeable battery"],
            "description": "A high-quality gaming controller for precision and comfort.",
            "price": 59.99
        },
        "GameSphere Y": {
            "name": "GameSphere Y",
            "category": "Gaming Consoles and Accessories",
            "brand": "GameSphere",
            "model_number": "GS-Y",
            "warranty": "1 year",
            "rating": 4.8,
            "features": ["4K gaming", "500GB storage", "Backward compatibility", "Online multiplayer"],
            "description": "A compact gaming console with powerful performance.",
            "price": 399.99
        },
        "ProGamer Racing Wheel": {
            "name": "ProGamer Racing Wheel",
            "category": "Gaming Consoles and Accessories",
            "brand": "ProGamer",
            "model_number": "PG-RW200",
            "warranty": "1 year",
            "rating": 4.5,
            "features": ["Force feedback", "Adjustable pedals", "Paddle shifters", "Compatible with GameSphere X"],
            "description": "Enhance your racing games with this realistic racing wheel.",
            "price": 249.99
        },
        "GameSphere VR Headset": {
            "name": "GameSphere VR Headset",
            "category": "Gaming Consoles and Accessories",
            "brand": "GameSphere",
            "model_number": "GS-VR",
            "warranty": "1 year",
            "rating": 4.6,
            "features": ["Immersive VR experience", "Built-in headphones", "Adjustable headband", "Compatible with GameSphere X"],
            "description": "Step into the world of virtual reality with this comfortable VR headset.",
            "price": 299.99
        },

        "AudioPhonic Noise-Canceling Headphones": {
            "name": "AudioPhonic Noise-Canceling Headphones",
            "category": "Audio Equipment",
            "brand": "AudioPhonic",
            "model_number": "AP-NC100",
            "warranty": "1 year",
            "rating": 4.6,
            "features": ["Active noise-canceling", "Bluetooth", "20-hour battery life", "Comfortable fit"],
            "description": "Experience immersive sound with these noise-canceling headphones.",
            "price": 199.99
        },
        "WaveSound Bluetooth Speaker": {
            "name": "WaveSound Bluetooth Speaker",
            "category": "Audio Equipment",
            "brand": "WaveSound",
            "model_number": "WS-BS50",
            "warranty": "1 year",
            "rating": 4.5,
            "features": ["Portable", "10-hour battery life", "Water-resistant", "Built-in microphone"],
            "description": "A compact and versatile Bluetooth speaker for music on the go.",
            "price": 49.99
        },
        "AudioPhonic True Wireless Earbuds": {
            "name": "AudioPhonic True Wireless Earbuds",
            "category": "Audio Equipment",
            "brand": "AudioPhonic",
            "model_number": "AP-TW20",
            "warranty": "1 year",
            "rating": 4.4,
            "features": ["True wireless", "Bluetooth 5.0", "Touch controls", "18-hour battery life"],
            "description": "Enjoy music without wires with these comfortable true wireless earbuds.",
            "price": 79.99
        },
        "WaveSound Soundbar": {
            "name": "WaveSound Soundbar",
            "category": "Audio Equipment",
            "brand": "WaveSound",
            "model_number": "WS-SB40",
            "warranty": "1 year",
            "rating": 4.3,
            "features": ["2.0 channel", "80W output", "Bluetooth", "Wall-mountable"],
            "description": "Upgrade your TV's audio with this slim and powerful soundbar.",
            "price": 99.99
        },
        "AudioPhonic Turntable": {
            "name": "AudioPhonic Turntable",
            "category": "Audio Equipment",
            "brand": "AudioPhonic",
            "model_number": "AP-TT10",
            "warranty": "1 year",
            "rating": 4.2,
            "features": ["3-speed", "Built-in speakers", "Bluetooth", "USB recording"],
            "description": "Rediscover your vinyl collection with this modern turntable.",
            "price": 149.99
        },

        "FotoSnap DSLR Camera": {
            "name": "FotoSnap DSLR Camera",
            "category": "Cameras and Camcorders",
            "brand": "FotoSnap",
            "model_number": "FS-DSLR200",
            "warranty": "1 year",
            "rating": 4.7,
            "features": ["24.2MP sensor", "1080p video", "3-inch LCD", "Interchangeable lenses"],
            "description": "Capture stunning photos and videos with this versatile DSLR camera.",
            "price": 599.99
        },
        "ActionCam 4K": {
            "name": "ActionCam 4K",
            "category": "Cameras and Camcorders",
            "brand": "ActionCam",
            "model_number": "AC-4K",
            "warranty": "1 year",
            "rating": 4.4,
            "features": ["4K video", "Waterproof", "Image stabilization", "Wi-Fi"],
            "description": "Record your adventures with this rugged and compact 4K action camera.",
            "price": 299.99
        },
        "FotoSnap Mirrorless Camera": {
            "name": "FotoSnap Mirrorless Camera",
            "category": "Cameras and Camcorders",
            "brand": "FotoSnap",
            "model_number": "FS-ML100",
            "warranty": "1 year",
            "rating": 4.6,
            "features": ["20.1MP sensor", "4K video", "3-inch touchscreen", "Interchangeable lenses"],
            "description": "A compact and lightweight mirrorless camera with advanced features.",
            "price": 799.99
        },
        "ZoomMaster Camcorder": {
            "name": "ZoomMaster Camcorder",
            "category": "Cameras and Camcorders",
            "brand": "ZoomMaster",
            "model_number": "ZM-CM50",
            "warranty": "1 year",
            "rating": 4.3,
            "features": ["1080p video", "30x optical zoom", "3-inch LCD", "Image stabilization"],
            "description": "Capture life's moments with this easy-to-use camcorder.",
            "price": 249.99
        },
        "FotoSnap Instant Camera": {
            "name": "FotoSnap Instant Camera",
            "category": "Cameras and Camcorders",
            "brand": "FotoSnap",
            "model_number": "FS-IC10",
            "warranty": "1 year",
            "rating": 4.1,
            "features": ["Instant prints", "Built-in flash", "Selfie mirror", "Battery-powered"],
            "description": "Create instant memories with this fun and portable instant camera.",
            "price": 69.99
        }
    }

    products_file = 'products.json'
    with open(products_file, 'w') as file:
        json.dump(products, file)
        
    return products




'''
注意：限于模型对中文理解能力较弱，中文 Prompt 可能会随机出现不成功，可以多次运行；也非常欢迎同学探究更稳定的中文 Prompt
'''
def process_user_message_ch(user_input, all_messages, debug=True):
    """
    对用户信息进行预处理
    
    参数:
    user_input : 用户输入
    all_messages : 历史信息
    debug : 是否开启 DEBUG 模式,默认开启
    """
    # 分隔符
    delimiter = "```"
    
    # 第一步：抽取出商品和对应的目录，类似于之前课程中的方法，做了一个封装
    category_and_product_response = find_category_and_product_only(user_input, get_products_and_category())
    # 将抽取出来的字符串转化为列表
    category_and_product_list = read_string_to_list(category_and_product_response)
    # print(category_and_product_list)

    if debug: print("第一步：抽取出商品列表")

    # 第三步：查找商品对应信息
    product_information = generate_output_string(category_and_product_list)
    if debug: print("第二步：查找抽取出的商品信息")
#     print('商品信息：',product_information)
    # 第四步：根据信息生成回答
    system_message = f"""
        您是一家西瓜电器的客户服务助理。\
        请以友好和乐于助人的语气回答问题，并提供简洁明了的答案。\
        当用户向你咨询时，请友好的告诉用户你所知道的产品信息。\
        引导用户购买，我们的产品。\
        检查你的回答，如果你的回答不是中文简体，请把它翻译为中文简体。\
        请确保向用户提出相关的后续问题。
    """
    # 插入 message
    messages = [
        {'role': 'system', 'content': system_message},
        {'role': 'user', 'content': f"{delimiter}{user_input}{delimiter}"},
        {'role': 'assistant', 'content': f"相关商品信息:\n{product_information}"}
    ]
    # 获取 LLM 的回答
    # 通过附加 all_messages 实现多轮对话
    final_response = get_gemma_response(all_messages + messages)
#     print(messages)
#     print(final_response)
    if debug:print("第三步：生成用户回答")
    # 将该轮信息加入到历史信息中
    all_messages = all_messages + messages[1:]

    # 第四步：模型检查是否很好地回答了用户问题
    user_message = f"""
    用户信息: {delimiter}{user_input}{delimiter}
    代理回复: {delimiter}{final_response}{delimiter}

    回复是否足够回答问题
    如果足够，回答 Y
    如果不足够，回答 N
    仅回答上述字母即可
    """
    # print(final_response)
    messages = [
        {'role': 'system', 'content': system_message},
        {'role': 'user', 'content': user_message}
    ]
    # 要求模型评估回答
    evaluation_response = get_gemma_response(messages)
    # print(evaluation_response)
    if debug: print("第六步：模型评估该回答")

    # 第七步：如果评估为 Y，输出回答；如果评估为 N，反馈将由人工修正答案
    # 使用 in 来避免模型可能生成 Yes
    if "Y" in evaluation_response:  
        if debug: print("第七步：模型赞同了该回答.")
        return final_response, all_messages
    else:
        if debug: print("第七步：模型不赞成该回答.")
        neg_str = "很抱歉，我无法提供您所需的信息。我将为您转接到一位人工客服代表以获取进一步帮助。"
        return neg_str, all_messages

user_input = "请告诉我关于 smartx pro phone 和 the fotosnap camera 的信息。另外，请告诉我关于你们的tvs的情况。"
response,_ = process_user_message_ch(user_input,[],debug=False)
print(response)

输出结果：

####
Customer Service Query: 
####
category: Smartphones and Accessories
products: ["SmartX ProPhone", "MobiTech PowerCase"]

category: Cameras and Camcorders
products: ["FotoSnap DSLR Camera", "ActionCam 4K"]

category: Televisions and Home Theater Systems
products: ["CineView 4K TV", "SoundMax Home Theater"]
####
错误：非法的 Json 格式
1. SmartX Pro Phone:

SmartX Pro Phone 是我们公司最新推出的智能手机产品。它具有高级的照相摄像技术、高速数据处理和智能化功能等特点。这款手机适用于日常生活和工作，能够满足您的多样需求。

2. FotoSnap Camera:

FotoSnap Camera 是我们的新一代相机产品。它拥有超高像素、高感光度和快速拍摄速度等特点。相机可以拍摄高清照片、视频，且具有智能化功能，可以自动调整拍摄参数、修复照相结果等功能。

3. TV:

关于我们公司的电视产品，我可以告诉您，我们提供了一系列的液晶电视、LED电视和OLED电视等多样化的选择。我们的电视具备高清显示、高对比度和智能化功能等特点，可以满足您的家庭娱乐需求。

额外信息：
您是否想了解更多关于 SmartX Pro Phone 和 FotoSnap Camera 的详细信息？或者您也想了解关于我们公司的电视产品有什么优缺点？

请随时提出您的问题，我们将尽快为您解答！

网站公告

今日签到

点亮在社区的每一天
去签到

热门文章

最新发布