跳到内容

如何构建一个聊天机器人#

LlamaIndex 作为您的数据与大型语言模型 (LLM) 之间的桥梁，提供了一个工具包，使您能够围绕您的数据建立一个查询接口，用于各种任务，例如问答和摘要。

在本教程中，我们将逐步指导您使用数据代理 (Data Agent)构建一个上下文增强的聊天机器人。这个由 LLM 提供支持的代理能够智能地执行数据上的任务。最终结果是一个聊天机器人代理，配备了 LlamaIndex 提供的一套强大的数据接口工具，用于回答有关您数据的查询。

注意：本教程基于最初在 SEC 10-K 文件上创建查询接口的工作 - 在此处查看。

背景#

在本指南中，我们将构建一个“10-K 聊天机器人”，它使用 Dropbox 中的 UBER 原始 10-K HTML 文件。用户可以与聊天机器人互动，询问与 10-K 文件相关的问题。

准备工作#

import os
import openai

os.environ["OPENAI_API_KEY"] = "sk-..."
openai.api_key = os.environ["OPENAI_API_KEY"]

import nest_asyncio

nest_asyncio.apply()

摄取数据#

首先，让我们下载 2019-2022 年的原始 10-K 文件。

# NOTE: the code examples assume you're operating within a Jupyter notebook.
# download files
!mkdir data
!wget "https://www.dropbox.com/s/948jr9cfs7fgj99/UBER.zip?dl=1" -O data/UBER.zip
!unzip data/UBER.zip -d data

为了将 HTML 文件解析为格式化文本，我们使用了 Unstructured 库。得益于 LlamaHub，我们可以直接与 Unstructured 集成，将任何文本转换为 LlamaIndex 可以摄取的 Document 格式。

首先安装必要的包

!pip install llama-hub unstructured

然后我们可以使用 UnstructuredReader 将 HTML 文件解析成 Document 对象列表。

from llama_index.readers.file import UnstructuredReader
from pathlib import Path

years = [2022, 2021, 2020, 2019]

loader = UnstructuredReader()
doc_set = {}
all_docs = []
for year in years:
    year_docs = loader.load_data(
        file=Path(f"./data/UBER/UBER_{year}.html"), split_documents=False
    )
    # insert year metadata into each year
    for d in year_docs:
        d.metadata = {"year": year}
    doc_set[year] = year_docs
    all_docs.extend(year_docs)

为每一年设置向量索引#

我们首先为每一年设置一个向量索引。每个向量索引允许我们询问关于特定年份 10-K 文件的问题。

我们构建每个索引并将其保存到磁盘。

# initialize simple vector indices
from llama_index.core import VectorStoreIndex, StorageContext
from llama_index.core import Settings

Settings.chunk_size = 512
index_set = {}
for year in years:
    storage_context = StorageContext.from_defaults()
    cur_index = VectorStoreIndex.from_documents(
        doc_set[year],
        storage_context=storage_context,
    )
    index_set[year] = cur_index
    storage_context.persist(persist_dir=f"./storage/{year}")

从磁盘加载索引，执行以下操作

# Load indices from disk
from llama_index.core import load_index_from_storage

index_set = {}
for year in years:
    storage_context = StorageContext.from_defaults(
        persist_dir=f"./storage/{year}"
    )
    cur_index = load_index_from_storage(
        storage_context,
    )
    index_set[year] = cur_index

设置子问题查询引擎以合成跨越 10-K 文件的答案#

由于我们可以访问四年的文档，我们可能不仅想询问特定年份 10-K 文档的问题，还想询问需要对所有 10-K 文件进行分析的问题。

为解决这个问题，我们可以使用子问题查询引擎 (Sub Question Query Engine)。它将一个查询分解为多个子查询，每个子查询由一个单独的向量索引回答，然后合成结果来回答整体查询。

LlamaIndex 提供了一些围绕索引（和查询引擎）的包装器，以便它们可以被查询引擎和代理使用。首先，我们为每个向量索引定义一个 QueryEngineTool。每个工具都有一个名称和描述；这些是 LLM 代理用来决定选择哪个工具的信息。

from llama_index.core.tools import QueryEngineTool, ToolMetadata

individual_query_engine_tools = [
    QueryEngineTool(
        query_engine=index_set[year].as_query_engine(),
        metadata=ToolMetadata(
            name=f"vector_index_{year}",
            description=f"useful for when you want to answer queries about the {year} SEC 10-K for Uber",
        ),
    )
    for year in years
]

现在我们可以创建子问题查询引擎，它将允许我们合成跨越 10-K 文件的答案。我们传入上面定义的 individual_query_engine_tools，以及用于运行子查询的 llm。

from llama_index.llms.openai import OpenAI
from llama_index.core.query_engine import SubQuestionQueryEngine

query_engine = SubQuestionQueryEngine.from_defaults(
    query_engine_tools=individual_query_engine_tools,
    llm=OpenAI(model="gpt-3.5-turbo"),
)

设置聊天机器人代理#

我们使用 LlamaIndex 数据代理来设置外部聊天机器人代理，该代理可以访问一组工具 (Tools)。具体来说，我们将使用一个 OpenAIAgent，它利用了 OpenAI API 函数调用。我们想使用我们之前为每个索引（对应于给定年份）定义的单独工具，以及我们上面定义的子问题查询引擎的工具。

首先，我们为子问题查询引擎定义一个 QueryEngineTool

query_engine_tool = QueryEngineTool(
    query_engine=query_engine,
    metadata=ToolMetadata(
        name="sub_question_query_engine",
        description="useful for when you want to answer queries that require analyzing multiple SEC 10-K documents for Uber",
    ),
)

然后，我们将上面定义的工具合并成一个工具列表供代理使用

tools = individual_query_engine_tools + [query_engine_tool]

最后，我们调用 OpenAIAgent.from_tools 创建代理，并传入上面定义的工具列表。

from llama_index.agent.openai import OpenAIAgent

agent = OpenAIAgent.from_tools(tools, verbose=True)

测试代理#

现在我们可以使用各种查询来测试代理。

如果我们使用一个简单的“hello”查询来测试它，代理不会使用任何工具。

response = agent.chat("hi, i am bob")
print(str(response))

Hello Bob! How can I assist you today?

如果我们使用关于特定年份 10-K 文件的查询来测试它，代理将使用相关的向量索引工具。

response = agent.chat(
    "What were some of the biggest risk factors in 2020 for Uber?"
)
print(str(response))

=== Calling Function ===
Calling function: vector_index_2020 with args: {
  "input": "biggest risk factors"
}
Got output: The biggest risk factors mentioned in the context are:
1. The adverse impact of the COVID-19 pandemic and actions taken to mitigate it on the business.
2. The potential reclassification of drivers as employees, workers, or quasi-employees instead of independent contractors.
3. Intense competition in the mobility, delivery, and logistics industries, with low-cost alternatives and well-capitalized competitors.
4. The need to lower fares or service fees and offer driver incentives and consumer discounts to remain competitive.
5. Significant losses incurred and the uncertainty of achieving profitability.
6. The risk of not attracting or maintaining a critical mass of platform users.
7. Operational, compliance, and cultural challenges related to the workplace culture and forward-leaning approach.
8. The potential negative impact of international investments and the challenges of conducting business in foreign countries.
9. Risks associated with operational and compliance challenges, localization, laws and regulations, competition, social acceptance, technological compatibility, improper business practices, liability uncertainty, managing international operations, currency fluctuations, cash transactions, tax consequences, and payment fraud.
========================
Some of the biggest risk factors for Uber in 2020 were:

1. The adverse impact of the COVID-19 pandemic and actions taken to mitigate it on the business.
2. The potential reclassification of drivers as employees, workers, or quasi-employees instead of independent contractors.
3. Intense competition in the mobility, delivery, and logistics industries, with low-cost alternatives and well-capitalized competitors.
4. The need to lower fares or service fees and offer driver incentives and consumer discounts to remain competitive.
5. Significant losses incurred and the uncertainty of achieving profitability.
6. The risk of not attracting or maintaining a critical mass of platform users.
7. Operational, compliance, and cultural challenges related to the workplace culture and forward-leaning approach.
8. The potential negative impact of international investments and the challenges of conducting business in foreign countries.
9. Risks associated with operational and compliance challenges, localization, laws and regulations, competition, social acceptance, technological compatibility, improper business practices, liability uncertainty, managing international operations, currency fluctuations, cash transactions, tax consequences, and payment fraud.

These risk factors highlight the challenges and uncertainties that Uber faced in 2020.

最后，如果我们使用查询来比较/对比不同年份的风险因素，代理将使用子问题查询引擎工具。

cross_query_str = "Compare/contrast the risk factors described in the Uber 10-K across years. Give answer in bullet points."

response = agent.chat(cross_query_str)
print(str(response))

=== Calling Function ===
Calling function: sub_question_query_engine with args: {
  "input": "Compare/contrast the risk factors described in the Uber 10-K across years"
}
Generated 4 sub questions.
[vector_index_2022] Q: What are the risk factors described in the 2022 SEC 10-K for Uber?
[vector_index_2021] Q: What are the risk factors described in the 2021 SEC 10-K for Uber?
[vector_index_2020] Q: What are the risk factors described in the 2020 SEC 10-K for Uber?
[vector_index_2019] Q: What are the risk factors described in the 2019 SEC 10-K for Uber?
[vector_index_2021] A: The risk factors described in the 2021 SEC 10-K for Uber include the adverse impact of the COVID-19 pandemic on their business, the potential reclassification of drivers as employees instead of independent contractors, intense competition in the mobility, delivery, and logistics industries, the need to lower fares and offer incentives to remain competitive, significant losses incurred by the company, the importance of attracting and maintaining a critical mass of platform users, and the ongoing legal challenges regarding driver classification.
[vector_index_2020] A: The risk factors described in the 2020 SEC 10-K for Uber include the adverse impact of the COVID-19 pandemic on their business, the potential reclassification of drivers as employees instead of independent contractors, intense competition in the mobility, delivery, and logistics industries, the need to lower fares and offer incentives to remain competitive, significant losses and the uncertainty of achieving profitability, the importance of attracting and retaining a critical mass of drivers and users, and the challenges associated with their workplace culture and operational compliance.
[vector_index_2022] A: The risk factors described in the 2022 SEC 10-K for Uber include the potential adverse effect on their business if drivers were classified as employees instead of independent contractors, the highly competitive nature of the mobility, delivery, and logistics industries, the need to lower fares or service fees to remain competitive in certain markets, the company's history of significant losses and the expectation of increased operating expenses in the future, and the potential impact on their platform if they are unable to attract or maintain a critical mass of drivers, consumers, merchants, shippers, and carriers.
[vector_index_2019] A: The risk factors described in the 2019 SEC 10-K for Uber include the loss of their license to operate in London, the complexity of their business and operating model due to regulatory uncertainties, the potential for additional regulations for their other products in the Other Bets segment, the evolving laws and regulations regarding the development and deployment of autonomous vehicles, and the increasing number of data protection and privacy laws around the world. Additionally, there are legal proceedings, litigation, claims, and government investigations that Uber is involved in, which could impose a burden on management and employees and come with defense costs or unfavorable rulings.
Got output: The risk factors described in the Uber 10-K reports across the years include the potential reclassification of drivers as employees instead of independent contractors, intense competition in the mobility, delivery, and logistics industries, the need to lower fares and offer incentives to remain competitive, significant losses incurred by the company, the importance of attracting and maintaining a critical mass of platform users, and the ongoing legal challenges regarding driver classification. Additionally, there are specific risk factors mentioned in each year's report, such as the adverse impact of the COVID-19 pandemic in 2020 and 2021, the loss of their license to operate in London in 2019, and the evolving laws and regulations regarding autonomous vehicles in 2019. Overall, while there are some similarities in the risk factors mentioned, there are also specific factors that vary across the years.
========================
=== Calling Function ===
Calling function: vector_index_2022 with args: {
  "input": "risk factors"
}
Got output: Some of the risk factors mentioned in the context include the potential adverse effect on the business if drivers were classified as employees instead of independent contractors, the highly competitive nature of the mobility, delivery, and logistics industries, the need to lower fares or service fees to remain competitive, the company's history of significant losses and the expectation of increased operating expenses, the impact of future pandemics or disease outbreaks on the business and financial results, and the potential harm to the business due to economic conditions and their effect on discretionary consumer spending.
========================
=== Calling Function ===
Calling function: vector_index_2021 with args: {
  "input": "risk factors"
}
Got output: The COVID-19 pandemic and the impact of actions to mitigate the pandemic have adversely affected and may continue to adversely affect parts of our business. Our business would be adversely affected if Drivers were classified as employees, workers or quasi-employees instead of independent contractors. The mobility, delivery, and logistics industries are highly competitive, with well-established and low-cost alternatives that have been available for decades, low barriers to entry, low switching costs, and well-capitalized competitors in nearly every major geographic region. To remain competitive in certain markets, we have in the past lowered, and may continue to lower, fares or service fees, and we have in the past offered, and may continue to offer, significant Driver incentives and consumer discounts and promotions. We have incurred significant losses since inception, including in the United States and other major markets. We expect our operating expenses to increase significantly in the foreseeable future, and we may not achieve or maintain profitability. If we are unable to attract or maintain a critical mass of Drivers, consumers, merchants, shippers, and carriers, whether as a result of competition or other factors, our platform will become less appealing to platform users.
========================
=== Calling Function ===
Calling function: vector_index_2020 with args: {
  "input": "risk factors"
}
Got output: The risk factors mentioned in the context include the adverse impact of the COVID-19 pandemic on the business, the potential reclassification of drivers as employees, the highly competitive nature of the mobility, delivery, and logistics industries, the need to lower fares or service fees to remain competitive, the company's history of significant losses and potential future expenses, the importance of attracting and maintaining a critical mass of platform users, and the operational and cultural challenges faced by the company.
========================
=== Calling Function ===
Calling function: vector_index_2019 with args: {
  "input": "risk factors"
}
Got output: The risk factors mentioned in the context include competition with local companies, differing levels of social acceptance, technological compatibility issues, exposure to improper business practices, legal uncertainty, difficulties in managing international operations, fluctuations in currency exchange rates, regulations governing local currencies, tax consequences, financial accounting burdens, difficulties in implementing financial systems, import and export restrictions, political and economic instability, public health concerns, reduced protection for intellectual property rights, limited influence over minority-owned affiliates, and regulatory complexities. These risk factors could adversely affect the international operations, business, financial condition, and operating results of the company.
========================
Here is a comparison of the risk factors described in the Uber 10-K reports across years:

2022 Risk Factors:
- Potential adverse effect if drivers were classified as employees instead of independent contractors.
- Highly competitive nature of the mobility, delivery, and logistics industries.
- Need to lower fares or service fees to remain competitive.
- History of significant losses and expectation of increased operating expenses.
- Impact of future pandemics or disease outbreaks on the business and financial results.
- Potential harm to the business due to economic conditions and their effect on discretionary consumer spending.

2021 Risk Factors:
- Adverse impact of the COVID-19 pandemic and actions to mitigate it on the business.
- Potential reclassification of drivers as employees instead of independent contractors.
- Highly competitive nature of the mobility, delivery, and logistics industries.
- Need to lower fares or service fees and offer incentives to remain competitive.
- History of significant losses and uncertainty of achieving profitability.
- Importance of attracting and maintaining a critical mass of platform users.

2020 Risk Factors:
- Adverse impact of the COVID-19 pandemic on the business.
- Potential reclassification of drivers as employees.
- Highly competitive nature of the mobility, delivery, and logistics industries.
- Need to lower fares or service fees to remain competitive.
- History of significant losses and potential future expenses.
- Importance of attracting and maintaining a critical mass of platform users.
- Operational and cultural challenges faced by the company.

2019 Risk Factors:
- Competition with local companies.
- Differing levels of social acceptance.
- Technological compatibility issues.
- Exposure to improper business practices.
- Legal uncertainty.
- Difficulties in managing international operations.
- Fluctuations in currency exchange rates.
- Regulations governing local currencies.
- Tax consequences.
- Financial accounting burdens.
- Difficulties in implementing financial systems.
- Import and export restrictions.
- Political and economic instability.
- Public health concerns.
- Reduced protection for intellectual property rights.
- Limited influence over minority-owned affiliates.
- Regulatory complexities.

These comparisons highlight both common and unique risk factors that Uber faced in different years.

设置聊天机器人循环#

现在我们已经设置好了聊天机器人，只需要再几个步骤就可以设置一个基本的交互循环来与我们的 SEC 增强型聊天机器人聊天！

agent = OpenAIAgent.from_tools(tools)  # verbose=False by default

while True:
    text_input = input("User: ")
    if text_input == "exit":
        break
    response = agent.chat(text_input)
    print(f"Agent: {response}")

这是循环运行的示例

User:  What were some of the legal proceedings against Uber in 2022?
Agent: In 2022, Uber faced several legal proceedings. Some of the notable ones include:

1. Petition against Proposition 22: A petition was filed in California alleging that Proposition 22, which classifies app-based drivers as independent contractors, is unconstitutional.

2. Lawsuit by Massachusetts Attorney General: The Massachusetts Attorney General filed a lawsuit against Uber, claiming that drivers should be classified as employees and entitled to protections under wage and labor laws.

3. Allegations by New York Attorney General: The New York Attorney General made allegations against Uber regarding the misclassification of drivers and related employment violations.

4. Swiss social security rulings: Swiss social security rulings classified Uber drivers as employees, which could have implications for Uber's operations in Switzerland.

5. Class action lawsuits in Australia: Uber faced class action lawsuits in Australia, with allegations that the company conspired to harm participants in the taxi, hire-car, and limousine industries.

It's important to note that the outcomes of these legal proceedings are uncertain and may vary.

User:

Notebook#

查看我们的相应 Notebook。