查询转换手册¶

用户查询在作为 RAG 查询引擎、Agent 或任何其他管线的一部分执行之前，可以通过多种方式进行转换和分解。

本指南向您展示了转换、分解查询以及查找相关工具集的不同方法。每种技术可能适用于不同的用例！

为了命名方便，我们将底层管线定义为“工具”。以下是不同的查询转换方法

1. 路由：保留查询，但识别该查询适用的相关工具子集。将这些工具作为相关选择输出。
2. 查询重写：保留工具，但以各种不同方式重写查询，以便针对相同的工具执行。
3. 子问题：将查询分解为针对不同工具（通过其元数据标识）的多个子问题。
4. ReAct Agent 工具选择：给定初始查询，识别 1) 要选择的工具，以及 2) 要在该工具上执行的查询。

本指南的目标是向您展示如何将这些查询转换作为模块化组件使用。当然，这些组件都集成到更大的系统中（例如，子问题生成器是我们 SubQuestionQueryEngine 的一部分）——每个组件的指南链接如下。

看看吧，并告诉我们您的想法！

In [ ]

%pip install llama-index-question-gen-openai
%pip install llama-index-llms-openai

%pip install llama-index-question-gen-openai %pip install llama-index-llms-openai

In [ ]

from IPython.display import Markdown, display


# define prompt viewing function
def display_prompt_dict(prompts_dict):
    for k, p in prompts_dict.items():
        text_md = f"**Prompt Key**: {k}<br>" f"**Text:** <br>"
        display(Markdown(text_md))
        print(p.get_template())
        display(Markdown("<br><br>"))

from IPython.display import Markdown, display # 定义提示查看函数 def display_prompt_dict(prompts_dict): for k, p in prompts_dict.items(): text_md = f"**提示键**: {k}
" f"**文本：**
" display(Markdown(text_md)) print(p.get_template()) display(Markdown("

"))

路由¶

在此示例中，我们展示了如何使用查询来选择相关的工具选项集。

我们使用 selector 抽象来选择相关的工具——根据抽象，它可以是单个工具，也可以是多个工具。

我们有四种选择器：(LLM 或函数调用) x (单选 或 多选) 的组合

In [ ]

from llama_index.core.selectors import LLMSingleSelector, LLMMultiSelector
from llama_index.core.selectors import (
    PydanticMultiSelector,
    PydanticSingleSelector,
)

from llama_index.core.selectors import LLMSingleSelector, LLMMultiSelector from llama_index.core.selectors import ( PydanticMultiSelector, PydanticSingleSelector, )

In [ ]

# pydantic selectors feed in pydantic objects to a function calling API
# single selector (pydantic, function calling)
# selector = PydanticSingleSelector.from_defaults()

# multi selector (pydantic, function calling)
# selector = PydanticMultiSelector.from_defaults()

# LLM selectors use text completion endpoints
# single selector (LLM)
# selector = LLMSingleSelector.from_defaults()
# multi selector (LLM)
selector = LLMMultiSelector.from_defaults()

# pydantic 选择器将 pydantic 对象馈送到函数调用 API # 单一选择器 (pydantic, 函数调用) # selector = PydanticSingleSelector.from_defaults() # 多重选择器 (pydantic, 函数调用) # selector = PydanticMultiSelector.from_defaults() # LLM 选择器使用文本完成端点 # 单一选择器 (LLM) # selector = LLMSingleSelector.from_defaults() # 多重选择器 (LLM) selector = LLMMultiSelector.from_defaults()

In [ ]

from llama_index.core.tools import ToolMetadata

tool_choices = [
    ToolMetadata(
        name="covid_nyt",
        description=("This tool contains a NYT news article about COVID-19"),
    ),
    ToolMetadata(
        name="covid_wiki",
        description=("This tool contains the Wikipedia page about COVID-19"),
    ),
    ToolMetadata(
        name="covid_tesla",
        description=("This tool contains the Wikipedia page about apples"),
    ),
]

from llama_index.core.tools import ToolMetadata tool_choices = [ ToolMetadata( name="covid_nyt", description=( "该工具包含一篇关于 COVID-19 的纽约时报新闻文章" ), ), ToolMetadata( name="covid_wiki", description=( "该工具包含关于 COVID-19 的维基百科页面" ), ), ToolMetadata( name="covid_tesla", description=( "该工具包含关于苹果的维基百科页面" ), ), ]

In [ ]

display_prompt_dict(selector.get_prompts())

display_prompt_dict(selector.get_prompts())

提示键: prompt
文本

Some choices are given below. It is provided in a numbered list (1 to {num_choices}), where each item in the list corresponds to a summary.
---------------------
{context_list}
---------------------
Using only the choices above and not prior knowledge, return the top choices (no more than {max_outputs}, but only select what is needed) that are most relevant to the question: '{query_str}'


The output should be ONLY JSON formatted as a JSON instance.

Here is an example:
[
    {{
        choice: 1,
        reason: "<insert reason for choice>"
    }},
    ...
]

In [ ]

selector_result = selector.select(
    tool_choices, query="Tell me more about COVID-19"
)

selector_result = selector.select( tool_choices, query="告诉我更多关于 COVID-19 的信息" )

In [ ]

selector_result.selections

selector_result.selections

Out[ ]

[SingleSelection(index=0, reason='This tool contains a NYT news article about COVID-19'),
 SingleSelection(index=1, reason='This tool contains the Wikipedia page about COVID-19')]

在我们的专用路由器页面了解更多关于路由抽象的信息。

查询重写¶

在本节中，我们向您展示如何将查询重写为多个查询。然后，您可以对检索器执行所有这些查询。

这是高级检索技术中的关键一步。通过查询重写，您可以为 [集成检索] 和 [融合] 生成多个查询，从而获得更高质量的检索结果。

与子问题生成器不同，这只是一个提示调用，独立于工具存在。

查询重写（自定义）¶

这里我们展示了如何使用提示生成多个查询，利用我们的 LLM 和提示抽象。

In [ ]

from llama_index.core import PromptTemplate
from llama_index.llms.openai import OpenAI

query_gen_str = """\
You are a helpful assistant that generates multiple search queries based on a \
single input query. Generate {num_queries} search queries, one on each line, \
related to the following input query:
Query: {query}
Queries:
"""
query_gen_prompt = PromptTemplate(query_gen_str)

llm = OpenAI(model="gpt-3.5-turbo")


def generate_queries(query: str, llm, num_queries: int = 4):
    response = llm.predict(
        query_gen_prompt, num_queries=num_queries, query=query
    )
    # assume LLM proper put each query on a newline
    queries = response.split("\n")
    queries_str = "\n".join(queries)
    print(f"Generated queries:\n{queries_str}")
    return queries

from llama_index.core import PromptTemplate from llama_index.llms.openai import OpenAI query_gen_str = """\ 您是一个有用的助手，根据单个输入查询生成多个搜索查询。请生成与以下输入查询相关的 {num_queries} 个搜索查询，每行一个： 查询：{query} 查询列表： """ query_gen_prompt = PromptTemplate(query_gen_str) llm = OpenAI(model="gpt-3.5-turbo") def generate_queries(query: str, llm, num_queries: int = 4): response = llm.predict( query_gen_prompt, num_queries=num_queries, query=query ) # 假设 LLM 正确地将每个查询放在新行 queries = response.split("\n") queries_str = "\n".join(queries) print(f"生成的查询：\n{queries_str}") return queries

In [ ]

queries = generate_queries("What happened at Interleaf and Viaweb?", llm)

queries = generate_queries("Interleaf 和 Viaweb 发生了什么？", llm)

Generated queries:
1. What were the major events or milestones in the history of Interleaf and Viaweb?
2. Who were the founders and key figures involved in the development of Interleaf and Viaweb?
3. What were the products or services offered by Interleaf and Viaweb?
4. Are there any notable success stories or failures associated with Interleaf and Viaweb?

In [ ]

queries

queries

Out[ ]

['1. What were the major events or milestones in the history of Interleaf and Viaweb?',
 '2. Who were the founders and key figures involved in the development of Interleaf and Viaweb?',
 '3. What were the products or services offered by Interleaf and Viaweb?',
 '4. Are there any notable success stories or failures associated with Interleaf and Viaweb?']

有关使用检索器的端到端实现的更多详细信息，请查看我们关于融合检索器的指南

• 模块指南
• 从零开始构建融合检索器

查询重写（使用 QueryTransform）¶

在本节中，我们向您展示如何使用我们的 QueryTransform 类进行查询转换。

In [ ]

from llama_index.core.indices.query.query_transform import HyDEQueryTransform
from llama_index.llms.openai import OpenAI

from llama_index.core.indices.query.query_transform import HyDEQueryTransform from llama_index.llms.openai import OpenAI

In [ ]

hyde = HyDEQueryTransform(include_original=True)
llm = OpenAI(model="gpt-3.5-turbo")

query_bundle = hyde.run("What is Bel?")

hyde = HyDEQueryTransform(include_original=True) llm = OpenAI(model="gpt-3.5-turbo") query_bundle = hyde.run("什么是 Bel？")

这会生成一个查询捆绑包，其中包含原始查询，以及表示应嵌入的查询的 custom_embedding_strs。

In [ ]

new_query.custom_embedding_strs

new_query.custom_embedding_strs

Out[ ]

['Bel is a term that has multiple meanings and can be interpreted in various ways depending on the context. In ancient Mesopotamian mythology, Bel was a prominent deity and one of the chief gods of the Babylonian pantheon. He was often associated with the sky, storms, and fertility. Bel was considered to be the father of the gods and held great power and authority over the other deities.\n\nIn addition to its mythological significance, Bel is also a title that was used to address rulers and leaders in ancient Babylon. It was a term of respect and reverence, similar to the modern-day title of "king" or "emperor." The title of Bel was bestowed upon those who held significant political and military power, and it symbolized their authority and dominion over their subjects.\n\nFurthermore, Bel is also a common given name in various cultures around the world. It can be found in different forms and variations, such as Belinda, Isabel, or Bella. As a personal name, Bel often carries connotations of beauty, grace, and strength.\n\nIn summary, Bel can refer to a powerful deity in ancient Mesopotamian mythology, a title of respect for rulers and leaders, or a personal name with positive attributes. The meaning of Bel can vary depending on the specific context in which it is used.',
 'What is Bel?']

子问题¶

给定一组工具和一个用户查询，决定 1) 要生成的子问题集，以及 2) 每个子问题应运行的工具。

我们使用依赖于函数调用的 OpenAIQuestionGenerator 和依赖于提示的 LLMQuestionGenerator 来运行一个示例。

In [ ]

from llama_index.core.question_gen import LLMQuestionGenerator
from llama_index.question_gen.openai import OpenAIQuestionGenerator
from llama_index.llms.openai import OpenAI

from llama_index.core.question_gen import LLMQuestionGenerator from llama_index.question_gen.openai import OpenAIQuestionGenerator from llama_index.llms.openai import OpenAI

In [ ]

llm = OpenAI()
question_gen = OpenAIQuestionGenerator.from_defaults(llm=llm)

llm = OpenAI() question_gen = OpenAIQuestionGenerator.from_defaults(llm=llm)

In [ ]

display_prompt_dict(question_gen.get_prompts())

display_prompt_dict(question_gen.get_prompts())

提示键: question_gen_prompt
文本

You are a world class state of the art agent.

You have access to multiple tools, each representing a different data source or API.
Each of the tools has a name and a description, formatted as a JSON dictionary.
The keys of the dictionary are the names of the tools and the values are the descriptions.
Your purpose is to help answer a complex user question by generating a list of sub questions that can be answered by the tools.

These are the guidelines you consider when completing your task:
* Be as specific as possible
* The sub questions should be relevant to the user question
* The sub questions should be answerable by the tools provided
* You can generate multiple sub questions for each tool
* Tools must be specified by their name, not their description
* You don't need to use a tool if you don't think it's relevant

Output the list of sub questions by calling the SubQuestionList function.

## Tools
```json
{tools_str}
```

## User Question
{query_str}

In [ ]

from llama_index.core.tools import ToolMetadata

tool_choices = [
    ToolMetadata(
        name="uber_2021_10k",
        description=(
            "Provides information about Uber financials for year 2021"
        ),
    ),
    ToolMetadata(
        name="lyft_2021_10k",
        description=(
            "Provides information about Lyft financials for year 2021"
        ),
    ),
]

from llama_index.core.tools import ToolMetadata tool_choices = [ ToolMetadata( name="uber_2021_10k", description=( "提供有关 Uber 2021 财年信息" ), ), ToolMetadata( name="lyft_2021_10k", description=( "提供有关 Lyft 2021 财年信息" ), ), ]

In [ ]

from llama_index.core import QueryBundle

query_str = "Compare and contrast Uber and Lyft"
choices = question_gen.generate(tool_choices, QueryBundle(query_str=query_str))

from llama_index.core import QueryBundle query_str = "比较和对比 Uber 和 Lyft" choices = question_gen.generate(tool_choices, QueryBundle(query_str=query_str))

输出是 SubQuestion Pydantic 对象。

In [ ]

choices

choices

Out[ ]

[SubQuestion(sub_question='What are the financials of Uber for the year 2021?', tool_name='uber_2021_10k'),
 SubQuestion(sub_question='What are the financials of Lyft for the year 2021?', tool_name='lyft_2021_10k')]

有关如何将其以更打包的方式插入您的 RAG 管线的详细信息，请查看我们的SubQuestionQueryEngine。

使用 ReAct 提示进行查询转换¶

ReAct 是一个流行的 Agent 框架，这里我们展示了核心 ReAct 提示如何用于转换查询。

我们使用 ReActChatFormatter 获取 LLM 的输入消息集。

In [ ]

from llama_index.core.agent import ReActChatFormatter
from llama_index.core.agent.react.output_parser import ReActOutputParser
from llama_index.core.tools import FunctionTool
from llama_index.core.llms import ChatMessage

from llama_index.core.agent import ReActChatFormatter from llama_index.core.agent.react.output_parser import ReActOutputParser from llama_index.core.tools import FunctionTool from llama_index.core.llms import ChatMessage

In [ ]

def execute_sql(sql: str) -> str:
    """Given a SQL input string, execute it."""
    # NOTE: This is a mock function
    return f"Executed {sql}"


def add(a: int, b: int) -> int:
    """Add two numbers."""
    return a + b


tool1 = FunctionTool.from_defaults(fn=execute_sql)
tool2 = FunctionTool.from_defaults(fn=add)
tools = [tool1, tool2]

def execute_sql(sql: str) -> str: """给定一个 SQL 输入字符串，执行它。""" # 注意：这是一个模拟函数 return f"已执行 {sql}" def add(a: int, b: int) -> int: """将两个数字相加。""" return a + b tool1 = FunctionTool.from_defaults(fn=execute_sql) tool2 = FunctionTool.from_defaults(fn=add) tools = [tool1, tool2]

这里我们获取要传递给 LLM 的输入提示消息。来看看吧！

In [ ]

chat_formatter = ReActChatFormatter()
output_parser = ReActOutputParser()
input_msgs = chat_formatter.format(
    tools,
    [
        ChatMessage(
            content="Can you find the top three rows from the table named `revenue_years`",
            role="user",
        )
    ],
)
input_msgs

chat_formatter = ReActChatFormatter() output_parser = ReActOutputParser() input_msgs = chat_formatter.format( tools, [ ChatMessage( content="能否查找名为 `revenue_years` 的表中前三行", role="user", ) ], ) input_msgs

Out[ ]

[ChatMessage(role=<MessageRole.SYSTEM: 'system'>, content='\nYou are designed to help with a variety of tasks, from answering questions     to providing summaries to other types of analyses.\n\n## Tools\nYou have access to a wide variety of tools. You are responsible for using\nthe tools in any sequence you deem appropriate to complete the task at hand.\nThis may require breaking the task into subtasks and using different tools\nto complete each subtask.\n\nYou have access to the following tools:\n> Tool Name: execute_sql\nTool Description: execute_sql(sql: str) -> str\nGiven a SQL input string, execute it.\nTool Args: {\'title\': \'execute_sql\', \'type\': \'object\', \'properties\': {\'sql\': {\'title\': \'Sql\', \'type\': \'string\'}}, \'required\': [\'sql\']}\n\n> Tool Name: add\nTool Description: add(a: int, b: int) -> int\nAdd two numbers.\nTool Args: {\'title\': \'add\', \'type\': \'object\', \'properties\': {\'a\': {\'title\': \'A\', \'type\': \'integer\'}, \'b\': {\'title\': \'B\', \'type\': \'integer\'}}, \'required\': [\'a\', \'b\']}\n\n\n## Output Format\nTo answer the question, please use the following format.\n\n```\nThought: I need to use a tool to help me answer the question.\nAction: tool name (one of execute_sql, add) if using a tool.\nAction Input: the input to the tool, in a JSON format representing the kwargs (e.g. {"input": "hello world", "num_beams": 5})\n```\n\nPlease ALWAYS start with a Thought.\n\nPlease use a valid JSON format for the Action Input. Do NOT do this {\'input\': \'hello world\', \'num_beams\': 5}.\n\nIf this format is used, the user will respond in the following format:\n\n```\nObservation: tool response\n```\n\nYou should keep repeating the above format until you have enough information\nto answer the question without using any more tools. At that point, you MUST respond\nin the one of the following two formats:\n\n```\nThought: I can answer without using any more tools.\nAnswer: [your answer here]\n```\n\n```\nThought: I cannot answer the question with the provided tools.\nAnswer: Sorry, I cannot answer your query.\n```\n\n## Current Conversation\nBelow is the current conversation consisting of interleaving human and assistant messages.\n\n', additional_kwargs={}),
 ChatMessage(role=<MessageRole.USER: 'user'>, content='Can you find the top three rows from the table named `revenue_years`', additional_kwargs={})]

接下来我们获取模型的输出。

In [ ]

llm = OpenAI(model="gpt-4-1106-preview")

llm = OpenAI(model="gpt-4-1106-preview")

In [ ]

response = llm.chat(input_msgs)

response = llm.chat(input_msgs)

最后，我们使用 ReActOutputParser 将内容解析为结构化输出，并分析 action inputs。

In [ ]

reasoning_step = output_parser.parse(response.message.content)

reasoning_step = output_parser.parse(response.message.content)

In [ ]

reasoning_step.action_input

reasoning_step.action_input

Out[ ]

{'sql': 'SELECT * FROM revenue_years ORDER BY revenue DESC LIMIT 3'}