译者 | 朱先忠
审校 | 重楼
引言
大型语言模型已经展现出令人印象深刻的能力，并且随着每一代新模型的发布，它们仍在稳步改进。例如，聊天机器人和自动摘要器等应用程序可以直接利用LLM的语言能力，因为这些LLM只要求生成文本输出——这也是该类模型的自然设置。此外，大型语言模型还表现出了理解和解决复杂任务的令人印象深刻的能力，但是只要它们的解决方案保持“纸上谈兵”，即纯文本形式，那么它们就需要外部人类用户代表它们行事并报告所提议操作的结果。另一方面，代理系统通过让模型作用于其环境来解决这个问题，通常是通过一组可以执行特定操作的工具。通过这种方式，LLM就可以在与环境交互的同时通过反复试验迭代地找到解决方案。
一个有趣的情况是，LLM代理可以访问的工具本身就是代理，这是多代理系统的核心概念。多代理系统通过将任务分配和委托给专门的模型并将其输出像拼图一样拼凑在一起来解决任务。实现此类系统的一种常见方法是使用管理代理来协调和协调其他代理的工作流程。
值得注意的是，代理系统，尤其是多代理系统，需要强大的LLM作为骨干才能正常运行，因为底层模型需要能够理解各种工具的用途和适用性，并将原始问题分解为每个工具可以解决的子问题。因此，ChatGPT模型或Anthropic公司的Claude等专有模型通常成为代理系统的默认解决方案。幸运的是，开源LLM的性能继续大幅提升，以至于其中一些LLM在某些情况下可以与专有商业模型相媲美。更有趣的是，中等规模的开放型LLM现在可以执行几年前无法想象的复杂任务。
在本文中，我将展示一个可以在消费级电脑上运行的“小型”LLM如何能够为多代理系统提供良好的结果。具体来说，我将提供一个教程，介绍如何使用中国阿里公司开源的Qwen2.5–7B-Instruct模型创建一个多代理RAG系统。你可以在我的项目的GitHub存储库和Colab中找到此项目所有完整的源代码实现。
在深入研究这个系统架构的细节之前，我将首先回顾一些有关LLM代理的基本概念，因为这些概念将有助于更好地理解我们要使用的开发框架。
ReAct框架
ReAct框架，是在论文《ReAct：语言模型中的协同推理和行动》中提出的一种用于构建LLM代理的流行框架。该方法的主要思想是将思维链提示的有效性纳入代理框架。ReAct框架由一组相互交错的推理和行动步骤组成：大型语言模型在发出动作之前被提示提供思维序列。通过这种方式，模型可以创建动态推理轨迹来引导动作并更新高级计划，同时结合来自与环境交互的信息。这样一来，就允许采用迭代和增量方法来解决给定的任务。在实际开发中，ReAct代理的工作流程由思考、行动和观察序列组成：模型在思考步骤中对总体计划和具体工具的使用进行推理，然后在行动步骤中调用相关工具，最后在观察步骤中从环境中接收反馈。
下面给出的是ReAct框架的一个示例。
ReAct、Chain-of-Thought和Act-Only三框架在问答任务中的比较（本图片来自论文《ReAct：语言模型中的协同推理和行动》）。
代码代理
代码代理是一种特殊类型的LLM代理，它能够使用可执行的Python代码与环境进行交互。这种代码代理的实现基于论文《可执行代码操作引出更好的LLM代理》中提出的CodeAct框架。CodeAct与ReAct框架非常相似，不同之处在于每个操作都由可以执行多个操作的任意可执行代码组成。手工开发的工具作为常规Python函数提供给代理，而代理可以在代码中调用这些函数。
与使用JSON或其他文本格式执行操作的更传统的代理相比，代码代理具有一组独特的优势：
- 它们可以利用现有软件包与手工开发的任务特定型工具相结合。
- 它们可以使用出现错误后返回的错误消息自行调试生成的代码。
- LLM熟悉编写代码，因为代码通常广泛存在于它们的预训练数据中，使其成为编写操作的更自然的格式。
- 代码自然允许存储中间结果并在单个操作中组合多个操作，而JSON或其他文本格式可能需要多个操作才能完成相同的操作。
出于这些原因，与使用JSON或其他文本格式执行操作的代理相比，代码代理可以提供更好的性能和更快的执行速度。
代码代理与使用JSON或文本作为操作的代理之间的比较（图片来自论文《可执行代码操作引出更好的LLM代理》）。
下面是原始论文中的一个具体示例，展示了代码代理如何需要更少的操作来解决某些任务。
代码代理与使用JSON/文本操作格式的代理比较：代码代理可以在一个操作中执行多个操作（图片来自论文《可执行代码操作引出更好的LLM代理》）。
Hugging Face转换器库提供了有用的模块来构建代理，特别是代码代理。Hugging Face转换器代理框架专注于清晰度和模块化作为核心设计原则。这些在构建代理系统时尤为重要：工作流程的复杂性使得控制架构的所有互连部分至关重要。这些设计选择使Hugging Face代理成为构建自定义和灵活代理系统的绝佳工具。当使用开源模型为代理引擎提供支持时，Hugging Face代理框架具有进一步的优势，即可以轻松访问Hugging Face生态系统中存在的模型和实用程序。
Hugging Face代码代理还解决了不安全的代码执行问题。事实上，让LLM不受约束地生成代码可能会带来严重风险，因为它可能会执行不良操作。例如，幻觉可能会导致代理删除重要文件。为了减轻这种风险，Hugging Face代码代理实现使用自下而上的方法来保护代码执行：代码解释器只能执行明确授权的操作。这与通常的自上而下的范式形成对比，后者从功能齐全的Python解释器开始，然后禁止可能有危险的操作。Hugging Face实现包括可执行的安全授权函数列表，并提供可导入的安全模块列表。除非用户预先授权；否则，任何其他内容都无法执行。你可以在Hugging Face公司的博客文章中阅读有关Hugging Face（代码）代理的更多信息：
代理RAG
检索增强生成已成为涉及大型语言模型的信息检索任务的事实标准。这种技术可以帮助保持LLM信息的最新状态，提供对特定信息的访问，并减少幻觉。此外，它还可以通过返回LLM模型用于生成答案的信息源来增强人类的可解释性和监督性。通常的RAG工作流程，包括基于与用户查询的语义相似性的检索过程以及使用检索到的信息对模型的上下文增强，不足以解决某些特定任务。一些不适合传统RAG的情况包括需要与信息源交互的任务、需要回答多条信息的查询，以及需要非平凡操作才能与源中包含的实际信息相联系的复杂查询。
传统RAG系统的一个具体挑战性示例是多跳问答转换器（MHQA）。它涉及提取和组合多条信息，可能需要对提取的信息和仍然缺失的信息进行多次迭代推理。例如，如果向模型提出“桦木胶合板是否漂浮在乙醇中？”的问题，即使用于RAG的来源包含有关这两种材料密度的信息，但是如果这两条信息没有直接的联系，那么标准RAG框架也可能会失败。
增强RAG以避免上述缺点的一种流行方法是使用代理系统。LLM转换器代理可以将原始查询分解为一系列子查询，然后使用语义搜索作为工具来检索这些生成的子查询的段落，随着收集到更多信息而更改和调整其计划。它可以自主决定是否收集了足够的信息来回答每个查询，或者是否应该继续搜索。代理RAG框架可以通过将其扩展到多代理系统来进一步增强，其中每个代理都有自己定义的任务和职责。例如，这允许将高级任务规划与文档源的交互分开。在下一节中，我将描述这种系统的实际实现。
带有代码代理的多代理RAG
在本节中，我将讨论我用于实现基于遵循ReAct框架的代码代理的多代理RAG系统的一般架构选择。你可以在以下GitHub存储库中的完整代码实现中找到其余详细信息。
多代理系统的目标是通过在维基百科上搜索必要的信息来回答问题。它由3个代理组成：
- 管理代理，其工作是将任务分解为子任务并使用其输出提供最终答案。
- 维基百科搜索代理，用于在维基百科上查找相关页面并组合从中提取的信息。
- 页面搜索代理，用于从提供的维基百科页面中检索和汇总与给定查询相关的信息。
这三个代理以分层方式组织：每个代理都可以使用层次结构中紧邻下方的代理作为工具。具体来说，管理代理可以调用维基百科搜索代理来查找有关查询的信息，而查询又可以使用页面搜索代理从维基百科页面中提取特定信息。
下面是架构图，指定每个代理可以调用哪些手工制作的工具（包括包装其他代理的工具）。请注意，由于代码代理使用代码执行来执行操作，因此这些实际上并不是它们可以使用的唯一工具，因为任何本机Python操作和函数（只要获得授权）也可以使用。
架构图显示代理和手工制作的工具（图片由作者本人提供）。
接下来，让我们深入了解架构中涉及的代理的工作原理。
管理代理
管理代理是顶级代理，它接收用户的问题并负责返回答案。它可以使用维基百科搜索代理作为工具，通过查询提示它并接收搜索的最终结果。其目的是通过将用户问题分成一系列子查询并汇总搜索结果，从维基百科收集必要的信息。
以下是此代理使用的系统提示，它基于默认的Hugging Face默认提示模板构建。请注意，提示中提供的示例遵循为代理提供支持的模型的聊天模板，在本例中我们使用Qwen2.5-7B-Instruct。
【译者注】因项目分析需要，本文中多次给出如下英文形式的系统提示。但是，因为这些内容大多是重复性的，所以我仅给出一处提示的中文翻译——后面不再重译。敬请谅解！
You are an expert assistant who can find answer on the internet using code blobs and tools. To do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.（你是一位专家助理，可以使用代码块和工具在互联网上找到答案。为此，你被授予了访问一系列工具的权限：这些工具基本上是可以用代码调用的Python函数。）
You will be given the task of answering a user question and you should answer it by retrieving the necessary information from Wikipedia. Use and trust only the information you retrieved, don't make up false facts.（你将被赋予回答用户问题的任务，并且你应该通过从维基百科检索必要的信息来回答。仅使用和信任你检索到的信息，不要编造虚假事实。）
To help you, you have been given access to a search agent you can use as a tool. You can use the search agent to find information on Wikipedia. Break down the task into smaller sub-tasks and use the search agent to find the necessary information for each sub-task.（为了帮助你，你已获得一个可用作工具的搜索代理的访问权限。你可以使用搜索代理在Wikipedia上查找信息。将任务分解为较小的子任务，并使用搜索代理查找每个子任务所需的信息。）
To solve the task, you must plan forward to proceed in a series of steps, in a cycle of 'Thought:', 'Code:', and 'Observation:' sequences.（为了解决这个任务，你必须提前计划，按照“思考：”、“代码：”和“观察：”序列的循环进行一系列步骤。）
At each step, in the 'Thought:' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.（在“思考：”序列的每个步骤中，你应该首先解释解决任务的理由和想要使用的工具。）
Then in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_action>' sequence.（然后在“代码:”序列中，你应该用简单的Python编写代码。代码序列必须以“<end_action>”序列结尾。）
During each intermediate step, you can use 'print()' to save whatever important information you will then need. These print outputs will be provided back to you by the user in the 'Observation:' field, which will be available as input for the next steps. Always print the output of tools, don't process it or try to extract information before inspecting it.（在每个中间步骤中，你可以使用“print()”保存你随后需要的任何重要信息。这些打印输出将由用户在“观察：”字段中返回给你，这些输出将作为后续步骤的输入。始终打印工具的输出，不要对其进行处理或在检查之前尝试提取信息。）
If an error rise while executing the code, it will be shown in the 'Observation:' field. In that case, fix the code and try again.（如果执行代码时出现错误，它将显示在“观察：”字段中。在这种情况下，请修复代码并重试。）
In the end you have to return a final answer using the `final_answer` tool.（最后，你必须使用“final_answer”工具返回最终答案。）
Here are a few notional examples:（以下是一些概念性的例子：）
---
<|im_start|>user
Task: When was the capital of Italy founded?<|im_end|>
<|im_start|>assistant
Thought: Let's break up the task: I first need to find the capital of Italy and then look at its foundation date. I will use the tool `wikipedia_search_agent` to get the capital of Italy. Code:
```py
result = wikipedia_search_agent("Italy capital")
print("Capital of Italy:", result)
```<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 0] -> Observation:
Capital of Italy:According to the information extracted from the Wikipedia page 'Rome', the capital of Italy is Rome.<|im_end|>
<|im_start|>assistant
Thought: Now that I know that the capital of Italy is Rome, I can use the `wikipedia_search_agent` tool to look for its foundation date.
Code:
```py
result = wikipedia_search_agent("Rome foundation date")
print("Rome foundation:", result)
```<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 1] -> Observation:
Rome foundation: According to the information from the Wikipedia page 'Natale di Roma', the traditional foundation date of Rome is April 21, 753 BC.<|im_end|>
<|im_start|>assistant
Thought: Now that I have retrieved the relevant information, I can use the `final_answer` tool to return the answer.
Code:
```py
final_answer("According to the legend Rome was founded on 21 April 753 BCE, but archaeological evidence dates back its development during the Bronze Age.")
```<end_action><|im_end|>
---
<|im_start|>user
Task: "What's the difference in population between Shanghai and New York?"<|im_end|>
<|im_start|>assistant
Thought: I need to get the populations for both cities and compare them: I will use the tool `search_agent` to get the population of both cities.
Code:
```py
population_guangzhou_info = wikipedia_search_agent("New York City population")
population_shanghai_info = wikipedia_search_agent("Shanghai population")
print("Population Guangzhou:", population_guangzhou)
print("Population Shanghai:", population_shanghai)
```<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 0] -> Observation:
Population Guangzhou: The population of New York City is approximately 8,258,035 as of 2023.
Population Shanghai: According to the information extracted from the Wikipedia page 'Shanghai', the population of the city proper is around 24.87 million inhabitants in 2023.<|im_end|>
<|im_start|>assistant
Thought: Now I know both the population of Shanghai (24.87 million) and of New York City (8.25 million), I will calculate the difference and return the result.
Code:
```py
population_difference = 24.87*1e6 - 8.25*1e6
answer=f"The difference in population between Shanghai and New York is {population_difference} inhabitants."
final_answer(answer)
```<end_action><|im_end|>
---
On top of performing computations in the Python code snippets that you create, you have access to those tools (and no other tool):（除了在你创建的Python代码片段中执行计算之外，你还可以访问这些工具（而不能使用其他工具）：）
<<tool_descriptions>>
<<managed_agents_descriptions>>
You can use imports in your code, but exclusively from the following list of modules: <<authorized_imports>>. Do not try to import other modules or else you will get an error.
Now start and solve the task!（你可以在代码中使用导入，但只能从以下模块列表中使用：<<authorized_imports>>。请勿尝试导入其他模块，否则会出错。
现在开始解决任务！）维基百科搜索代理
此代理负责向管理代理提交报告，它接收来自管理代理的查询，并负责返回从维基百科检索到的信息。它可以访问两个工具：
- 维基百科搜索工具，使用维基百科包中的内置搜索功能。它接收查询作为输入，并返回维基百科页面及其摘要的列表。
- 页面搜索代理，从特定维基百科页面检索有关查询的信息。
此代理收集信息以回答查询，将其划分为进一步的子查询，并在需要时组合来自多个页面的信息。这是通过使用维基百科包的搜索工具来识别可能包含回答查询所需信息的潜在页面来实现的：代理可以使用报告的页面摘要，也可以调用页面搜索代理从特定页面中提取更多信息。在收集到足够的数据后，它会将答案返回给管理代理。
系统提示再次对Hugging Face默认提示进行了轻微修改，其中包含一些遵循模型聊天模板的特定示例。
You are an expert assistant that retrieves information from Wikipedia using code blobs and tools. To do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.
You will be given a general query, your task will be of retrieving and summarising information that is relevant to the query from multiple passages retrieved from the given Wikipedia page. Use and trust only the information you retrieved, don't make up false facts. Try to summarize the information in a few sentences.
To solve the task, you must plan forward to proceed in a series of steps, in a cycle of 'Thought:', 'Code:', and 'Observation:' sequences.
At each step, in the 'Thought:' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.
Then in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_action>' sequence.
During each intermediate step, you can use 'print()' to save whatever important information you will then need. These print outputs will be provided back to you by the user in the 'Observation:' field, which will be available as input for the next steps. Always print the output of tools, don't process it or try to extract information before inspecting it.
If an error rise while executing the code, it will be shown in the 'Observation:' field. In that case, fix the code and try again.
In the end you have to return a final answer using the `final_answer` tool.
Here are a few notional examples:
---
<|im_start|>user
Task: Retrieve information about the query:"What's the capital of France?" from the Wikipedia page "France".<|im_end|>
<|im_start|>assistant
Thought: I need to find the capital of France. I will use the tool `retrieve_passages` to get the capital of France from the Wikipedia page.
Code:
```py
result = retrieve_passages("France capital")
print("Capital of France:", result)
```<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 0] -> Observation:
Retrieved passages for query "France capital":
Passage 0: ... population of nearly 68.4 million as of January 2024. France is a semi-presidential republic with its capital in Paris, the ...
Passage 1: ... France, officially the French Republic, is a country located primarily in Western Europe. Its overseas regions and territories ...
Passage 2: ... The vast majority of France's territory and population is situated in Western Europe and is called Metropolitan France. It is ...
Passage 3: ... France is a highly urbanised country, with its largest cities (in terms of metropolitan area population in 2021) being Paris ...
Passage 4: ... === Government ===\nFrance.fr – official French tourism site (in English)...<|im_end|>
<|im_start|>assistant
Thought: Now that I know that the capital of France is Paris, I can use the `final_answer` tool to return the answer.
Code:
```py
final_answer("The capital of France is Paris.")
```<end_action><|im_end|>
---
<|im_start|>user
Task: Retrieve information about the query:"Tallest mountain in the World" from the Wikipedia page "List of highest mountains on Earth"<|im_end|>
<|im_start|>assistant
Thought: I need to find the tallest mountain in the world. I will use the tool `retrieve_passages` to look for data on the Wikipedia page.
Code:
```py
result = retrieve_passages("highest mountain")
print(result)
```<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 1] -> Observation:
Retrieved passages for query "highest mountain":
Passage 0: ... above sea level) is the world's tallest mountain and volcano, rising about 10,203 m (33,474 ft) from the Pacific Ocean floor. ...
Passage 1: ... As of December 2018, the highest peaks on four of the mountains—Gangkhar Puensum, Labuche Kang III, Karjiang, and Tongshanjiabu, all located in Bhutan or China—have not been ascended. ...
Passage 2: ... The highest mountains above sea level are generally not the highest above the surrounding terrain. ...
Passage 3: ... The highest mountain outside of Asia is Aconcagua (6,961 m or 22,838 ft), the 189th highest in the world. ...
Passage 4: ... the southern summit of Peru's tallest mountain, Huascarán, is another contender. Both have elevations above sea level more than 2 km (1.2 mi) less than that of Everest....
<|im_end|>
<|im_start|>assistant
Thought: The results don't clearly specify a clear result for the world's tallest mountain, I will use the tool `web_results` with a different query.
Code:
```py
result = retrieve_passages("world's tallest mountain")
print(result)
```<end_action><|im_end|>
<|im_start|>user
Passages retrieved from page List of highest mountains on Earth:
Passage 0: ... The highest mountain outside of Asia is Aconcagua (6,961 m or 22,838 ft), the 189th highest in the world....
Passage 1: ... above sea level) is the world's tallest mountain and volcano, rising about 10,203 m (33,474 ft) from the Pacific Ocean floor. ...
Passage 2: ... The bases of mountain islands are below sea level, and given this consideration Mauna Kea (4,207 m (13,802 ft) above sea level) is the world's tallest mountain and volcano, rising about 10,203 m (33,474 ft) from the Pacific Ocean floor. ...
Passage 3: ... the southern summit of Peru's tallest mountain, Huascarán, is another contender. Both have elevations above sea level more than 2 km (1.2 mi) less than that of Everest. ...
Passage 4: ... The highest mountains are also not generally the most voluminous. Mauna Loa (4,169 m or 13,678 ft) is the largest mountain on Earth in terms of base area (about 5,200 km2 or 2,000 sq mi) and volume (about 42,000 km3 or 10,000 cu mi)...<|im_end|>
<|im_start|>assistant
Thought: I have found that Mauna Kea is the world's tallest mountain rising about 10,203 m (33,474 ft) from the Pacific Ocean floor. I can use the `final_answer` tool to return the relevant information.
Code:
```py
final_answer("Mauna Kea is the world's tallest mountain, rising about 10,203 m (33,474 ft) from the Pacific Ocean floor.")
```<end_action><|im_end|>
___
On top of performing computations in the Python code snippets that you create, you have access to those tools (and no other tool):
<<tool_descriptions>>
<<managed_agents_descriptions>>
You can use imports in your code, but only from the following list of modules: <<authorized_imports>>. Do not try to import other modules or else you will get an error.
Now start and solve the task!页面搜索代理
此代理的任务是向维基百科搜索代理提交报告，后者为其提供查询和维基百科页面的标题，并负责从该页面检索相关信息以回答查询。这本质上是一个单代理RAG系统。为了执行任务，此代理生成自定义查询并使用语义搜索工具检索与其更相似的段落。语义搜索工具遵循一个简单的实现，将页面内容分成块并使用LangChain提供的FAISS向量数据库嵌入它们。
以下是系统提示，仍然基于Hugging Face默认提供的提示构建而成：
You are an expert assistant that finds answers to questions by consulting Wikipedia, using code blobs and tools. To do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.
You will be given a general query, your task will be of finding an answer to the query using the information you retrieve from Wikipedia. Use and trust only the information you retrieved, don't make up false facts. Cite the page where you found the information.
You can search for pages and their summaries from Wikipedia using the `search_wikipedia` tool and look for specific passages from a page using the `search_info` tool. You should decide how to use these tools to find an appropriate answer:some queries can be answered by looking at one page summary, others can require looking at specific passages from multiple pages.
To solve the task, you must plan forward to proceed in a series of steps, in a cycle of 'Thought:', 'Code:', and 'Observation:' sequences.
At each step, in the 'Thought:' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.
Then in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_action>' sequence.
During each intermediate step, you can use 'print()' to save whatever important information you will then need. These print outputs will be provided back to you by the user in the 'Observation:' field, which will be available as input for the next steps. Always print the output of tools, don't process it or try to extract information before inspecting it.
If an error rise while executing the code, it will be shown in the 'Observation:' field. In that case, fix the code and try again.
In the end you have to return a final answer using the `final_answer` tool.
Here are a few notional examples:
---
<|im_start|>user
Task: When was the ancient philosopher Seneca born?<|im_end|>
<|im_start|>assistant
Thought: I will use the tool `search_wikipedia` to search for Seneca's birth on Wikipedia. I will specify I am looking for the philosopher for disambiguation.
Code:
```py
result = search_wikipedia("Seneca philosopher birth")
print("result)
```<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 0] -> Observation:
Pages found for query 'Seneca philosopher birth':
Page: Seneca the Younger
Summary: Lucius Annaeus Seneca the Younger ( SEN-ik-ə; c.4 BC – AD 65), usually known mononymously as Seneca, was a Stoic philosopher of Ancient Rome, a statesman, dramatist, and in one work, satirist, from the post-Augustan age of Latin literature.
Seneca was born in Colonia Patricia Corduba in Hispania, a
Page: Phaedra (Seneca)
Summary: Phaedra is a Roman tragedy written by philosopher and dramatist Lucius Annaeus Seneca before 54 A.D. Its 1,280 lines of verse tell the story of Phaedra, wife of King Theseus of Athens and her consuming lust for her stepson Hippolytus. Based on Greek mythology and the tragedy Hippolytus by Euripides,
Page: Seneca the Elder
Summary: Lucius Annaeus Seneca the Elder ( SEN-ik-ə; c.54 BC – c. AD 39), also known as Seneca the Rhetorician, was a Roman writer, born of a wealthy equestrian family of Corduba, Hispania. He wrote a collection of reminiscences about the Roman schools of rhetoric, six books of which are extant in a more or
Page: AD 1
Summary: AD 1 (I) or 1 CE was a common year starting on Saturday or Sunday, a common year starting on Saturday by the proleptic Julian calendar, and a common year starting on Monday by the proleptic Gregorian calendar. It is the epoch year for the Anno Domini (AD) Christian calendar era, and the 1st year of
Page: Seneca Falls Convention
Summary: The Seneca Falls Convention was the first women's rights convention. It advertised itself as "a convention to discuss the social, civil, and religious condition and rights of woman". Held in the Wesleyan Chapel of the town of Seneca Falls, New York, it spanned two days over July 19–20, 1848. Attrac
<|im_start|>assistant
Thought: From the summary of the page "", I can see that Seneca was born in . I can use the `final_answer` tool to return the answer.
Code:
```py
final_answer("According to the Wikipedia page 'Seneca the Younger', Seneca was born in 4 BC.")
```<end_action><|im_end|>
---
<|im_start|>user
Task: Who was Charlemagne predecessor?<|im_end|>
<|im_start|>assistant
Thought: I will use the tool `search_wikipedia` to search for Charlemagne reign duration.
Code:
```py
result = search_wikipedia("Charlemagne predecessor")
print(result)
```<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 0] -> Observation:
Pages found for query 'Charlemagne predecessor':
Page: Charlemagne
Summary: Charlemagne ( SHAR-lə-mayn; 2 April 748 – 28 January 814) was King of the Franks from 768, King of the Lombards from 774, and Emperor of what is now known as the Carolingian Empire from 800, holding these titles until his death in 814. He united most of Western and Central Europe, and was the first
Page: Pope Leo III
Summary: Pope Leo III (Latin: Leo III; died 12 June 816) was bishop of Rome and ruler of the Papal States from 26 December 795 to his death. Protected by Charlemagne from the supporters of his predecessor, Adrian I, Leo subsequently strengthened Charlemagne's position by crowning him emperor. The coronation
Page: Throne of Charlemagne
Summary: The Throne of Charlemagne (German: Karlsthron or Aachener Königsthron, "Royal Throne of Aachen") is a throne erected in the 790s by Charlemagne, as one of the fittings of his palatine chapel in Aachen (today's Aachen Cathedral) and placed in the Octagon of the church. Until 1531, it served as the co
Page: Louis the Pious
Summary: Louis the Pious (Latin: Hludowicus Pius; French: Louis le Pieux; German: Ludwig der Fromme; 16 April 778 – 20 June 840), also called the Fair and the Debonaire, was King of the Franks and co-emperor with his father, Charlemagne, from 813. He was also King of Aquitaine from 781. As the only surviving
Page: Holy Roman Emperor
Summary: The Holy Roman Emperor, originally and officially the Emperor of the Romans (Latin: Imperator Romanorum; German: Kaiser der Römer) during the Middle Ages, and also known as the Romano-German Emperor since the early modern period (Latin: Imperator Germanorum; German: Römisch-deutscher Kaiser, lit. 'R
<|im_end|>
<|im_start|>assistant
Thought: The results don't contain explicit information about Charlemagne predecessor, I will search for more information on the page 'Charlemagne' using the 'search_info' tool.
Code:
```py
result = search_info("Charlemagne predecessor", "Charlemagne")
print(result)
```<end_action><|im_end|>
<|im_start|>user
[OUTPUT OF STEP 1] -> Observation:
Information retrieved from the page 'Charlemagne' for the query 'Charlemagne predecessor':
Charlemagne's predecessor was Pepin the Short.
<|im_end|>
<|im_start|>assistant
Thought: I have found that, according to the Wikipedia page 'Charlemagne', Pepin the Short was Charlemagne predecessor. I will return the results using the `final_answer` tool.
Code:
```py
final_answer("According to the information extracted from the Wikipedia page 'Charlemagne', his predecessor was Pepin the Short.")
```<end_action><|im_end|>
___
On top of performing computations in the Python code snippets that you create, you have access to those tools (and no other tool):
<<tool_descriptions>>
<<managed_agents_descriptions>>
You can use imports in your code, but only from the following list of modules: <<authorized_imports>>. Do not try to import other modules or else you will get an error.
Now start and solve the task!实施选择
在本小节中，我将概述我的方案与使用Hugging Face代理直接实施架构的主要区别。这些是经过有限的反复试验后获得效果良好的解决方案的结果。我没有进行过广泛的测试和切除，因此它们可能不是最佳选择。
- 提示：如前几节所述，每个代理都有自己的专用系统提示，与Hugging Face代码代理提供的默认提示不同。我观察到，也许是由于所用模型的大小有限，通用标准系统提示并没有给出良好的结果。该模型似乎最适合使用能够密切反映其被要求执行的任务的系统提示，包括重要用例的定制示例。由于我使用聊天模型的目的是改进指令遵循行为，因此提供的示例遵循模型的聊天模板，以尽可能接近运行期间遇到的格式。
- 总结历史：较长的执行历史对执行速度和任务性能都有不利影响。后者可能是由于模型从长上下文中检索必要信息的能力有限。此外，极长的执行历史记录可能会超过引擎模型的最大上下文长度。为了缓解这些问题并加快执行速度，我选择不显示先前的“思想-行动-观察”步骤的所有细节，而是仅收集先前的观察结果。更具体地说，在每个步骤中，模型仅接收以下聊天历史记录：系统消息、包含任务的第一条消息、其最后一个操作以及先前观察的所有历史记录。此外，只有当执行错误发生在最后一步时，它们才会出现在观察历史中，先前已经解决的错误将被丢弃。
- 工具与托管代理：Hugging Face代理实现对托管代理具有本机支持，但将它们包装为工具可以更好地控制提示并实现更简化的实现。特别是，Hugging Face实现为托管代理及其管理器添加了特定提示。虽然我没有看到解决给定任务的能力存在实质性差异，但我更喜欢第二种方法，因为它对于所呈现的架构来说更灵活、更精简，并且更容易控制代理的行为。这也有助于减少提示长度，这对于加快计算速度很有用。
- 限制页面搜索代理的最大试验次数：有时页面搜索代理会继续在给定页面上寻找不包含它的信息。减少最大试验次数可以缓解这个问题：达到该次数后，代理执行将停止，工具将返回代码执行的最后一次观察结果。
- 将工具响应更改为用户消息：这更像是一个技术性的、特定于实现的方面。由于Qwen2.5–7B-Instruct的聊天模板仅支持系统、用户和助手，因此观察结果将作为用户消息返回。
示例展示
在本节中，我将收集使用前面所述架构生成的一些示例。我还将提供参与任务的所有代理的详细执行情况，以展示它们在某些真实案例中的交互方式。你可以使用我提供的谷歌Colab笔记本来探索更多有关示例。案例中所有提取的段落均取自执行中指定的维基百科页面。
简单举例
首先，让我们开始探索一个简单的例子。此例子中需要结合来自多个数据源的信息，此外还需要一些基本的算术知识。
任务：How many years passed between the construction of the Eiffel Tower and the construction of the Empire State Building?（埃菲尔铁塔的建造和帝国大厦的建造之间相隔了多少年？）
以下给出的是管理代理的执行日志。它可以正确地将任务分解为查找两座建筑的建造时间并计算年份差。
Agent: Thought: First, I need to find out when the Eiffel Tower and the Empire State Building were constructed. I will use the `wikipedia_search_agent` tool to find this information.
Code:
```py
wikipedia_search_agent(query="Eiffel Tower construction year")
```<end_action>
Observation: Print outputs:
Last output from code snippet:
According to the information extracted from the Wikipedia page 'Eiffel Tower', the construction of the Eiffel Tower took place from 1887 to 1889.
Agent: Thought: Now I have the construction period of the Eiffel Tower. Next, I need to find the construction period of the Empire State Building. I will use the `wikipedia_search_agent` tool again.
Code:
```py
wikipedia_search_agent(query="Empire State Building construction year")
```<end_action>
Observation: Print outputs:
Last output from code snippet:
According to the information extracted from the Wikipedia page 'Empire State Building', the construction of the Empire State Building started in 1930 and ended in 1931.
Agent: Thought: Now I have the construction periods for both the Eiffel Tower and the Empire State Building. I can now calculate the number of years between their constructions.
Code:
```py
construction_eiffel_tower_start = 1887
construction_eiffel_tower_end = 1889
construction_empire_state_building_start = 1930
construction_empire_state_building_end = 1931
years_passed = construction_empire_state_building_start - construction_eiffel_tower_end
answer = f"The number of years passed between the construction of the Eiffel Tower and the Empire State Building is {years_passed} years."
final_answer(answer)
```<end_action>
Observation: Print outputs:
Last output from code snippet:
The number of years passed between the construction of the Eiffel Tower and the Empire State Building is 41 years.现在，让我们来直观地看一下维基百科搜索代理的执行情况。它正确地搜索并报告了页面摘要中发现的施工期，而无需检查单个页面。值得注意的是，尽管被问及“施工年份”，但它报告了整个施工期，因为不清楚年份是指施工工程的开始还是结束。
TASK: Eiffel Tower construction year
AGENT: Thought: I will use the `search_wikipedia` tool to find information about the Eiffel Tower construction year.
Code:
```py
search_wikipedia('Eiffel Tower construction year')
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
Pages found for query 'Eiffel Tower construction year':
Page: Eiffel Tower
Summary: The Eiffel Tower ( EYE-fəl; French: Tour Eiffel [tuʁ ɛfɛl] ) is a wrought-iron lattice tower on the Champ de Mars in Paris, France. It is named after the engineer Gustave Eiffel, whose company designed and built the tower from 1887 to 1889.
Locally nicknamed "La dame de fer" (French for "Iron Lady"), it was constructed as the centerpiece of the 1889 World's Fair, and to crown the centennial anniversary of the French Revolution. Although initially criticised by some of France's leading artists and intellectuals for its design, it has since become a global cultural icon of France and one of the most recognisable structures in the world. The tower received 5,889,000 visitors in 2022. The Eiffel Tower is the most visited monument with an entrance fee in the world: 6.91 million people ascended it in 2015. It was designated a monument historique in 1964, and was named part of a UNESCO World Heritage Site ("Paris, Banks of the Seine") in 1991.
The tower is 330 metres (1,083 ft) tall, about t
Page: Eiffel Tower (Paris, Texas)
Summary: Texas's Eiffel Tower is a landmark in the city of Paris, Texas. The tower was constructed in 1993. It is a scale model of the Eiffel Tower in Paris, France; at 65 feet in height, it is roughly one-sixteenth of the height of the original.
Page: Gustave Eiffel
Summary: Alexandre Gustave Eiffel ( EYE-fəl, French: [alɛksɑ̃dʁ ɡystav ɛfɛl]; né Bonickhausen dit Eiffel; 15 December 1832 – 27 December 1923) was a French civil engineer. A graduate of École Centrale des Arts et Manufactures, he made his name with various bridges for the French railway network, most famously the Garabit Viaduct. He is best known for the world-famous Eiffel Tower, designed by his company and built for the 1889 Universal Exposition in Paris, and his contribution to building the Statue of Liberty in New York. After his retirement from engineering, Eiffel focused on research into meteorology and aerodynamics, making significant contributions in both fields.
Page: Watkin's Tower
Summary: Watkin's Tower was a partially completed iron lattice tower in Wembley Park, London, England. Its construction was an ambitious project to create a 358-metre (1,175 ft)-high visitor attraction in Wembley Park to the north of the city, led by the railway entrepreneur Sir Edward Watkin. Marketed as the "Great Tower of London", it was designed to surpass the height of the Eiffel Tower in Paris, and it was part of Wembley Park's emergence as a recreational place. The tower was never completed and it was demolished in 1907. The site of the tower is now occupied by the English national football ground, Wembley Stadium.
Page: Eiffel Tower (Paris, Tennessee)
Summary: The Eiffel Tower is a landmark in the city of Paris, Tennessee. It is a 1:20 scale replica of the original located in Paris, France.
AGENT: Thought: From the summary of the page 'Eiffel Tower', I can see that the construction of the Eiffel Tower took place from 1887 to 1889. I will use the `final_answer` tool to return the answer.
Code:
```py
final_answer("According to the information extracted from the Wikipedia page 'Eiffel Tower', the construction of the Eiffel Tower took place from 1887 to 1889.")
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
According to the information extracted from the Wikipedia page 'Eiffel Tower', the construction of the Eiffel Tower took place from 1887 to 1889.
------------------------------
TASK: Empire State Building construction year
AGENT: Thought: I will use the `search_wikipedia` tool to find information about the construction year of the Empire State Building.
Code:
```py
search_wikipedia('Empire State Building construction year')
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
Pages found for query 'Empire State Building construction year':
Page: Empire State Building
Summary: The Empire State Building is a 102-story Art Deco skyscraper in the Midtown South neighborhood of Manhattan in New York City. The building was designed by Shreve, Lamb & Harmon and built from 1930 to 1931. Its name is derived from "Empire State", the nickname of the state of New York. The building has a roof height of 1,250 feet (380 m) and stands a total of 1,454 feet (443.2 m) tall, including its antenna. The Empire State Building was the world's tallest building until the first tower of the World Trade Center was topped out in 1970; following the September 11 attacks in 2001, the Empire State Building was New York City's tallest building until it was surpassed in 2012 by One World Trade Center. As of 2024, the building is the seventh-tallest building in New York City, the ninth-tallest completed skyscraper in the United States, and the 57th-tallest completed skyscraper in the world.
The site of the Empire State Building, on the west side of Fifth Avenue between West 33rd and 34th St
Page: British Empire Building
Summary: The British Empire Building, also known by its address 620 Fifth Avenue, is a commercial building at Rockefeller Center in the Midtown Manhattan neighborhood of New York City. Completed in 1933, the six-story structure was designed in the Art Deco style by Raymond Hood, Rockefeller Center's lead architect. The British Empire Building, along with the nearly identical La Maison Francaise to the south and the high-rise International Building to the north, comprise a group of retail-and-office structures known as the International Complex. La Maison Francaise and the British Empire Building are separated by Channel Gardens, a planted pedestrian esplanade running west to the complex's Lower Plaza.
The facade is made of limestone, with a main entrance along Fifth Avenue and secondary entrances on 50th Street and Channel Gardens. The top of the British Empire Building contains setbacks, a rooftop garden, and a partial seventh-story penthouse. The building's entrances contain ornate decoration
Page: 2012 Empire State Building shooting
Summary: On August 24, 2012, a gunman shot and killed a former co-worker outside the Empire State Building in New York City. Following the initial shooting, the gunman, 58-year-old Jeffrey T. Johnson, was fatally shot by police officers after raising his weapon at them. Nine bystanders were wounded by stray bullets fired by the officers and ricocheting debris, but none suffered life-threatening injuries.
Page: Empire State Building in popular culture
Summary: The Empire State Building is a 102-story skyscraper on Fifth Avenue between West 33rd and 34th Streets in Midtown, Manhattan, New York City. It has a roof height of 1,250 feet (381 m), and with its antenna included, it stands a total of 1,454 feet (443.2 m) tall. The Empire State Building stood as the world's tallest building for nearly 40 years, from its completion in early 1931 until the topping out of the original World Trade Center's North Tower in late 1970. It has been featured in numerous films, TV shows, songs, video games, books, photographs, and artwork.
Page: Empire State Plaza
Summary: The Governor Nelson A. Rockefeller Empire State Plaza (known commonly as the Empire State Plaza, and also as the South Mall) is a complex of several state government buildings in downtown Albany, New York.
The complex was built between 1965 and 1976 at an estimated total cost of $2 billion. It houses several departments of the New York State administration and is integrated with the New York State Capitol, completed in 1899, which houses the state legislature. Among the offices at the plaza are the Department of Health and the Biggs Laboratory of the Wadsworth Center. The Empire State Art Collection, a major public collection of 1960s and 1970s monumental abstract artworks, is on permanent display throughout the site. The New York State Office of General Services maintains the plaza. The Nelson A. Rockefeller Empire State Plaza Performing Arts Center Corporation is a New York state public-benefit corporation that was created in 1979 to manage the performing arts facility in the plaza.
AGENT: Thought: From the summary of the page "Empire State Building", I can see that the building was designed and built from 1930 to 1931. I will use the `final_answer` tool to return the answer.
Code:
```py
final_answer("According to the information extracted from the Wikipedia page 'Empire State Building', the construction of the Empire State Building started in 1930 and ended in 1931.")
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
According to the information extracted from the Wikipedia page 'Empire State Building', the construction of the Empire State Building started in 1930 and ended in 1931.上面显然没有使用段落检索代理，因为所有信息都已在页面摘要中找到。
更复杂的例子
现在，让我们尝试一个更复杂的例子：询问桦木胶合板是否漂浮在酒精中。这个问题需要基本的物理理解和算术能力，并结合不同寻常的检索任务。
任务：Does birch plywood float in ethanol?（桦木胶合板是否漂浮在酒精中？）
首先，让我们以可视化方式分析一下各种代理的日志。
管理代理日志：
AGENT: Thought: To determine if birch plywood floats in ethanol, we need to know the density of both birch plywood and ethanol. If the density of birch plywood is less than the density of ethanol, it will float. I will use the `wikipedia_search_agent` tool to find the densities of birch plywood and ethanol.
Code:
```py
birch_plywood_density_info = wikipedia_search_agent("density of birch plywood")
ethanol_density_info = wikipedia_search_agent("density of ethanol")
print(birch_plywood_density_info)
print(ethanol_density_info)
```<end_action>
OBSERVATION: Print outputs:
The density of birch plywood is approximately 680 kg/m³.
The density of ethanol at 20°C is approximately 0.7894 g/cm³.
AGENT: Thought: Now that I have the densities, I can compare them. Birch plywood has a density of 680 kg/m³ and ethanol has a density of 0.7894 g/cm³. Since 1 g/cm³ is equal to 1000 kg/m³, the density of ethanol is 789.4 kg/m³. Since the density of birch plywood (680 kg/m³) is less than the density of ethanol (789.4 kg/m³), birch plywood will float in ethanol. I will now provide this conclusion using the `final_answer` function.
Code:
```py
final_answer("Birch plywood will float in ethanol because its density (680 kg/m³) is less than the density of ethanol (789.4 kg/m³).")
```<end_action>
OBSERVATION: Print outputs:
Last output from code snippet:
Birch plywood will float in ethanol because its density (680 kg/m³) is less than the density of ethanol (789.4 kg/m³).维基百科搜索代理日志：
TASK: density of birch plywood
AGENT: Thought: I will use the `search_wikipedia` tool to find information about the density of birch plywood.
Code:
```py
search_wikipedia('birch plywood')
```<end_action>
OBSERVATION: Print outputs:
Last output from code snippet:
Pages found for query 'birch plywood':
Page: Plywood
Summary: Plywood is a composite material manufactured from thin layers, or "plies", of wood veneer that have been stacked and glued together. It is an engineered wood from the family of manufactured boards, which include plywood, medium-density fibreboard (MDF), oriented strand board (OSB), and particle board (or chipboard).
All plywoods bind resin and wood fibre sheets (cellulose cells are long, strong and thin) to form a composite material. The sheets of wood are stacked such that each layer has its grain set typically (see below) perpendicular to its adjacent layers. This alternation of the grain is called cross-graining and has several important benefits: it reduces the tendency of wood to split when nailed at the edges; it reduces thickness swelling and shrinkage, providing improved dimensional stability; and it makes the strength of the panel consistent across all directions. There is usually an odd number of plies, so that the sheet is balanced, that is, the surface layers have their gr
Page: Birch
Summary: A birch is a thin-leaved deciduous hardwood tree of the genus Betula (), in the family Betulaceae, which also includes alders, hazels, and hornbeams. It is closely related to the beech-oak family Fagaceae. The genus Betula contains 30 to 60 known taxa of which 11 are on the IUCN 2011 Red List of Threatened Species. They are typically short-lived pioneer species and are widespread in the Northern Hemisphere, particularly in northern areas of temperate climates and in boreal climates. Birch wood is used for a wide range of purposes.
Page: Birch wood
Summary: Birch wood is a type of wood of the birch. Birch wood is pale yellow-brown wood having a close, straight grain and uniform texture that finishes to a smooth surface. Sometimes it is dyed to imitate mahogany. This type of wood is used for among others firewood, turnery, furniture, cabinetry, tools handles, hoops, plywood, flooring and shoe heels.
Page: Falco F8L
Summary: The Falco F8L is an Italian-designed lightweight 2-seater aerobatic aircraft.
Page: Crusader (speedboat)
Summary: Crusader was a jet-powered speed boat piloted by John Cobb.
The combination of an aerodynamically stable hull form and turbojet propulsion was proposed by Reid Railton, Cobb's adviser. A rocket-powered scale model was tested at Haslar. The full size design was by Peter du Cane and built by Vospers of Portsmouth. Technical assistance came from Saunders-Roe and Vickers-Supermarine. It cost £15,000 in 1949.
It was silver and scarlet in colour and 10 m long.
The engine was a de Havilland Ghost Mk 48 centrifugal turbojet provided as a loan by the Ministry of Supply at the request of Major Frank Halford, the engine designer. The engine was rated at 5,000 lb thrust fed by two scoop inlets forward of the cockpit.
The hull was of trimaran form, a main hull with a planing step, and two smaller rear-mounted outriggers. Construction was of birch plywood frames and stringers. The hull was skinned in birch ply covered in doped fabric with metal skin reinforcement for planing surfaces. Aircraft-sty
AGENT: Thought: The pages returned from the search did not directly mention the density of birch plywood. However, the page on Birch Wood mentions that birch wood is used for plywood. I will use the `search_info` tool to find more specific information about the density of birch plywood from the page 'Plywood'.
Code:
```py
search_info('density of birch plywood', 'Plywood')
```<end_action>
OBSERVATION: Print outputs:
Last output from code snippet:
Information retrieved from the page 'Plywood' for the query 'density of birch plywood':
The density of birch plywood is approximately 680 kg/m³.
AGENT: Thought: I have found the density of birch plywood from the Wikipedia page 'Plywood'. The density is approximately 680 kg/m³.
Code:
```py
final_answer("The density of birch plywood is approximately 680 kg/m³.")
```<end_action>
OBSERVATION: Print outputs:
Last output from code snippet:
The density of birch plywood is approximately 680 kg/m³.
------------------------------
TASK: density of ethanol
AGENT: Thought: I will use the `search_wikipedia` tool to find the density of ethanol from Wikipedia.
Code:
```py
search_wikipedia('density of ethanol')
```<end_action>
OBSERVATION: Print outputs:
Last output from code snippet:
Pages found for query 'density of ethanol':
Page: Ethanol (data page)
Summary: This page provides supplementary chemical data on ethanol.
Page: Ethanol
Summary: Ethanol (also called ethyl alcohol, grain alcohol, drinking alcohol, or simply alcohol) is an organic compound with the chemical formula CH3CH2OH. It is an alcohol, with its formula also written as C2H5OH, C2H6O or EtOH, where Et stands for ethyl. Ethanol is a volatile, flammable, colorless liquid with a characteristic wine-like odor and pungent taste. In nature, grape-sugar breaks up by the action of fermentation into alcohol or carbonic acid, without anything being added. As a psychoactive depressant, it is the active ingredient in alcoholic beverages, and the second most consumed drug globally behind caffeine.
Ethanol is naturally produced by the fermentation process of sugars by yeasts or via petrochemical processes such as ethylene hydration. Historically it was used as a general anesthetic, and has modern medical applications as an antiseptic, disinfectant, solvent for some medications, and antidote for methanol poisoning and ethylene glycol poisoning. It is used as a chemical so
Page: Alcohol by volume
Summary: Alcohol by volume (abbreviated as alc/vol or ABV) is a standard measure of the volume of alcohol contained in a given volume of an alcoholic beverage, expressed as a volume percent. It is defined as the number of millilitres (mL) of pure ethanol present in 100 mL (3.5 imp fl oz; 3.4 US fl oz) of solution at 20 °C (68 °F). The number of millilitres of pure ethanol is the mass of the ethanol divided by its density at 20 °C (68 °F), which is 0.78945 g/mL (0.82353 oz/US fl oz; 0.79122 oz/imp fl oz; 0.45633 oz/cu in). The alc/vol standard is used worldwide. The International Organization of Legal Metrology has tables of density of water–ethanol mixtures at different concentrations and temperatures.
In some countries, e.g. France, alcohol by volume is often referred to as degrees Gay-Lussac (after the French chemist Joseph Louis Gay-Lussac), although there is a slight difference since the Gay-Lussac convention uses the International Standard Atmosphere value for temperature, 15 °C (59 °F).
Page: Alcohol fuel
Summary: Various alcohols are used as fuel for internal combustion engines. The first four aliphatic alcohols (methanol, ethanol, propanol, and butanol)
are of interest as fuels because they can be synthesized chemically or biologically, and they have characteristics which allow them to be used in internal combustion engines. The general chemical formula for alcohol fuel is CnH2n+1OH.
Most methanol is produced from natural gas, although it can be produced from biomass using very similar chemical processes. Ethanol is commonly produced from biological material through fermentation processes. Biobutanol has the advantage in combustion engines in that its energy density is closer to gasoline than the simpler alcohols (while still retaining over 25% higher octane rating); however, biobutanol is currently more difficult to produce than ethanol or methanol. When obtained from biological materials and/or biological processes, they are known as bioalcohols (e.g. "bioethanol"). There is no chemical dif
Page: Cellulosic ethanol
Summary: Cellulosic ethanol is ethanol (ethyl alcohol) produced from cellulose (the stringy fiber of a plant) rather than from the plant's seeds or fruit. It can be produced from grasses, wood, algae, or other plants. It is generally discussed for use as a biofuel. The carbon dioxide that plants absorb as they grow offsets some of the carbon dioxide emitted when ethanol made from them is burned, so cellulosic ethanol fuel has the potential to have a lower carbon footprint than fossil fuels.
Interest in cellulosic ethanol is driven by its potential to replace ethanol made from corn or sugarcane. Since these plants are also used for food products, diverting them for ethanol production can cause food prices to rise; cellulose-based sources, on the other hand, generally do not compete with food, since the fibrous parts of plants are mostly inedible to humans. Another potential advantage is the high diversity and abundance of cellulose sources; grasses, trees and algae are found in almost every envi
AGENT: Thought: The summary of the page 'Ethanol' mentions that ethanol is an alcohol with a characteristic wine-like odor and pungent taste. However, it does not provide the density of ethanol. I will use the `search_info` tool to find the density of ethanol from the 'Ethanol (data page)'.
Code:
```py
search_info('density of ethanol', 'Ethanol (data page)')
```<end_action>
OBSERVATION: Print outputs:
Last output from code snippet:
Information retrieved from the page 'Ethanol (data page)' for the query 'density of ethanol':
The density of ethanol at 20°C is approximately 0.7894 g/cm³.
AGENT: Thought: I have found the density of ethanol from the Wikipedia page 'Ethanol (data page)'. I will return the result using the `final_answer` tool.
Code:
```py
final_answer("The density of ethanol at 20°C is approximately 0.7894 g/cm³.")
```<end_action>
OBSERVATION: Print outputs:
Last output from code snippet:
The density of ethanol at 20°C is approximately 0.7894 g/cm³.页面搜索代理日志如下：
TASK: Retrieve information about the query:"density of birch plywood" from the Wikipedia page "Plywood".
AGENT: Thought: I need to find the density of birch plywood. I will use the tool `retrieve_passages` to look for data on the Wikipedia page.
Code:
```py
result = retrieve_passages("density of birch plywood")
print(result)
```<end_action>
OBSERVATION: Print outputs:
Retrieved passages for query "density of birch plywood":
Passage 0: ... . Shear stress, by contrast, is higher in the center of the panel, and at the outer fibres. Within Europe basic plywood can be divided into three main categories: birch plywood (density approx. 680 kg/m3), mixed plywood (density approx. 620 kg/m3) and conifer plywoods (density 460–520 kg/m3). ...
Passage 1: ... . Aircraft grade plywood is made from three or more plies of birch, as thin as 0.40 millimetres (1⁄64 in) thick in total, and is extremely strong and light. ...
Passage 2: ... Baltic Birch plywood is a product of an area around the Baltic Sea. Originally manufactured for European cabinet makers but now popular in the United States as well. It is very stable composed of an inner void-free core of cross-banded birch plys with an exterior grade adhesive. The face veneers are thicker than traditional cabinet grade ...
Passage 3: ... . As a result, thicker panels can span greater distances under the same loads. In bending, the maximum stress occurs in the outermost layers, one in tension, the other in compression. Bending stress decreases from the maximum at the face layers to nearly zero at the central layer. Shear stress, by contrast, is higher in the center of the panel, and at the outer fibres. Within Europe basic plywood can be divided into three main categories: birch plywood (density approx ...
Passage 4: ... Wind turbine blades
Insulation boxes for liquefied natural gas (LNG) carriers
Smooth surface and accurate thickness combined with the durability of the material makes birch plywood a favorable material for many special end uses e.g.:
High-end loud speakers
Die-cutting boards
Supporting structure for parquet
Playground equipment
Furniture
Signs and fences for demanding outdoor advertising
Musical instruments
Sports equipment...
AGENT: Thought: From the passages, I can see that the density of birch plywood is approximately 680 kg/m³. I can use the `final_answer` tool to provide the answer.
Code:
```py
final_answer("The density of birch plywood is approximately 680 kg/m³.")
```<end_action>
OBSERVATION: Print outputs:
Last output from code snippet:
The density of birch plywood is approximately 680 kg/m³.
------------------------------
TASK: Retrieve information about the query:"density of ethanol" from the Wikipedia page "Ethanol (data page)".
AGENT: Thought: I need to find the density of ethanol. I will use the tool `retrieve_passages` to get the information from the Wikipedia page.
Code:
```py
result = retrieve_passages("density of ethanol")
print(result)
```<end_action>
OBSERVATION: Print outputs:
Retrieved passages for query "density of ethanol":
Passage 0: ... == Density of ethanol at various temperatures ==
Data obtained from Lange 1967
These data correlate as ρ [g/cm3] = −8.461834×10−4 T [°C] + 0.8063372 with an R2 = 0.99999.
== Properties of aqueous ethanol solutions ==
Data obtained from Lange 1967
== Boiling points of aqueous solutions ==
Data obtained from CRC Handbook of Chemistry (Page 2117): 2391
‡Azeotropic mixture
== Charts ==
== References == ...
Passage 1: ... This page provides supplementary chemical data on ethanol.
== Material Safety Data Sheet ==
External MSDS
== Structure and properties ==
== Thermodynamic properties ==
== Spectral data ==
== Vapor pressure of liquid ==
== Density of ethanol at various temperatures ==
Data obtained from Lange 1967
These data correlate as ρ [g/cm3] = −8.461834×10−4 T [°C] + 0.8063372 with an R2 = 0.99999.
== Properties of aqueous ethanol solutions ==
Data obtained from Lange 1967...
AGENT: Thought: From the passages, I can see that the density of ethanol varies with temperature. I can use the provided linear equation to calculate the density at a specific temperature. I will use the `math` module to perform the calculation.
Code:
```py
# Extract the coefficients from the equation
a = -8.461834e-4
b = 0.8063372
# Calculate the density at a specific temperature, let's take 20°C as an example
temperature = 20
density = a * temperature + b
print(density)
```<end_action>
OBSERVATION: Print outputs:
0.789413532
AGENT: Thought: The passage provides a linear equation to calculate the density of ethanol at different temperatures. I can now use this equation to provide the density of ethanol at a specific temperature. I will use the `final_answer` tool to return the relevant information.
Code:
```py
final_answer(f"The density of ethanol at 20°C is approximately {round(0.789413532, 4)} g/cm³.")
```<end_action>
OBSERVATION: Print outputs:
Last output from code snippet:
The density of ethanol at 20°C is approximately 0.7894 g/cm³.该模型正确地将密度差异识别为漂浮/下沉的原因，将任务分解为查找两种物质的密度，并且能够从检索到的数据中得出正确的结论，尽管它们采用的是不同的测量单位。
局限性
我们上面所讨论的系统具有令人印象深刻的功能，尤其是考虑到所用引擎模型的有限大小时。该系统也有自己的局限性。这其中更大的一个局限性似乎与引擎模型本身的功能有关：虽然它似乎能够理解和遵循复杂而冗长的指令以及正确使用所提供的工具，但有时它竟然无法遵守简单的指导方针，并且倾向于重复无效的操作而不做任何改变。当代理正在寻找的信息不存在（或无法使用语义搜索工具轻松提取）时，这种情况尤其突出。
另一个缺点是代理固有的缺点，在多代理系统中更为突出，即各种代理执行所需的计算时间。在某些简单情况下，标准RAG工作流程足以回答问题，这可能会产生不必要的计算开销。
最后，多个代理相互交互会增加幻觉的风险，因为一个代理产生的幻觉可能会在执行链中传播，这也使得追踪变得非常困难。
让我们看一个例子，在这个例子中，系统虽然仍然提供正确的答案，但过度使用工具调用（带有一些重复的操作），不必要地延长了执行时间。
任务：Which dynasty was ruling China at the time of the fall of Constantinople?（君士坦丁堡陷落时，哪个朝代统治着中国？）
该任务需要良好的抽象水平，因为这两个事件没有关联，君士坦丁堡陷落的确切年份可能不会在相应朝代的页面上报告。
管理代理的执行仍然精简且准确，通过首先检索君士坦丁堡陷落的日期，然后查找那一年的中国朝代，正确地解决了任务。然而，我们可以看到，搜索结果虽然仍然包含所需的信息，但看起来有点奇怪。
Agent: Thought: To answer this question, I need to find out when Constantinople fell and which Chinese dynasty was ruling at that time. I'll start by finding the fall date of Constantinople.
Code:
```py
wikipedia_search_agent(query="Fall of Constantinople")
```<end_action>
Observation: Print outputs:
Last output from code snippet:
The leader of the Ottoman Empire in 1453, during the fall of Constantinople, was Mehmed II, also known as Mehmed the Conqueror.
Agent: Thought: From the previous search, we know that Constantinople fell in 1453, and it was conquered by Mehmed II. Now I need to find out which Chinese dynasty was ruling in 1453. I will search for the Chinese dynasties around that time.
Code:
```py
wikipedia_search_agent(query="Chinese dynasties 1453")
```<end_action>
Observation: Print outputs:
Last output from code snippet:
In 1453, the Ming dynasty was in full control of China. No specific events related to 1453 are mentioned in the information provided.
Agent: Thought: Based on the information provided, the Ming dynasty was in full control of China in 1453. Therefore, the dynasty ruling China when Constantinople fell would be the Ming dynasty.
Code:
```py
final_answer("The dynasty ruling China when Constantinople fell in 1453 was the Ming dynasty.")
```<end_action>
Observation: Print outputs:
Last output from code snippet:
The dynasty ruling China when Constantinople fell in 1453 was the Ming dynasty.让我们检查相应的维基百科搜索代理任务及其执行情况。我们可以看到，可能是由于“君士坦丁堡陷落”这个宽泛的任务，代理在找到正确的日期后会查看其他特定信息。检索有关中国朝代的信息时也会发生同样的情况，但另一个问题是某些工具调用重复了相同的内容。
TASK: Fall of Constantinople
AGENT: Thought: I will use the `search_wikipedia` tool to find information about the fall of Constantinople. This will likely provide me with a summary of the event and possibly links to related pages.
Code:
```py
search_wikipedia("Fall of Constantinople")
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
Pages found for query 'Fall of Constantinople':
Page: Fall of Constantinople
Summary: The fall of Constantinople, also known as the conquest of Constantinople, was the capture of the capital of the Byzantine Empire by the Ottoman Empire. The city was captured on 29 May 1453 as part of the culmination of a 55-day siege which had begun on 6 April.
The attacking Ottoman Army, which significantly outnumbered Constantinople's defenders, was commanded by the 21-year-old Sultan Mehmed II (later nicknamed "the Conqueror"), while the Byzantine army was led by Emperor Constantine XI Palaiologos. After conquering the city, Mehmed II made Constantinople the new Ottoman capital, replacing Adrianople.
The fall of Constantinople and of the Byzantine Empire was a watershed of the Late Middle Ages, marking the effective end of the Roman Empire, a state which began in roughly 27 BC and had lasted nearly 1500 years. For many modern historians, the fall of Constantinople marks the end of the medieval period and the beginning of the early modern period. The city's fall also stood as a turni
Page: Sack of Constantinople
Summary: The sack of Constantinople occurred in April 1204 and marked the culmination of the Fourth Crusade. Crusaders sacked and destroyed most of Constantinople, the capital of the Byzantine Empire. After the capture of the city, the Latin Empire (known to the Byzantines as the Frankokratia, or the Latin occupation) was established and Baldwin of Flanders crowned as Emperor Baldwin I of Constantinople in Hagia Sophia.
After the city's sacking, most of the Byzantine Empire's territories were divided up among the Crusaders. Byzantine aristocrats also established a number of small independent splinter states—one of them being the Empire of Nicaea, which would eventually recapture Constantinople in 1261 and proclaim the reinstatement of the Empire. However, the restored Empire never managed to reclaim all its former territory or attain its earlier economic strength, and it gradually succumbed to the rising Ottoman Empire over the following two centuries.
The Byzantine Empire was left poorer, smal
Page: Constantinople
Summary: Constantinople (see other names) became the capital of the Roman Empire during the reign of Constantine the Great in 330. Following the collapse of the Western Roman Empire in the late 5th century, Constantinople remained the capital of the Eastern Roman Empire (also known as the Byzantine Empire; 330–1204 and 1261–1453), the Latin Empire (1204–1261), and the Ottoman Empire (1453–1922). Following the Turkish War of Independence, the Turkish capital then moved to Ankara. Officially renamed Istanbul in 1930, the city is today the largest city in Europe, straddling the Bosporus strait and lying in both Europe and Asia, and the financial center of Turkey.
In 324, following the reunification of the Eastern and Western Roman Empires, the ancient city of Byzantium was selected to serve as the new capital of the Roman Empire, and the city was renamed Nova Roma, or 'New Rome', by Emperor Constantine the Great. On 11 May 330, it was renamed Constantinople and dedicated to Constantine. Constantin
Page: Moscow, third Rome
Summary: Moscow, third Rome (Russian: Москва — третий Рим; Moskva, tretiĭ Rim) is a theological and political concept asserting Moscow as the successor to ancient Rome, with the Russian world carrying forward the legacy of the Roman Empire. The term "third Rome" refers to a historical topic of debate in European culture: the question of the successor city to the "first Rome" (Rome, within the Western Roman Empire) and the "second Rome" (Constantinople, within the Eastern Roman Empire).
Page: Byzantine Empire
Summary: The Byzantine Empire, also referred to as the Eastern Roman Empire, was the continuation of the Roman Empire centred in Constantinople during late antiquity and the Middle Ages. The eastern half of the Empire survived the conditions that caused the fall of the West in the 5th century AD, and continued to exist until the fall of Constantinople to the Ottoman Empire in 1453. During most of its existence, the empire remained the most powerful economic, cultural, and military force in the Mediterranean world. The term "Byzantine Empire" was only coined following the empire's demise; its citizens referred to the polity as the "Roman Empire" and to themselves as "Romans". Due to the imperial seat's move from Rome to Byzantium, the adoption of state Christianity, and the predominance of Greek instead of Latin, modern historians continue to make a distinction between the earlier Roman Empire and the later Byzantine Empire.
During the earlier Pax Romana period, the western parts of the empire b
AGENT: Thought: From the summary of the page "Fall of Constantinople", I can see that the event took place in 1453. I will use the `search_info` tool to find more details about the event, specifically who was the leader of the Ottoman Empire at that time.
Code:
```py
search_info("leader of the Ottoman Empire in 1453", "Fall of Constantinople")
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
Information retrieved from the page 'Fall of Constantinople' for the query 'leader of the Ottoman Empire in 1453':
The leader of the Ottoman Empire in 1453 was Mehmed II, also known as Mehmed the Conqueror.
AGENT: Thought: I have found that the leader of the Ottoman Empire in 1453 was Mehmed II, also known as Mehmed the Conqueror. I will use the `final_answer` tool to provide the answer.
Code:
```py
final_answer("The leader of the Ottoman Empire in 1453, during the fall of Constantinople, was Mehmed II, also known as Mehmed the Conqueror.")
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
The leader of the Ottoman Empire in 1453, during the fall of Constantinople, was Mehmed II, also known as Mehmed the Conqueror.
------------------------------
TASK: Chinese dynasties 1453
AGENT: Thought: I will use the `search_wikipedia` tool to find information about Chinese dynasties around the year 1453. I will provide a general query related to Chinese dynasties in that time period.
Code:
```py
search_wikipedia('Chinese dynasties 1453')
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
Pages found for query 'Chinese dynasties 1453':
Page: Chinese Empire
Summary: Chinese Empire (or Empire of China) is a term referring to the realm ruled by the Emperor of China during the era known as Imperial China. It was coined by western scholars and used to describe the Ming and Qing dynasties (or imperial Chinese dynasties in general). Another term was "Celestial Empire", in reference to the status of the emperor as the Son of Heaven. In 221 BC, China was unified under an emperor for the first time, and various dynasties or empires founded by hereditary monarchs ruled China for a total of two millennia since then, including the Qin, Han, Jin, Sui, Tang, Song, Yuan, Ming, and Qing.
Page: Ming dynasty
Summary: The Ming dynasty, officially the Great Ming, was an imperial dynasty of China, ruling from 1368 to 1644 following the collapse of the Mongol-led Yuan dynasty. The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China. Although the primary capital of Beijing fell in 1644 to a rebellion led by Li Zicheng (who established the short-lived Shun dynasty), numerous rump regimes ruled by remnants of the Ming imperial family—collectively called the Southern Ming—survived until 1662.
The Ming dynasty's founder, the Hongwu Emperor (r. 1368–1398), attempted to create a society of self-sufficient rural communities ordered in a rigid, immobile system that would guarantee and support a permanent class of soldiers for his dynasty: the empire's standing army exceeded one million troops and the navy's dockyards in Nanjing were the largest in the world. He also took great care breaking the power of the court eunuchs and unrelated magnates, enfeoff
Page: List of time periods
Summary: The categorisation of the past into discrete, quantified named blocks of time is called periodization. This is a list of such named time periods as defined in various fields of study.
These can be divided broadly into prehistorical periods and historical periods
(when written records began to be kept).
In archaeology and anthropology, prehistory is subdivided into the three-age system, this list includes the use of the three-age system as well as a number of various designation used in reference to sub-ages within the traditional three.
The dates for each age can vary by region. On the geologic time scale, the Holocene epoch starts at the end of the last glacial period of the current ice age (c. 10,000 BC) and continues to the present. The beginning of the Mesolithic is usually considered to correspond to the beginning of the Holocene epoch.
Page: Celestial Empire
Summary: Celestial Empire (Chinese: 天朝; pinyin: Tiāncháo; lit. 'heavenly dynasty') is an old name used to refer to China or the Chinese Empire, from a literary and poetic translation of the Chinese term, one of many names for China. The name was used in reference to the status of the Emperor of China as the Son of Heaven in the Sinosphere.
Accordingly, in the 19th century, the name "Celestial" was used to refer to Chinese people. Both terms were widely used in the English-language popular mass media of the day, but fell into disuse later on. Its usage has become popular again in the present day (2015), particularly among Chinese Internet users. It is used to refer to the current Communist regime, to imply either disapproval for its political suppression and arrogance or national pride in the country's emergence as a superpower in the 21st century, depending on the context.
In modern times it has mostly fallen into disuse, but the name "Celestial Empire" still appears in various media such as ar
Page: List of dynasties
Summary: This is a list of monarchical dynasties and dynastic regimes organized by geographic region. Extant dynasties are rendered in bold and highlighted.
AGENT: Thought: From the summaries, I can see that the Ming dynasty ruled from 1368 to 1644, which covers the year 1453. I will use the `search_info` tool to find more detailed information about the Ming dynasty during the year 1453.
Code:
```py
search_info('1453', 'Ming dynasty')
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
Information retrieved from the page 'Ming dynasty' for the query '1453':
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
AGENT: Thought: Now that I know the Ming dynasty ruled during 1453, I can provide a more specific answer about the events that happened in China during that year. However, the information provided does not give us specific details about the events in 1453. I will use the `search_info` tool to find more detailed information about the Ming dynasty during the year 1453.
Code:
```py
search_info('1453', 'Ming dynasty')
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
Information retrieved from the page 'Ming dynasty' for the query '1453':
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
AGENT: Thought: The information provided does not specifically mention the events of 1453. However, we can infer that during the Ming dynasty, significant developments occurred. I will use the `search_info` tool to find more specific information about the events of 1453 in the Ming dynasty.
Code:
```py
search_info('1453', 'Ming dynasty')
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
Information retrieved from the page 'Ming dynasty' for the query '1453':
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
AGENT: Thought: The information provided indicates that the Ming dynasty was in full control of China during the year 1453. However, there is no specific mention of events that happened in 1453. I will use the `search_info` tool to find more specific information about the events of 1453 in the Ming dynasty.
Code:
```py
search_info('1453', 'Ming dynasty')
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
Information retrieved from the page 'Ming dynasty' for the query '1453':
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
AGENT: Thought: The information provided does not specifically mention any events that occurred in 1453. However, we know that the Ming dynasty was in full control of China during this time. I will use the `final_answer` tool to provide the answer based on the information we have.
Code:
```py
final_answer("In 1453, the Ming dynasty was in full control of China. No specific events related to 1453 are mentioned in the information provided.")
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
In 1453, the Ming dynasty was in full control of China. No specific events related to 1453 are mentioned in the information provided.深入研究页面搜索代理的执行情况，我们发现这里也使用相同的参数重复了多个工具调用。
TASK: Retrieve information about the query:"leader of the Ottoman Empire in 1453" from the Wikipedia page "Fall of Constantinople".
AGENT: Thought: I need to find out who was the leader of the Ottoman Empire in 1453. I will use the `retrieve_passages` tool to search for this information on the Wikipedia page "Fall of Constantinople".
Code:
```py
result = retrieve_passages("leader of the Ottoman Empire in 1453")
print(result)
```<end_action>
OBSERVATIONS: Print outputs:
Retrieved passages for query "leader of the Ottoman Empire in 1453":
Passage 0: ... When Mehmed II succeeded his father in 1451, he was 19 years old. Many European courts assumed that the young Ottoman ruler would not seriously challenge Christian hegemony in the Balkans and the Aegean. In fact, Europe celebrated Mehmed coming to the throne and hoped his inexperience would lead the Ottomans astray. This calculation was boosted by Mehmed's friendly overtures to the European envoys at his new court. But Mehmed's mild words were not matched by his actions ...
Passage 1: ... The attacking Ottoman Army, which significantly outnumbered Constantinople's defenders, was commanded by the 21-year-old Sultan Mehmed II (later nicknamed "the Conqueror"), while the Byzantine army was led by Emperor Constantine XI Palaiologos. After conquering the city, Mehmed II made Constantinople the new Ottoman capital, replacing Adrianople. ...
Passage 2: ... . The oldest boy, renamed Murad, became a personal favourite of Mehmed and served as Beylerbey (Governor-General) of Rumeli (the Balkans). The younger son, renamed Mesih Pasha, became Admiral of the Ottoman fleet and Sancak Beg (Governor) of the province of Gallipoli. He eventually served twice as Grand Vizier under Mehmed's son, Bayezid II. ...
Passage 3: ... == External links ==
Media related to Fall of Constantinople (1453) at Wikimedia Commons
The Siege of Constantinople As The Islamic World Sees it Archived 22 April 2021 at the Wayback Machine
World History Encyclopedia – 1453: The Fall of Constantinople
Constantinople Siege & Fall, BBC Radio 4 discussion with Roger Crowley, Judith Herrin & Colin Imber (In Our Time, 28 December 2006). ...
Passage 4: ... In the summer of 1452, when Rumeli Hisarı was completed and the threat of the Ottomans had become imminent, Constantine wrote to the Pope, promising to implement the union, which was declared valid by a half-hearted imperial court on 12 December 1452. Although he was eager for an advantage, Pope Nicholas V did not have the influence the Byzantines thought he had over the Western kings and princes, some of whom were wary of increasing papal control...
AGENT: Thought: From the passages, it seems that the leader of the Ottoman Empire in 1453 was Mehmed II, also known as Mehmed the Conqueror. I will use the `final_answer` tool to provide the answer.
Code:
```py
final_answer("The leader of the Ottoman Empire in 1453 was Mehmed II, also known as Mehmed the Conqueror.")
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
The leader of the Ottoman Empire in 1453 was Mehmed II, also known as Mehmed the Conqueror.
------------------------------
TASK: Retrieve information about the query:"1453" from the Wikipedia page "Ming dynasty".
AGENT: Thought: I need to find information related to the year 1453 from the Wikipedia page "Ming dynasty". I will use the `retrieve_passages` tool to get relevant passages.
Code:
```py
result = retrieve_passages("1453 Ming dynasty")
print(result)
```<end_action>
OBSERVATIONS: Print outputs:
Retrieved passages for query "1453 Ming dynasty":
Passage 0: ... The Ming dynasty, officially the Great Ming, was an imperial dynasty of China, ruling from 1368 to 1644 following the collapse of the Mongol-led Yuan dynasty. The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China ...
Passage 1: ... === Reference works and primary sources ===
Farmer, Edward L. ed. Ming History: An Introductory Guide to Research (1994).
Goodrich, Luther Carrington (1976). Dictionary of Ming Biography, 1368–1644. New York: Columbia University Press. ISBN 978-0-231-03833-1.
The Ming History English Translation Project, A collaborative project that makes available translations (from Chinese to English) of portions of the 明史 Mingshi (Official History of the Ming Dynasty). ...
Passage 2: ... ==== Reign of the Hongwu Emperor ==== ...
Passage 3: ... . The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China. Although the primary capital of Beijing fell in 1644 to a rebellion led by Li Zicheng (who established the short-lived Shun dynasty), numerous rump regimes ruled by remnants of the Ming imperial family—collectively called the Southern Ming—survived until 1662. ...
Passage 4: ... . Zhu Di assumed the throne as the Yongle Emperor (r. 1402–24); his reign is universally viewed by scholars as a "second founding" of the Ming dynasty since he reversed many of his father's policies....
AGENT: Thought: The passages do not directly mention the year 1453. However, I can infer that the Ming dynasty lasted from 1368 to 1644, and 1453 falls within this period. I will use the `final_answer` tool to provide a summary based on the information available.
Code:
```py
final_answer("The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.")
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
------------------------------
TASK: Retrieve information about the query:"1453" from the Wikipedia page "Ming dynasty".
AGENT: Thought: I need to find information related to the year 1453 from the Wikipedia page "Ming dynasty". I will use the `retrieve_passages` tool to get relevant passages.
Code:
```py
result = retrieve_passages("1453 Ming dynasty")
print(result)
```<end_action>
OBSERVATIONS: Print outputs:
Retrieved passages for query "1453 Ming dynasty":
Passage 0: ... The Ming dynasty, officially the Great Ming, was an imperial dynasty of China, ruling from 1368 to 1644 following the collapse of the Mongol-led Yuan dynasty. The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China ...
Passage 1: ... === Reference works and primary sources ===
Farmer, Edward L. ed. Ming History: An Introductory Guide to Research (1994).
Goodrich, Luther Carrington (1976). Dictionary of Ming Biography, 1368–1644. New York: Columbia University Press. ISBN 978-0-231-03833-1.
The Ming History English Translation Project, A collaborative project that makes available translations (from Chinese to English) of portions of the 明史 Mingshi (Official History of the Ming Dynasty). ...
Passage 2: ... ==== Reign of the Hongwu Emperor ==== ...
Passage 3: ... . The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China. Although the primary capital of Beijing fell in 1644 to a rebellion led by Li Zicheng (who established the short-lived Shun dynasty), numerous rump regimes ruled by remnants of the Ming imperial family—collectively called the Southern Ming—survived until 1662. ...
Passage 4: ... . Zhu Di assumed the throne as the Yongle Emperor (r. 1402–24); his reign is universally viewed by scholars as a "second founding" of the Ming dynasty since he reversed many of his father's policies....
AGENT: Thought: The passages do not directly mention the year 1453. However, I can infer that the Ming dynasty lasted from 1368 to 1644, and 1453 falls within this period. I will use the `final_answer` tool to provide a summary based on the information available.
Code:
```py
final_answer("The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.")
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
------------------------------
TASK: Retrieve information about the query:"1453" from the Wikipedia page "Ming dynasty".
AGENT: Thought: I need to find information related to the year 1453 from the Wikipedia page "Ming dynasty". I will use the `retrieve_passages` tool to get relevant passages.
Code:
```py
result = retrieve_passages("1453 Ming dynasty")
print(result)
```<end_action>
OBSERVATIONS: Print outputs:
Retrieved passages for query "1453 Ming dynasty":
Passage 0: ... The Ming dynasty, officially the Great Ming, was an imperial dynasty of China, ruling from 1368 to 1644 following the collapse of the Mongol-led Yuan dynasty. The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China ...
Passage 1: ... === Reference works and primary sources ===
Farmer, Edward L. ed. Ming History: An Introductory Guide to Research (1994).
Goodrich, Luther Carrington (1976). Dictionary of Ming Biography, 1368–1644. New York: Columbia University Press. ISBN 978-0-231-03833-1.
The Ming History English Translation Project, A collaborative project that makes available translations (from Chinese to English) of portions of the 明史 Mingshi (Official History of the Ming Dynasty). ...
Passage 2: ... ==== Reign of the Hongwu Emperor ==== ...
Passage 3: ... . The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China. Although the primary capital of Beijing fell in 1644 to a rebellion led by Li Zicheng (who established the short-lived Shun dynasty), numerous rump regimes ruled by remnants of the Ming imperial family—collectively called the Southern Ming—survived until 1662. ...
Passage 4: ... . Zhu Di assumed the throne as the Yongle Emperor (r. 1402–24); his reign is universally viewed by scholars as a "second founding" of the Ming dynasty since he reversed many of his father's policies....
AGENT: Thought: The passages do not directly mention the year 1453. However, I can infer that the Ming dynasty lasted from 1368 to 1644, and 1453 falls within this period. I will use the `final_answer` tool to provide a summary based on the information available.
Code:
```py
final_answer("The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.")
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.
------------------------------
TASK: Retrieve information about the query:"1453" from the Wikipedia page "Ming dynasty".
AGENT: Thought: I need to find information related to the year 1453 from the Wikipedia page "Ming dynasty". I will use the `retrieve_passages` tool to get relevant passages.
Code:
```py
result = retrieve_passages("1453 Ming dynasty")
print(result)
```<end_action>
OBSERVATIONS: Print outputs:
Retrieved passages for query "1453 Ming dynasty":
Passage 0: ... The Ming dynasty, officially the Great Ming, was an imperial dynasty of China, ruling from 1368 to 1644 following the collapse of the Mongol-led Yuan dynasty. The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China ...
Passage 1: ... === Reference works and primary sources ===
Farmer, Edward L. ed. Ming History: An Introductory Guide to Research (1994).
Goodrich, Luther Carrington (1976). Dictionary of Ming Biography, 1368–1644. New York: Columbia University Press. ISBN 978-0-231-03833-1.
The Ming History English Translation Project, A collaborative project that makes available translations (from Chinese to English) of portions of the 明史 Mingshi (Official History of the Ming Dynasty). ...
Passage 2: ... ==== Reign of the Hongwu Emperor ==== ...
Passage 3: ... . The Ming dynasty was the last imperial dynasty of China ruled by the Han people, the majority ethnic group in China. Although the primary capital of Beijing fell in 1644 to a rebellion led by Li Zicheng (who established the short-lived Shun dynasty), numerous rump regimes ruled by remnants of the Ming imperial family—collectively called the Southern Ming—survived until 1662. ...
Passage 4: ... . Zhu Di assumed the throne as the Yongle Emperor (r. 1402–24); his reign is universally viewed by scholars as a "second founding" of the Ming dynasty since he reversed many of his father's policies....
AGENT: Thought: The passages do not directly mention the year 1453. However, I can infer that the Ming dynasty lasted from 1368 to 1644, and 1453 falls within this period. I will use the `final_answer` tool to provide a summary based on the information available.
Code:
```py
final_answer("The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.")
```<end_action>
OBSERVATIONS: Print outputs:
Last output from code snippet:
The year 1453 falls within the period of the Ming dynasty, which ruled from 1368 to 1644. During this time, the Ming dynasty was in full control of China and experienced significant developments such as the construction of the Forbidden City and the expansion of the Great Wall of China.结论
在本文中，我介绍了如何使用代码代理与“小型”开源LLM（如Qwen2.5–7B-Instruct）创建一个多代理RAG系统。其中，我讨论了该系统的主要架构特性以及我为改进结果而做出的与Hugging Face代码代理实现相关的一些特定选择。该项目完整的代码详细信息可在GitHub存储库中找到。
值得注意的是，尽管本文中我所描述的多代理系统由运行在消费级电脑上的小型模型驱动，但它可以解决与复杂查询相关的多跳问答任务。特别是：
- 它可以将查询分解为可管理的子任务；
- 它可以识别包含必要信息的维基百科页面；
- 它可以组合来自多个页面的信息；
- 它可以在维基百科页面上搜索详细信息；
- 它可以确定是否需要更多信息并尝试找到它；
- 它可以成功修复它生成的代码中的小错误并处理工具错误（如维基百科消歧错误）。
另一方面，本文中我还概述了所构建系统的一些局限性，例如增加计算时间、重复动作和潜在的幻觉传播。后者可以通过在系统中包含一个“校对”代理来缓解，该代理负责检查报告的信息是否与检索到的信息源一致。
还值得注意的是，由于代理系统的核心是标准的RAG方法，因此可以在框架中实现所有用于提高后者效率和准确性的常用技术。
另一个可能的改进是使用技术来增加测试时间计算，使模型有更多“思考时间”，类似于OpenAI o1/o3模型。但需要注意的是，这种修改将进一步增加执行时间。
最后，由于多代理系统由专门从事单一任务的代理组成，因此为每个代理使用不同的模型引擎可以提高性能。特别是，可以为系统中的每个任务微调不同的模型以进一步提高性能。这对小模型尤其有益。值得一提的是，可以通过在一组预定任务上运行系统并在系统产生正确答案时保存代理的输出来收集微调数据，从而无需昂贵的手动数据注释。
好了，我希望你发现本文非常有用，你可以在GitHub存储库中找到文中项目完整的代码实现，并在Colab笔记本中亲自尝试一下。
译者介绍
朱先忠，51CTO社区编辑，51CTO专家博客、讲师，潍坊一所高校计算机教师，自由编程界老兵一枚。
原文标题：Multi-Agentic RAG withHugging FaceCode Agents，作者：Gabriele Sgroi
