ReActAgent - 计算器工具入门简介¶

这是一个展示 ReAct 智能体如何通过简单计算器工具（无需复杂的 RAG 管道或 API 调用）运作的笔记本。

我们将演示该智能体如何逐步推理，运用不同工具来实现最终目标。

相比函数调用型智能体，ReAct 智能体的主要优势在于：它能兼容任何大语言模型，无论该模型是否支持函数调用功能。

如果您在 Colab 上打开此 Notebook，可能需要安装 LlamaIndex 🦙。

In [ ]:

%pip install llama-index

%pip install llama-index

In [ ]:

import os

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

import os os.environ["OPENAI_API_KEY"] = "sk-..."

定义函数工具¶

我们设置了一些简单的 multiply（乘法）和 add（加法）工具。请注意，您可以定义任意函数并将其传递给 FunctionTool（该工具会自动处理函数的文档字符串和参数签名）。

In [ ]:

def multiply(a: int, b: int) -> int:
    """Multiply two integers and returns the result integer"""
    return a * b


def add(a: int, b: int) -> int:
    """Add two integers and returns the result integer"""
    return a + b

def multiply(a: int, b: int) -> int: """Multiply two integers and returns the result integer""" return a * b def add(a: int, b: int) -> int: """Add two integers and returns the result integer""" return a + b

执行查询¶

In [ ]:

from llama_index.llms.openai import OpenAI
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context

llm = OpenAI(model="gpt-4o-mini")
agent = ReActAgent(tools=[multiply, add], llm=llm)

# Create a context to store the conversation history/session state
ctx = Context(agent)

from llama_index.llms.openai import OpenAI from llama_index.core.agent.workflow import ReActAgent from llama_index.core.workflow import Context llm = OpenAI(model="gpt-4o-mini") agent = ReActAgent(tools=[multiply, add], llm=llm) # Create a context to store the conversation history/session state ctx = Context(agent)

运行示例查询¶

通过流式传输结果，我们可以查看完整响应，包括思考过程和工具调用记录。

若只需流式传输最终结果，我们可以在响应中出现 Answer: 时开始缓冲流数据并输出。

In [ ]:

from llama_index.core.agent.workflow import AgentStream, ToolCallResult

handler = agent.run("What is 20+(2*4)?", ctx=ctx)

async for ev in handler.stream_events():
    # if isinstance(ev, ToolCallResult):
    #     print(f"\nCall {ev.tool_name} with {ev.tool_kwargs}\nReturned: {ev.tool_output}")
    if isinstance(ev, AgentStream):
        print(f"{ev.delta}", end="", flush=True)

response = await handler

from llama_index.core.agent.workflow import AgentStream, ToolCallResult handler = agent.run("What is 20+(2*4)?", ctx=ctx) async for ev in handler.stream_events(): # if isinstance(ev, ToolCallResult): # print(f"\nCall {ev.tool_name} with {ev.tool_kwargs}\nReturned: {ev.tool_output}") if isinstance(ev, AgentStream): print(f"{ev.delta}", end="", flush=True) response = await handler

Thought: The current language of the user is: English. I need to use a tool to help me answer the question.
Action: multiply
Action Input: {"a": 2, "b": 4}Thought: Now I have the result of the multiplication, which is 8. I will add this to 20 to complete the calculation.
Action: add
Action Input: {'a': 20, 'b': 8}Thought: I can answer without using any more tools. I'll use the user's language to answer.
Answer: The result of 20 + (2 * 4) is 28.

In [ ]:

print(str(response))

print(str(response))

The result of 20 + (2 * 4) is 28.

In [ ]:

print(response.tool_calls)

print(response.tool_calls)

[ToolCallResult(tool_name='multiply', tool_kwargs={'a': 2, 'b': 4}, tool_id='a394d807-a9b7-42e0-8bff-f47a432d1530', tool_output=ToolOutput(content='8', tool_name='multiply', raw_input={'args': (), 'kwargs': {'a': 2, 'b': 4}}, raw_output=8, is_error=False), return_direct=False), ToolCallResult(tool_name='add', tool_kwargs={'a': 20, 'b': 8}, tool_id='784ccd85-ae9a-4184-9613-3696742064c7', tool_output=ToolOutput(content='28', tool_name='add', raw_input={'args': (), 'kwargs': {'a': 20, 'b': 8}}, raw_output=28, is_error=False), return_direct=False)]

查看提示词¶

让我们来看看驱动 ReAct 智能体的核心系统提示词！

在智能体内部，当前对话历史会转储在这行下方。

In [ ]:

prompt_dict = agent.get_prompts()
for k, v in prompt_dict.items():
    print(f"Prompt: {k}\n\nValue: {v.template}")

prompt_dict = agent.get_prompts() for k, v in prompt_dict.items(): print(f"Prompt: {k}\n\nValue: {v.template}")

Prompt: react_header

Value: You are designed to help with a variety of tasks, from answering questions to providing summaries to other types of analyses.

## Tools

You have access to a wide variety of tools. You are responsible for using the tools in any sequence you deem appropriate to complete the task at hand.
This may require breaking the task into subtasks and using different tools to complete each subtask.

You have access to the following tools:
{tool_desc}


## Output Format

Please answer in the same language as the question and use the following format:

```
Thought: The current language of the user is: (user's language). I need to use a tool to help me answer the question.
Action: tool name (one of {tool_names}) if using a tool.
Action Input: the input to the tool, in a JSON format representing the kwargs (e.g. {{"input": "hello world", "num_beams": 5}})
```

Please ALWAYS start with a Thought.

NEVER surround your response with markdown code markers. You may use code markers within your response if you need to.

Please use a valid JSON format for the Action Input. Do NOT do this {{'input': 'hello world', 'num_beams': 5}}.

If this format is used, the tool will respond in the following format:

```
Observation: tool response
```

You should keep repeating the above format till you have enough information to answer the question without using any more tools. At that point, you MUST respond in one of the following two formats:

```
Thought: I can answer without using any more tools. I'll use the user's language to answer
Answer: [your answer here (In the same language as the user's question)]
```

```
Thought: I cannot answer the question with the provided tools.
Answer: [your answer here (In the same language as the user's question)]
```

## Current Conversation

Below is the current conversation consisting of interleaving human and assistant messages.

自定义提示词¶

作为趣味尝试，我们可以指示智能体以项目符号列表的形式输出答案及推理过程。具体请参阅"## 附加规则"章节。

In [ ]:

from llama_index.core import PromptTemplate

react_system_header_str = """\

You are designed to help with a variety of tasks, from answering questions \
    to providing summaries to other types of analyses.

## Tools
You have access to a wide variety of tools. You are responsible for using
the tools in any sequence you deem appropriate to complete the task at hand.
This may require breaking the task into subtasks and using different tools
to complete each subtask.

You have access to the following tools:
{tool_desc}

## Output Format
To answer the question, please use the following format.

```
Thought: I need to use a tool to help me answer the question.
Action: tool name (one of {tool_names}) if using a tool.
Action Input: the input to the tool, in a JSON format representing the kwargs (e.g. {{"input": "hello world", "num_beams": 5}})
```

Please ALWAYS start with a Thought.

Please use a valid JSON format for the Action Input. Do NOT do this {{'input': 'hello world', 'num_beams': 5}}.

If this format is used, the user will respond in the following format:

```
Observation: tool response
```

You should keep repeating the above format until you have enough information
to answer the question without using any more tools. At that point, you MUST respond
in the one of the following two formats:

```
Thought: I can answer without using any more tools.
Answer: [your answer here]
```

```
Thought: I cannot answer the question with the provided tools.
Answer: Sorry, I cannot answer your query.
```

## Additional Rules
- The answer MUST contain a sequence of bullet points that explain how you arrived at the answer. This can include aspects of the previous conversation history.
- You MUST obey the function signature of each tool. Do NOT pass in no arguments if the function expects arguments.

## Current Conversation
Below is the current conversation consisting of interleaving human and assistant messages.

"""
react_system_prompt = PromptTemplate(react_system_header_str)

from llama_index.core import PromptTemplate react_system_header_str = """\ You are designed to help with a variety of tasks, from answering questions \ to providing summaries to other types of analyses. ## Tools You have access to a wide variety of tools. You are responsible for using the tools in any sequence you deem appropriate to complete the task at hand. This may require breaking the task into subtasks and using different tools to complete each subtask. You have access to the following tools: {tool_desc} ## Output Format To answer the question, please use the following format. ``` Thought: I need to use a tool to help me answer the question. Action: tool name (one of {tool_names}) if using a tool. Action Input: the input to the tool, in a JSON format representing the kwargs (e.g. {{"input": "hello world", "num_beams": 5}}) ``` Please ALWAYS start with a Thought. Please use a valid JSON format for the Action Input. Do NOT do this {{'input': 'hello world', 'num_beams': 5}}. If this format is used, the user will respond in the following format: ``` Observation: tool response ``` You should keep repeating the above format until you have enough information to answer the question without using any more tools. At that point, you MUST respond in the one of the following two formats: ``` Thought: I can answer without using any more tools. Answer: [your answer here] ``` ``` Thought: I cannot answer the question with the provided tools. Answer: Sorry, I cannot answer your query. ``` ## Additional Rules - The answer MUST contain a sequence of bullet points that explain how you arrived at the answer. This can include aspects of the previous conversation history. - You MUST obey the function signature of each tool. Do NOT pass in no arguments if the function expects arguments. ## Current Conversation Below is the current conversation consisting of interleaving human and assistant messages. """ react_system_prompt = PromptTemplate(react_system_header_str)

In [ ]:

agent.get_prompts()

agent.get_prompts()

Out[ ]:

{'react_header': PromptTemplate(metadata={'prompt_type': <PromptType.CUSTOM: 'custom'>}, template_vars=['tool_desc', 'tool_names'], kwargs={}, output_parser=None, template_var_mappings=None, function_mappings=None, template='You are designed to help with a variety of tasks, from answering questions to providing summaries to other types of analyses.\n\n## Tools\n\nYou have access to a wide variety of tools. You are responsible for using the 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 to complete each subtask.\n\nYou have access to the following tools:\n{tool_desc}\n\n\n## Output Format\n\nPlease answer in the same language as the question and use the following format:\n\n```\nThought: The current language of the user is: (user\'s language). I need to use a tool to help me answer the question.\nAction: tool name (one of {tool_names}) 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\nNEVER surround your response with markdown code markers. You may use code markers within your response if you need to.\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 tool will respond in the following format:\n\n```\nObservation: tool response\n```\n\nYou should keep repeating the above format till you have enough information to answer the question without using any more tools. At that point, you MUST respond in one of the following two formats:\n\n```\nThought: I can answer without using any more tools. I\'ll use the user\'s language to answer\nAnswer: [your answer here (In the same language as the user\'s question)]\n```\n\n```\nThought: I cannot answer the question with the provided tools.\nAnswer: [your answer here (In the same language as the user\'s question)]\n```\n\n## Current Conversation\n\nBelow is the current conversation consisting of interleaving human and assistant messages.\n')}

In [ ]:

agent.update_prompts({"react_header": react_system_prompt})

agent.update_prompts({"react_header": react_system_prompt})

In [ ]:

handler = agent.run("What is 5+3+2")

async for ev in handler.stream_events():
    # if isinstance(ev, ToolCallResult):
    #     print(f"\nCall {ev.tool_name} with {ev.tool_kwargs}\nReturned: {ev.tool_output}")
    if isinstance(ev, AgentStream):
        print(f"{ev.delta}", end="", flush=True)

response = await handler

handler = agent.run("What is 5+3+2") async for ev in handler.stream_events(): # if isinstance(ev, ToolCallResult): # print(f"\nCall {ev.tool_name} with {ev.tool_kwargs}\nReturned: {ev.tool_output}") if isinstance(ev, AgentStream): print(f"{ev.delta}", end="", flush=True) response = await handler

Thought: The current language of the user is: English. I need to use a tool to help me answer the question.
Action: add
Action Input: {"a": 5, "b": 3}Thought: I need to add the result (8) to the remaining number (2).
Action: add
Action Input: {'a': 8, 'b': 2}Thought: I can answer without using any more tools. I'll use the user's language to answer.
Answer: The result of 5 + 3 + 2 is 10.

In [ ]:

print(response)

print(response)

The result of 5 + 3 + 2 is 10.