AI Agent Q&A Example

In this chapter, we will build our first real AI Agent.

We'll start with a simple Q&A Agent and gradually add more features.

Project Structure Preparation

First, create the directoryexample-ai-agent：

mkdir example-ai-agent

Enter the directoryexample-ai-agent, and use the uv command to create a virtual environment:

cd example-ai-agent

# 创建名为 .venv 的虚拟环境（默认）
uv venv

# 激活环境（macOS/Linux）
source .venv/bin/activate

# 激活环境（Windows）
.venv\Scripts\activate

Use uv to create and activate a virtual environment. For more details, you can readthe uv tutorial。

Create the project directory structure:

example-ai-agent/
├── .env
├── .gitignore
├── requirements.txt
├── test_basic_agent.py
├── README.md
├── src/
│   ├── __init__.py
│   └── simple_agent.py
└── tests/
    └── __init__.py

Apply for API Key on Alibaba Bailian

This chapter requires the search feature, so we use the Alibaba Qwen model because it has built-in search functionality.

The Tongyi Qianwen model on Alibaba Cloud Bailian supports OpenAI-compatible APIs. You only need to adjust the API Key, BASE_URL, and model name to migrate your existing OpenAI code to Alibaba Cloud Bailian.

  • base_url: Replace with https://dashscope.aliyuncs.com/compatible-mode/v1
  • api_key: Replace with your Alibaba Cloud Bailian API Key
  • model: Replace with qwen3-max

Reference link:https://help.aliyun.com/zh/model-studio/compatibility-of-openai-with-dashscope

We need to activate the Alibaba Cloud Bailian model service and obtain an API-KEY.

First, use your Alibaba Cloud main account to access the Bailian Model Studio platform:https://bailian.console.aliyun.com/, then click Login in the top-right corner. After logging in, click the gear ⚙️ icon in the top-right corner, select API key, and copy it. If you don't have one, you can also create an API key:

Activating Alibaba Cloud Bailian does not incur any fees. Charges only apply to model calls (after exceeding the free quota), model deployment, and model fine-tuning.

] APIs are now billed by token. Fortunately, the prices are quite affordable, so we can start by purchasing the cheapest package:Alibaba Cloud Bailian Large Model Service Platform。

You can also directly use the Coding Plan package from Bailian and Ark:https://www.example.com/claude-code/coding-plan.html。

Create the basic Agent class:

Example

# src/simple_agent.py
import os
from typing import List, Dict, Any
from openai import OpenAI
from dotenv import load_dotenv

# Load environment variables
load_dotenv()

class SimpleQAAgent:
    """Simple Q&A Agent"""

    def __init__(self, model: str = "qwen3-max"): # Set default model to DeepSeek
        """
Initialize Agent

        Args:
model: The model name to use, defaults to DeepSeek
        """
        # api_key = os.getenv("OPENAI_API_KEY")
        api_key = "sk-xxx" # Your API key
        base_url = "https://dashscope.aliyuncs.com/compatible-mode/v1"
        if not api_key:
            raise ValueError("Please set the OPENAI_API_KEY environment variable")

        self.client = OpenAI(
                        api_key = api_key,
                        base_url = base_url)
        self.model = model
        self.conversation_history: List[Dict[str, str]] = []
        self.system_prompt = "You are a helpful AI assistant. Please answer user questions politely and accurately."

    def add_to_history(self, role: str, content: str):
        """Add message to conversation history"""
        self.conversation_history.append({
            "role": role,
            "content": content
        })

        # Keep history length within 10 turns (to prevent token overflow)
        if len(self.conversation_history) > 10:
            self.conversation_history = self.conversation_history[-10:]

    def ask(self, question: str) -> str:
        """
Ask the Agent a question

        Args:
question: The user's question

        Returns:
The Agent's answer
        """
        # Add user question to history
        self.add_to_history("user", question)

        # Prepare message list
        messages = [
            {"role": "system", "content": self.system_prompt}
        ]
        messages.extend(self.conversation_history)

        try:
            # Call OpenAI API
            response = self.client.chat.completions.create(
                model=self.model,
                messages=messages,
                temperature=0.7,
                max_tokens=500
            )

            # Extract answer
            answer = response.choices[0].message.content

            # Add assistant answer to history
            self.add_to_history("assistant", answer)

            return answer

        except Exception as e:
            error_msg = f"Error calling API: {str(e)}"
            print(error_msg)
            return error_msg

    def clear_history(self):
        """Clear conversation history"""
        self.conversation_history.clear()

Create a test script to test the basic Agent:

Example

# test_basic_agent.py
from src.simple_agent import SimpleQAAgent

def test_basic_agent():
    """Test basic Q&A Agent"""
    print("=== Test Basic Q&A Agent ===")

    # Create Agent
    agent = SimpleQAAgent()

    # Test Q&A
    questions = [
        "Hello, please introduce yourself",
        "What is Python?",
        "What is the difference between machine learning and artificial intelligence?"
    ]

    for question in questions:
        print(f"\nUser: {question}")
        answer = agent.ask(question)
        print(f"Assistant: {answer}")

    # Test conversation coherence
    print("\n=== Test Conversation Coherence ===")
    agent.clear_history()

    # First round
    q1 = "My favorite color is blue"
    a1 = agent.ask(q1)
    print(f"User: {q1}")
    print(f"Assistant: {a1}")

    # Second round (should remember the previous conversation)
    q2 = "What color did I just say is my favorite?"
    a2 = agent.ask(q2)
    print(f"\nUser: {q2}")
    print(f"Assistant: {a2}")

    print("\nTest complete!")

if __name__ == "__main__":
    test_basic_agent()

Run the test:

python test_basic_agent.py

=== 测试基础问答 Agent ===

User: 你好，请介绍一下自己
example
助理: 你好！我是通义千问（Qwen），是阿里巴巴集团自主研发的超大规模语言模型。我可以帮助你回答问题、创作文字，比如写故事、写公文、写邮件、写剧本、逻辑推理、编程等等，还能表达观点，玩游戏等。如果你有任何问题或需要帮助，随时告诉我！

User: Python是什么？
助理: 你好！Python 是一种**高级、解释型、通用的编程语言**，由荷兰程序员 **吉多·范罗苏姆（Guido van Rossum）** 于1991年首次发布。它的设计哲学强调代码的**可读性**和**简洁性**，语法清晰简洁，使得初学者也能快速上手。
...

This basic Agent has several obvious limitations:

  • Can only answer from knowledge in the training data
  • Cannot access real-time information
  • Cannot perform calculations
  • Cannot operate external systems

This is exactly why we need to add tools to the Agent.

Add Search Tool

Qwen has built-in search functionality, passingenable_search: trueparameters can enable the web search feature.

# 导入依赖与创建客户端...
completion = client.chat.completions.create(
    # 需使用支持联网搜索的模型
    model="qwen3-max",
    messages=[{"role": "user", "content": "杭州明天天气如何"}],
    # 由于 enable_search 非 OpenAI 标准参数，使用 Python SDK 需要通过 extra_body 传入（使用Node.js SDK 需作为顶层参数传入）
    extra_body={"enable_search": True}
)

Documentation:https://help.aliyun.com/zh/model-studio/web-search

Agent with Integrated Search Tool

Now we integrate the search tool into the Agent. Create the agent_with_search.py file in the src directory:

Example

# src/agent_with_search.py
import os
from openai import OpenAI
from dotenv import load_dotenv

load_dotenv()


class AgentWithSearch:
    """Agent based on Qwen's built-in web search capability"""

    def __init__(self, model: str = "qwen3-max"):
        api_key = "sk-xxx"
        base_url = "https://dashscope.aliyuncs.com/compatible-mode/v1"

        if not api_key:
            raise ValueError("Please set the OPENAI_API_KEY environment variable (DashScope Key)")

        self.client = OpenAI(
            api_key=api_key,
            base_url=base_url
        )
        self.model = model

        self.system_prompt = """
You are a helpful AI assistant.

When the question involves real-time information, latest events, or content requiring fact-checking,
you can obtain the latest information through web search and state in your answers that the information comes from the internet.
"""

    def ask(self, question: str) -> str:
        messages = [
            {"role": "system", "content": self.system_prompt},
            {"role": "user", "content": question}
        ]

        try:
            response = self.client.chat.completions.create(
                model=self.model,
                messages=messages,
                temperature=0.7,
                max_tokens=800,
                extra_body={
                    "enable_search": True
                }
            )

            return response.choices[0].message.content

        except Exception as e:
            return f"Error: {repr(e)}"

    def interactive_chat(self):
        print("=== Qwen Web Search Agent ===")
        print("Enter quit / exit to end the conversation")

        while True:
            question = input("\n"You: ").strip()
            if question.lower() in {"quit", "exit"}:
                break

            print("Assistant:", self.ask(question))

Test Search Agent

Create the test_search_agent.py file in the root directory:

Example

# test_search_agent.py
from src.agent_with_search import AgentWithSearch

def test_search_agent():
    agent = AgentWithSearch()

    questions = [
        "What's the weather like in Beijing today?",
        "What is the latest technology news?",
        "Where was the 2024 Olympics held?",
        "What is Python?"
    ]

    for q in questions:
        print(f"\n"User: {q}")
        print("Assistant:", agent.ask(q)[:300], "...")

if __name__ == "__main__":
    test_search_agent()

Run the test:

python test_search_agent.py
User: 今天北京的天气怎么样？
助理: 今天是2026年2月7日，星期六。根据最新天气预报信息，北京今天的天气情况如下：

- **天气状况**：多云转晴  
- **气温范围**：最低气温约 **-9℃**，最高气温约 **2℃**（部分区域如海淀区记录为 **-5℃ ~ 5℃**）  
- **风向风力**：白天到夜间有 **东北风1级**，部分地区午后转为 **南风转西北风，小于3级**  
- **空气质量**：**37（优）**  
- **穿衣建议**：建议穿棉衣、冬大衣、皮夹克、厚呢外套、羽绒服等厚重保暖衣物，并佩戴手套、帽子等防寒配件  
...
Other extensions