> ## Documentation Index
> Fetch the complete documentation index at: https://thethirdpenco-feat-tool-lifecycle-events.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Wikipedia Agent

> Research agent that searches and summarizes Wikipedia

This example demonstrates building a research agent that can search Wikipedia and summarize articles.

## Features

* Async tool for Wikipedia API calls
* Multi-step research workflow
* Streaming output for real-time feedback

## Complete Code

```python theme={null}
import asyncio
import aiohttp
from ai_query import stream_text
from ai_query.providers import google, tool, Field

@tool(description="Search Wikipedia for articles matching a query")
async def search_wikipedia(
    query: str = Field(description="The search query")
) -> str:
    """Search Wikipedia and return article titles."""
    url = "https://en.wikipedia.org/w/api.php"
    params = {
        "action": "query",
        "list": "search",
        "srsearch": query,
        "format": "json",
        "srlimit": 5
    }

    async with aiohttp.ClientSession() as session:
        async with session.get(url, params=params) as response:
            data = await response.json()
            results = data.get("query", {}).get("search", [])

            if not results:
                return f"No results found for '{query}'"

            titles = [r["title"] for r in results]
            return f"Found articles: {', '.join(titles)}"

@tool(description="Get the content of a Wikipedia article")
async def get_article(
    title: str = Field(description="The exact article title")
) -> str:
    """Fetch the introduction of a Wikipedia article."""
    url = "https://en.wikipedia.org/w/api.php"
    params = {
        "action": "query",
        "titles": title,
        "prop": "extracts",
        "exintro": True,
        "explaintext": True,
        "format": "json"
    }

    async with aiohttp.ClientSession() as session:
        async with session.get(url, params=params) as response:
            data = await response.json()
            pages = data.get("query", {}).get("pages", {})

            for page in pages.values():
                extract = page.get("extract", "")
                if extract:
                    # Truncate to avoid token limits
                    return extract[:2000]

            return f"Could not find article: {title}"

async def main():
    print("Wikipedia Research Agent")
    print("=" * 40)

    result = stream_text(
        model=google("gemini-2.0-flash"),
        system="""You are a research assistant. When asked about a topic:
        1. Search Wikipedia for relevant articles
        2. Read the most relevant article(s)
        3. Provide a comprehensive summary""",
        prompt="Tell me about the history of Python programming language",
        tools={
            "search_wikipedia": search_wikipedia,
            "get_article": get_article
        }
    )

    async for chunk in result.text_stream:
        print(chunk, end="", flush=True)

    usage = await result.usage
    print(f"\n\n[Tokens used: {usage.total_tokens}]")

if __name__ == "__main__":
    asyncio.run(main())
```

## How It Works

1. **User asks a question** - "Tell me about the history of Python"

2. **AI searches Wikipedia** - Calls `search_wikipedia("Python programming language")`

3. **AI reads articles** - Calls `get_article("Python (programming language)")`

4. **AI summarizes** - Generates a comprehensive response based on the article content

## Sample Output

```
Wikipedia Research Agent
========================================
Let me research that for you...

Python is a high-level, general-purpose programming language created by
Guido van Rossum and first released in 1991. Here's a summary of its history:

**Origins (late 1980s)**
Python was conceived in the late 1980s by Guido van Rossum at Centrum
Wiskunde & Informatica (CWI) in the Netherlands as a successor to the
ABC programming language...

**Key Milestones:**
- 1991: Python 0.9.0 released
- 2000: Python 2.0 released with list comprehensions
- 2008: Python 3.0 released (major revision)
- 2020: Python 2 officially discontinued

[Tokens used: 1523]
```

## Customization Ideas

<AccordionGroup>
  <Accordion title="Add more research tools">
    Add tools for other APIs like news search, academic papers, or documentation.
  </Accordion>

  <Accordion title="Save research results">
    Add a tool to save summaries to files or a database.
  </Accordion>

  <Accordion title="Interactive mode">
    Wrap in a loop to allow follow-up questions about the research.
  </Accordion>
</AccordionGroup>