---
title: "Wikipedia Agent"
description: "Wikipedia data retrieval tools for AI agents."
icon: "book"
---

<Note>
  **Prerequisites**
  - Python 3.10 or higher
  - PraisonAI Agents package installed
  - `wikipedia` package installed
  - Basic understanding of Wikipedia APIs
</Note>

## Wikipedia Tools

Use Wikipedia Tools to retrieve and analyze Wikipedia content with AI agents.

<Steps>
  <Step title="Install Dependencies">
    First, install the required packages:
    ```bash
    pip install praisonaiagents wikipedia
    ```
  </Step>

  <Step title="Import Components">
    Import the necessary components:
    ```python
    from praisonaiagents import Agent, Task, PraisonAIAgents
    from praisonaiagents.tools import wiki_search, wiki_summary, wiki_page, wiki_random, wiki_language
    ```
  </Step>

  <Step title="Create Agent">
    Create a Wikipedia research agent:
    ```python
    wiki_agent = Agent(
        name="WikiResearcher",
        role="Wikipedia Research Specialist",
        goal="Research and analyze Wikipedia content efficiently.",
        backstory="Expert in information retrieval and content analysis.",
        tools=[wiki_search, wiki_summary, wiki_page, wiki_random, wiki_language],
        self_reflect=False
    )
    ```
  </Step>

  <Step title="Define Task">
    Define the research task:
    ```python
    research_task = Task(
        description="Research historical events and gather information.",
        expected_output="Comprehensive research summary with citations.",
        agent=wiki_agent,
        name="historical_research"
    )
    ```
  </Step>

  <Step title="Run Agent">
    Initialize and run the agent:
    ```python
    agents = PraisonAIAgents(
        agents=[wiki_agent],
        tasks=[research_task],
        process="sequential"
    )
    agents.start()
    ```
  </Step>
</Steps>

## Understanding Wikipedia Tools

<Card title="What are Wikipedia Tools?" icon="question">
  Wikipedia Tools provide research capabilities for AI agents:
  - Article search and retrieval
  - Content summary generation
  - Full page information access
  - Random article discovery
  - Multi-language support
</Card>

## Key Components

<CardGroup cols={2}>
  <Card title="Wiki Agent" icon="user-robot">
    Create specialized research agents:
    ```python
    Agent(tools=[wiki_search, wiki_summary, wiki_page, wiki_random, wiki_language])
    ```
  </Card>
  <Card title="Wiki Task" icon="list-check">
    Define research tasks:
    ```python
    Task(description="wiki_query")
    ```
  </Card>
  <Card title="Process Types" icon="arrows-split-up-and-left">
    Sequential or parallel processing:
    ```python
    process="sequential"
    ```
  </Card>
  <Card title="Wiki Options" icon="sliders">
    Customize search parameters:
    ```python
    language="en", sentences=3
    ```
  </Card>
</CardGroup>

## Examples

### Basic Wikipedia Research Agent

```python
from praisonaiagents import Agent, Task, PraisonAIAgents
from praisonaiagents.tools import wiki_search, wiki_summary, wiki_page, wiki_random, wiki_language

# Create Wikipedia agent
wiki_agent = Agent(
    name="WikiExpert",
    role="Research Specialist",
    goal="Research topics efficiently and accurately.",
    backstory="Expert in information gathering and analysis.",
    tools=[wiki_search, wiki_summary, wiki_page, wiki_random, wiki_language],
    self_reflect=False
)

# Define research task
research_task = Task(
    description="Research scientific discoveries and breakthroughs.",
    expected_output="Detailed research report with references.",
    agent=wiki_agent,
    name="science_research"
)

# Run agent
agents = PraisonAIAgents(
    agents=[wiki_agent],
    tasks=[research_task],
    process="sequential"
)
agents.start()

```

### Advanced Research with Multiple Agents

```python
# Create research agent
researcher_agent = Agent(
    name="Researcher",
    role="Content Researcher",
    goal="Research topics systematically.",
    tools=[wiki_search, wiki_summary, wiki_page],
    self_reflect=False
)

# Create analysis agent
analysis_agent = Agent(
    name="Analyzer",
    role="Content Analyst",
    goal="Analyze and summarize research findings.",
    backstory="Expert in content analysis and synthesis.",
    tools=[wiki_summary, wiki_page],
    self_reflect=False
)

# Define tasks
research_task = Task(
    description="Research technological advancements.",
    agent=researcher_agent,
    name="tech_research"
)

analysis_task = Task(
    description="Analyze and synthesize research findings.",
    agent=analysis_agent,
    name="content_analysis"
)

# Run agents
agents = PraisonAIAgents(
    agents=[researcher_agent, analysis_agent],
    tasks=[research_task, analysis_task],
    process="sequential"
)
agents.start()
```

## Best Practices

<AccordionGroup>
  <Accordion title="Agent Configuration">
    Configure agents with clear research focus:
    ```python
    Agent(
        name="WikiResearcher",
        role="Research Specialist",
        goal="Research topics accurately and efficiently",
        tools=[wiki_search, wiki_summary, wiki_page, wiki_random, wiki_language]
    )
    ```
  </Accordion>

  <Accordion title="Task Definition">
    Define specific research objectives:
    ```python
    Task(
        description="Research historical events and gather sources",
        expected_output="Detailed research summary"
    )
    ```
  </Accordion>
</AccordionGroup>

## Common Patterns

### Research Pipeline
```python
# Research agent
researcher = Agent(
    name="Researcher",
    role="Wiki Researcher",
    tools=[wiki_search, wiki_summary, wiki_page]
)

# Analysis agent
analyzer = Agent(
    name="Analyzer",
    role="Content Analyzer",
    tools=[wiki_summary, wiki_page]
)

# Define tasks
research_task = Task(
    description="Research topic",
    agent=researcher
)

analyze_task = Task(
    description="Analyze findings",
    agent=analyzer
)

# Run workflow
agents = PraisonAIAgents(
    agents=[researcher, analyzer],
    tasks=[research_task, analyze_task]
)