Getting Started

Get up and running with WikiRest API in under 5 minutes.

Step 1: Get your API key

Create a free account to get your API key. No credit card required. The free tier includes 5,000 requests per month.

Step 2: Make your first request

Try searching Wikipedia with a simple cURL command:

curl -H "X-API-Key: YOUR_API_KEY" \
  "https://api.wikirest.com/v1/search?q=machine+learning&limit=3"

Step 3: Explore the response

You'll receive a JSON response with search results:

{
  "hits": [
    {
      "id": "12345_1",
      "page_id": 12345,
      "rev_id": 1234567890,
      "title": "Machine learning",
      "section": "Overview",
      "text": "Machine learning is a subset of artificial intelligence...",
      "chunk_id": 1,
      "url": "https://en.wikipedia.org/wiki/Machine_learning",
      "source": {
        "project": "en.wikipedia.org",
        "source_url": "https://en.wikipedia.org/wiki/Machine_learning",
        "permalink": "https://en.wikipedia.org/w/index.php?curid=12345&oldid=1234567890"
      },
      "license": {
        "name": "CC BY-SA 4.0",
        "url": "https://creativecommons.org/licenses/by-sa/4.0/"
      },
      "_formatted": {
        "text": "Machine learning is a subset of artificial intelligence..."
      }
    }
  ],
  "query": "machine learning",
  "processingTimeMs": 12,
  "estimatedTotalHits": 1543,
  "attribution": {
    "license": { "name": "CC BY-SA 4.0", "url": "..." },
    "attribution_notice": "Content derived from Wikipedia..."
  }
}

Understanding the response

Common use cases

RAG (Retrieval-Augmented Generation)

Use WikiRest to ground your LLM responses with factual Wikipedia content. The pre-chunked passages are optimized for context windows.

# Python example with OpenAI
import requests
import openai

# Search Wikipedia
wiki_response = requests.get(
    "https://api.wikirest.com/v1/search",
    headers={"X-API-Key": "YOUR_API_KEY"},
    params={"q": "quantum computing", "limit": 3}
).json()

# Build context from chunks
context = "\n\n".join([
    f"Source: {hit['title']}\n{hit['text']}"
    for hit in wiki_response["hits"]
])

# Use with OpenAI
response = openai.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "system", "content": f"Use this context:\n{context}"},
        {"role": "user", "content": "Explain quantum computing"}
    ]
)

Building a search interface

Create an instant Wikipedia search for your application:

// JavaScript
const searchWikipedia = async (query) => {
  const response = await fetch(
    `https://api.wikirest.com/v1/search?q=${encodeURIComponent(query)}&limit=10`,
    { headers: { "X-API-Key": "YOUR_API_KEY" } }
  );
  return response.json();
};

// Display results with highlighting
const results = await searchWikipedia("artificial intelligence");
results.hits.forEach(hit => {
  console.log(`${hit.title}: ${hit._formatted.text}`);
});

Next steps

• Authentication guide - Learn about API key management
• API Reference - Explore all endpoints
• Rate limiting - Understand usage limits
• Examples - Code samples in multiple languages