The problem
A model may remember a topic from training, but that is not the same as reading the current Wikipedia article. Without a retrieval tool it cannot check a revision, quote the page it actually saw, or reliably separate article text from navigation and page furniture.
How NativePort helps
NativePort gives your agent access to Jina Reader, which opens the article and returns a readable version. You can keep that text with the source link and let the agent answer from it. Wikipedia is already public; the benefit here is convenient retrieval and cleaner input.
Technical implementation
Use Python 3 with requests installed (python -m pip install requests). Set NATIVEPORT_API_KEY in your environment to your NativePort key. Run the snippets on your server, where your key stays private.
Set ARTICLE_URL to a full Wikipedia article URL.
import os
import requests
BASE = "https://api.nativeport.ai"
HEADERS = {"Authorization": f"Bearer {os.environ['NATIVEPORT_API_KEY']}"}
article_url = os.environ["ARTICLE_URL"]
response = requests.get(BASE + "/jina/reader/" + article_url,
headers=HEADERS, timeout=90)
response.raise_for_status()
print("Source:", article_url)
print(response.text)Pass the returned text and source URL together to your model. Keep the retrieval date if you need to reproduce an answer later.
Tool costs
| Tool used in the example | Price per call |
|---|---|
| Jina Reader | $0.0000211 / 1,000 tokens (usage-based) |
Prices in USD. Usage-based tools have no fixed per-call price. View pricing.
Let your agent build it
You don’t need to write this code yourself. Copy this page’s link and paste it into your agent. Ask it to follow the guide and implement the feature for you.