Jina Reader

Convert URLs to LLM-friendly content with Jina Reader API

Jina Reader lets an agent turn any URL into clean, LLM-ready text.

Diagram

Overview

Jina Reader API converts any URL into clean, LLM-ready text. It handles JavaScript rendering, removes ads, and extracts the main content.

Installation

bash

pip install "praisonai[tools]"

Environment Variables

bash

export JINA_API_KEY="${JINA_API_KEY:?Set JINA_API_KEY in your shell}"  # Optional - works without key with limits

Get your API key from Jina AI.

How It Works

Diagram

Quick Start

Simple Usage

python

from praisonai_tools import JinaTool

# Initialize
jina = JinaTool()

# Read a URL
content = jina.read("https://example.com")
print(content)

With Configuration
Use the same tool with an agent — see Usage with Agent below, or pass env vars and options from the sections above.

Usage with Agent

python

from praisonaiagents import Agent
from praisonai_tools import JinaTool

agent = Agent(
    name="Reader",
    instructions="You are a content reader. Use Jina to extract content from URLs.",
    tools=[JinaTool()]
)

response = agent.chat("Read the content from https://praison.ai/docs")
print(response)

Available Methods

read(url)

Read and extract content from a URL.

python

from praisonai_tools import JinaTool

jina = JinaTool()
result = jina.read("https://example.com/article")

# Returns:
# {
#     "url": "https://example.com/article",
#     "title": "Article Title",
#     "content": "Clean extracted content...",
#     "description": "..."
# }

search(query)

Search the web and get content.

python

results = jina.search("Python best practices")

Configuration Options

python

jina = JinaTool(
    api_key="your_key",    # Optional: defaults to JINA_API_KEY
    timeout=30             # Request timeout in seconds
)

Function-Based Usage

python

from praisonai_tools import jina_read

# Quick read without instantiating class
content = jina_read("https://example.com")

CLI Usage

bash

# Use with praisonai (works without API key)
praisonai --tools JinaTool "Read the content from https://example.com"

Error Handling

python

from praisonai_tools import JinaTool

jina = JinaTool()
result = jina.read("https://example.com")

if "error" in result:
    print(f"Error: {result['error']}")
else:
    print(f"Title: {result['title']}")
    print(f"Content: {result['content'][:500]}")

Common Errors

Error	Cause	Solution
`Connection error`	Network issue	Check internet connection
`Timeout`	Page took too long	Increase timeout or try later
`Rate limited`	Too many requests	Add API key or add delays