Load Hatena Blog posts into LlamaIndex for RAG

Hatena Blog Loader retrieves article content from your personal Hatena Blog using the AtomPub API and converts it into documents for LlamaIndex.

Use this loader when you need to load your own Hatena Blog content into LlamaIndex applications. You can get AtomPub credentials from the admin page after logging into Hatena Blog.

Do NOT use this loader if you need to fetch content from other people's blogs, as it requires AtomPub credentials from your own Hatena Blog admin page.

You provide three authentication parameters: your AtomPub root endpoint, API key, and Hatena Blog username. All credentials are obtained from the Hatena Blog admin page after logging in.

The loader returns a collection of LlamaIndex documents containing your blog post content.

This loader integrates with LlamaIndex, the data framework for building LLM applications. It's specifically designed as a data reader component within the LlamaIndex ecosystem.

It connects to Hatena Blog via the AtomPub API, the standard protocol for publishing and editing web resources on the Hatena blogging platform.

Install the package:

pip install llama-index-readers-hatena-blog

Basic implementation:

import os

from llama_index.readers.hatena_blog import HatenaBlogReader

root_endpoint = os.getenv("ATOM_PUB_ROOT_ENDPOINT")
api_key = os.getenv("ATOM_PUB_API_KEY")
username = os.getenv("HATENA_BLOG_USERNAME")

reader = HatenaBlogReader(
    root_endpoint=root_endpoint, api_key=api_key, username=username
)
documents = reader.load_data()

This loader serves Hatena Blog authors who want to load their published content into LlamaIndex applications.