llama-index-readers-confluence

What it is and what it does

llama-index-readers-confluence is a LlamaIndex integration that fetches pages and attachments from Atlassian Confluence cloud instances and converts them into LlamaIndex Document objects. It handles authentication via OAuth 2.0, API tokens, cookies, or basic auth (username/API token), and supports querying pages by ID, space key, label, or Confluence Query Language (CQL). The loader can optionally extract text from attachments in PDF, PNG, JPEG, SVG, Word, and Excel formats, adding the extracted content to the document metadata.

The package provides advanced features including custom parsers for attachment types, processing callbacks to filter documents and attachments, event monitoring through LlamaIndex's instrumentation system, and configurable error handling. It depends on atlassian-python-api for API communication and uses specialized libraries (pdf2image, pytesseract, pillow, docx2txt, markdownify, xlrd, svglib) to extract text from different file formats.

Use it for:

• Ingest Confluence documentation into a RAG pipeline for semantic search and question-answering over internal knowledge bases
• Migrate Confluence content to a vector database for AI-powered knowledge retrieval systems
• Build automated documentation processors that extract and transform Confluence pages for downstream analysis
• Create backup and archival systems that convert Confluence spaces into structured document collections
• Integrate Confluence as a data source for LlamaIndex-based AI agents that need access to organizational documentation

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Loads pages and attachments from Confluence cloud instances into LlamaIndex documents, supporting multiple query methods and file type extraction.

Yes. The package is actively maintained, has low install friction, carries no known vulnerabilities, and uses a permissive MIT license. Install it if you need to load Confluence pages into LlamaIndex for RAG, search, or documentation processing workflows. The attachment extraction and advanced configuration options add value for complex use cases.

Install

llama-index-readers-confluence on PyPI

pip install llama-index-readers-confluence

uv add llama-index-readers-confluence

poetry add llama-index-readers-confluence

Installing llama-index-readers-confluence

Before you install

Low install friction with a pure-Python wheel distribution. Actively maintained as of the latest release.

License in practice

MIT license permits commercial and private use with minimal restrictions.

Quickstart

from llama_index.readers.confluence import ConfluenceReader

reader = ConfluenceReader(
    base_url="https://yoursite.atlassian.com/wiki",
    api_token="your_token"
)
documents = reader.load_data(space_key="SPACE_KEY")

Requires Python 3.10 or later; Confluence base URL must end with `/wiki`; API token or environment variables (CONFLUENCE_API_TOKEN or CONFLUENCE_USERNAME/CONFLUENCE_PASSWORD) needed for authentication.

Verify before relying

• Performance characteristics when processing large numbers of pages or attachments
• Completeness of text extraction from supported attachment types (PDF, PNG, JPEG, SVG, Word, Excel)
• Whether custom parsers can be extended beyond the documented file types

Package facts

Evidence: llama_index_readers_confluence-0.7.0-py3-none-any.whl

Tags

More Text Processing packages