wiki-rag and WikiRag

These are competitors offering similar RAG pipelines over Wikipedia content, with the key technical difference being that moodlehq/wiki-rag targets arbitrary MediaWiki instances via API while MauroAndretta/WikiRag is specifically optimized for Wikipedia's knowledge base.

wiki-rag
50
Established
WikiRag
27
Experimental
Maintenance 10/25
Adoption 7/25
Maturity 16/25
Community 17/25
Maintenance 0/25
Adoption 5/25
Maturity 9/25
Community 13/25
Stars: 31
Forks: 9
Downloads:
Commits (30d): 0
Language: Python
License: BSD-3-Clause
Stars: 10
Forks: 2
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: Apache-2.0
No Package No Dependents
Stale 6m No Package No Dependents

About wiki-rag

moodlehq/wiki-rag

An experimental Retrieval-Augmented Generation (RAG) system specialised in ingesting MediaWiki sites via their API and providing an OpenAI API interface to interact with them.

Implements a modular pipeline with separate executables for loading MediaWiki content via API, indexing embeddings into Milvus vector database, and serving queries through an OpenAI-compatible REST API with bearer token authentication and streaming support. Also provides an MCP server integration and supports incremental updates to avoid reprocessing unchanged pages.

About WikiRag

MauroAndretta/WikiRag

WikiRag is a Retrieval-Augmented Generation (RAG) system designed for question answering, it reduces hallucination thanks to the RAG architecture. It leverages Wikipedia content as a knowledge base.

Implements a vectorization pipeline that embeds Wikipedia articles into Qdrant vector database using HuggingFace embeddings, then chains retrieval with local Ollama LLM inference. Optional DuckDuckGo web search expands context when Wikipedia knowledge proves insufficient, with evaluation metrics (semantic similarity, factual correctness) provided via Ragas library. Includes a Streamlit UI for interactive querying.

Related comparisons

Scores updated daily from GitHub, PyPI, and npm data. How scores work