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.
No commits in the last 6 months.
Stars
10
Forks
2
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Aug 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/MauroAndretta/WikiRag"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
moodlehq/wiki-rag
An experimental Retrieval-Augmented Generation (RAG) system specialised in ingesting MediaWiki...
macromeer/offline-wikipedia-rag
Free offline AI with complete Wikipedia knowledge - 100% private
QingFei1/LongRAG
[EMNLP 2024] LongRAG: A Dual-perspective Retrieval-Augmented Generation Paradigm for...
AdyTech99/volo
An F/OSS solution combining AI with Wikipedia knowledge via a RAG pipeline
xumozhu/RAG-system
Retrieval-Augmented Generation system: ask a question, retrieve relevant documents, and generate...