---
inference: false
language: en
license:
- cc-by-sa-3.0
- gfdl
library_name: txtai
tags:
- sentence-similarity
datasets:
- NeuML/wikipedia-20240101
---

# Wikipedia txtai embeddings slim

This is a [txtai](https://github.com/neuml/txtai) embeddings index for the [English edition of Wikipedia](https://en.wikipedia.org/).

The slim version has the `100K most popular` Wikipedia pages ranked by page views. This embeddings index also has graph indexing enabled, which enables using this as a source for GraphRAG.

See the [txtai-wikipedia](https://hf.co/models/neuml/txtai-wikipedia) model page for additional information on this datasource.