E5 Small Sentence Embeddings

Description

Text Embeddings by Weakly-Supervised Contrastive Pre-training. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022

Predicted Entities

Live Demo Open in Colab Download Copy S3 URI

How to use

embeddings =E5Embeddings.pretrained("e5_small","en") \
            .setInputCols(["documents"]) \
            .setOutputCol("instructor")

pipeline = Pipeline().setStages([document_assembler, embeddings])

val embeddings = E5Embeddings.pretrained("e5_small","en")
      .setInputCols(["document"])
      .setOutputCol("e5_embeddings")
val pipeline = new Pipeline().setStages(Array(document, embeddings))

Model Information