Edit on GitHub
  • John Snow Labs
  • Jan 27, 2025

German e5_base_german_sentence_similarity_pipeline pipeline E5Embeddings from kaixkhazaki

  • de
  • open_source
  • pipeline
  • onnx

Description

Pretrained E5Embeddings, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.e5_base_german_sentence_similarity_pipeline is a German model originally trained by kaixkhazaki.

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("e5_base_german_sentence_similarity_pipeline", lang = "de")
annotations =  pipeline.transform(df)   



val pipeline = new PretrainedPipeline("e5_base_german_sentence_similarity_pipeline", lang = "de")
val annotations = pipeline.transform(df)

Model Information

Model Name: e5_base_german_sentence_similarity_pipeline
Type: pipeline
Compatibility: Spark NLP 5.5.1+
License: Open Source
Edition: Official
Language: de
Size: 385.6 MB

References

https://huggingface.co/kaixkhazaki/e5-base-german-sentence-similarity

Included Models

  • DocumentAssembler
  • E5Embeddings