English baai_bge_base_english_nowr_1_2 BGEEmbeddings from alexakkol

Description

Pretrained BGEEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.baai_bge_base_english_nowr_1_2 is a English model originally trained by alexakkol.

Download Copy S3 URI

How to use

 
documentAssembler = DocumentAssembler() \
      .setInputCol("text") \
      .setOutputCol("document")

embeddings = BGEEmbeddings.pretrained("baai_bge_base_english_nowr_1_2","en") \
      .setInputCols(["document"]) \
      .setOutputCol("embeddings")       
        
pipeline = Pipeline().setStages([documentAssembler, embeddings])
data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)


val documentAssembler = new DocumentAssembler() 
    .setInputCol("text") 
    .setOutputCol("document")
    

val embeddings = BGEEmbeddings.pretrained("baai_bge_base_english_nowr_1_2","en") 
    .setInputCols(Array("document")) 
    .setOutputCol("embeddings")

val pipeline = new Pipeline().setStages(Array(documentAssembler, embeddings))
val data = Seq("I love spark-nlp).toDS.toDF("text")
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)

Model Information

Model Name: baai_bge_base_english_nowr_1_2
Compatibility: Spark NLP 5.4.0+
License: Open Source
Edition: Official
Input Labels: [document]
Output Labels: [bge]
Language: en
Size: 112.6 MB

References

https://huggingface.co/alexakkol/BAAI-bge-base-en-nowr-1-2