Description
Pretrained MxbaiEmbeddings, adataped from huggingface imported to Spark-NLP to provide scalability and production-readiness.
How to use
documentAssembler = DocumentAssembler() \
.setInputCol('text') \
.setOutputCol('document')
mxbai = MxbaiEmbeddings.pretrained("mxbai_large_v1","en") \
.setInputCols("document") \
.setOutputCol("embeddings") \
pipeline = Pipeline().setStages([documentAssembler, mxbai])
data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
pipelineModel = pipeline.fit(data)
pipelineDF = pipelineModel.transform(data)
val documentAssembler = new DocumentAssembler()
.setInputCols("text")
.setOutputCols("document")
val mxbai = MxbaiEmbeddings.pretrained("mxbai_large_v1", "en")
.setInputCols("documents")
.setOutputCol("embeddings")
val pipeline = new Pipeline().setStages(Array(documentAssembler, mxbai))
val data = Seq("I love spark-nlp").toDS.toDF("text")
val pipelineModel = pipeline.fit(data)
val pipelineDF = pipelineModel.transform(data)
Model Information
| Model Name: | mxbai_large_v1 |
| Compatibility: | Spark NLP 5.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document] |
| Output Labels: | [Mxbai] |
| Language: | en |
| Size: | 793.8 MB |