Description
Pretrained BGEEmbeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.
bge_medembed_large_v0_1 is a English model originally trained by abhinand
How to use
document_assembler = DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
embeddings = BGEEmbeddings.pretrained("bge_medembed_large_v0_1","en")\
.setInputCols(["document"])\
.setOutputCol("embeddings")
pipeline = Pipeline(
stages = [
document_assembler,
embeddings
])
data = spark.createDataFrame([["I love spark-nlp"]]).toDF("text")
result = pipeline.fit(data).transform(data)
val document_assembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val embeddings = BGEEmbeddings.pretrained("bge_medembed_large_v0_1","en")
.setInputCols(Array("document"))
.setOutputCol("embeddings")
val pipeline = new Pipeline().setStages(Array(document_assembler, embeddings))
val data = Seq("I love spark-nlp").toDS.toDF("text")
val result = pipeline.fit(data).transform(data)
Results
+----------------------------------------------------------------------------------------------------+
| bge_embedding|
+----------------------------------------------------------------------------------------------------+
|[{sentence_embeddings, 0, 15, I love spark-nlp, {sentence -> 0}, [-0.018065551, -0.032784615, 0.0...|
+----------------------------------------------------------------------------------------------------+
Model Information
| Model Name: | bge_medembed_large_v0_1 |
| Compatibility: | Spark NLP 5.5.0+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document] |
| Output Labels: | [bge] |
| Language: | en |
| Size: | 1.2 GB |