public class BgeSmallEnV15QuantizedEmbeddingModel extends AbstractInProcessEmbeddingModel
Maximum length of text (in tokens) that can be embedded at once: unlimited. However, while you can embed very long texts, the quality of the embedding degrades as the text lengthens. It is recommended to embed segments of no more than 512 tokens long.
Embedding dimensions: 384
It is recommended to add "Represent this sentence for searching relevant passages:" prefix to a query.
More details here
dimension| Constructor and Description |
|---|
BgeSmallEnV15QuantizedEmbeddingModel()
Creates an instance of an
BgeSmallEnV15QuantizedEmbeddingModel. |
BgeSmallEnV15QuantizedEmbeddingModel(Executor executor)
Creates an instance of an
BgeSmallEnV15QuantizedEmbeddingModel. |
| Modifier and Type | Method and Description |
|---|---|
protected Executor |
executor() |
protected Integer |
knownDimension() |
protected OnnxBertBiEncoder |
model() |
embedAll, estimateTokenCount, loadFromJardimensionclone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitestimateTokenCount, estimateTokenCountembed, embedpublic BgeSmallEnV15QuantizedEmbeddingModel()
BgeSmallEnV15QuantizedEmbeddingModel.
Uses a fixed thread pool with the number of threads equal to the number of available processors.public BgeSmallEnV15QuantizedEmbeddingModel(Executor executor)
BgeSmallEnV15QuantizedEmbeddingModel.executor - The executor to use to parallelize the embedding process.protected OnnxBertBiEncoder model()
model in class AbstractInProcessEmbeddingModelprotected Executor executor()
executor in class AbstractInProcessEmbeddingModelprotected Integer knownDimension()
knownDimension in class DimensionAwareEmbeddingModelCopyright © 2024. All rights reserved.