Johnsnowlabs
访问johnsnowlabs的企业NLP库生态系统，通过开源的johnsnowlabs库，拥有超过21,000个企业NLP模型，涵盖200多种语言。要查看所有24,000多个模型，请访问John Snow Labs模型中心
安装与设置
pip install johnsnowlabs
要[安装企业功能](https://nlp.johnsnowlabs.com/docs/en/jsl/install_licensed_quick，请运行：
# for more details see https://nlp.johnsnowlabs.com/docs/en/jsl/install_licensed_quick
nlp.install()
您可以使用基于gpu、cpu、apple_silicon、aarch优化的二进制文件嵌入您的查询和文档。
默认情况下使用cpu二进制文件。
一旦会话开始，您必须重新启动您的笔记本以在GPU或CPU之间切换，否则更改将不会生效。
嵌入查询与CPU:
document = "foo bar"
embedding = JohnSnowLabsEmbeddings('embed_sentence.bert')
output = embedding.embed_query(document)
使用GPU嵌入查询:
document = "foo bar"
embedding = JohnSnowLabsEmbeddings('embed_sentence.bert','gpu')
output = embedding.embed_query(document)
在Apple Silicon（M1、M2等）上嵌入查询：
documents = ["foo bar", 'bar foo']
embedding = JohnSnowLabsEmbeddings('embed_sentence.bert','apple_silicon')
output = embedding.embed_query(document)
使用AARCH嵌入查询:
documents = ["foo bar", 'bar foo']
embedding = JohnSnowLabsEmbeddings('embed_sentence.bert','aarch')
output = embedding.embed_query(document)
使用CPU嵌入文档:
documents = ["foo bar", 'bar foo']
embedding = JohnSnowLabsEmbeddings('embed_sentence.bert','gpu')
output = embedding.embed_documents(documents)
使用GPU嵌入文档：
documents = ["foo bar", 'bar foo']
embedding = JohnSnowLabsEmbeddings('embed_sentence.bert','gpu')
output = embedding.embed_documents(documents)
嵌入文档与Apple Silicon (M1, M2, 等..):
```python
documents = ["foo bar", 'bar foo']
embedding = JohnSnowLabsEmbeddings('embed_sentence.bert','apple_silicon')
output = embedding.embed_documents(documents)
使用AARCH嵌入文档：
```python
documents = ["foo bar", 'bar foo']
embedding = JohnSnowLabsEmbeddings('embed_sentence.bert','aarch')
output = embedding.embed_documents(documents)
模型通过nlp.load加载，并且Spark会话在后台通过nlp.start()启动。