transformers/README.md

# Text Embedding with Transformers

*author: Jael Gu*



## Desription

A text embedding operator implemented with pretrained models from [Huggingface Transformers](https://huggingface.co/docs/transformers).



```python
from towhee import ops

text_encoder = ops.text_embedding.transformers(model_name="bert-base-cased")
text_embedding = text_encoder("Hello, world.")
```

## Factory Constructor

Create the operator via the following factory method

***ops.text_embedding.transformers(model_name)***



## Interface

A text embedding operator takes a sentence, paragraph, or document in string as an input
and output an embedding vector in ndarray which captures the input's core semantic elements.


**Parameters:**

​	***text***: *str*

​	The text in string.



**Returns**: *numpy.ndarray*

​	The text embedding extracted by model.



## Code Example

Use the pretrained Bert-Base-Cased model ('bert-base-cased')
to generate a text embedding for the sentence "Hello, world.". 

 *Write the pipeline in simplified style*:

```python
import towhee.DataCollection as dc

dc.glob("Hello, world.")
  .text_embedding.transformers('bert-base-cased')
  .show()
```

*Write a same pipeline with explicit inputs/outputs name specifications:*

```python
from towhee import DataCollection as dc

dc.glob['text']('Hello, world.')
  .text_embedding.transformers['text', 'vec']('bert-base-cased')
  .select('vec')
  .show()
```