|
|
|
# Text Embedding with dpr
|
|
|
|
|
|
|
|
*author: Kyle He*
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## Desription
|
|
|
|
|
|
|
|
This operator uses Dense Passage Retrieval (DPR) to convert long text to embeddings.
|
|
|
|
|
|
|
|
Dense Passage Retrieval (DPR) is a set of tools and models for state-of-the-art open-domain Q&A research.
|
|
|
|
It was introduced in Dense Passage Retrieval for Open-Domain Question Answering by Vladimir Karpukhin,
|
|
|
|
Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, Wen-tau Yih[1].
|
|
|
|
|
|
|
|
**DPR** models were proposed in "Dense Passage Retrieval for Open-Domain Question Answering"[2].
|
|
|
|
|
|
|
|
In this work, we show that retrieval can be practically implemented using dense representations alone,
|
|
|
|
where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework[2].
|
|
|
|
|
|
|
|
## Reference
|
|
|
|
|
|
|
|
[1].https://huggingface.co/docs/transformers/model_doc/dpr
|
|
|
|
|
|
|
|
[2].https://arxiv.org/abs/2004.04906
|
|
|
|
|
|
|
|
## Code Example
|
|
|
|
|
|
|
|
Use the pretrained model "facebook/dpr-ctx_encoder-single-nq-base"
|
|
|
|
to generate a text embedding for the sentence "Hello, world.".
|
|
|
|
|
|
|
|
*Write the pipeline*:
|
|
|
|
|
|
|
|
```python
|
|
|
|
from towhee import dc
|
|
|
|
|
|
|
|
|
|
|
|
dc.stream(["Hello, world."])
|
|
|
|
.text_embedding.dpr("facebook/dpr-ctx_encoder-single-nq-base")
|
|
|
|
.show()
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
|
|
## Factory Constructor
|
|
|
|
|
|
|
|
Create the operator via the following factory method
|
|
|
|
|
|
|
|
***text_embedding.dpr(model_name="")***
|
|
|
|
|
|
|
|
**Parameters:**
|
|
|
|
|
|
|
|
***model_name***: *str*
|
|
|
|
|
|
|
|
The model name in string.
|
|
|
|
The default value is "facebook/dpr-ctx_encoder-single-nq-base".
|
|
|
|
You can get the list of supported model names by calling `get_model_list` from [dpr.py](https://towhee.io/text-embedding/dpr/src/branch/main/dpr.py).
|
|
|
|
|
|
|
|
|
|
|
|
## Interface
|
|
|
|
|
|
|
|
The operator takes a text in string as input.
|
|
|
|
It loads tokenizer and pre-trained model using model name.
|
|
|
|
and then return text embedding in ndarray.
|
|
|
|
|
|
|
|
**Parameters:**
|
|
|
|
|
|
|
|
***text***: *str*
|
|
|
|
|
|
|
|
The text in string.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
**Returns**:
|
|
|
|
|
|
|
|
*numpy.ndarray*
|
|
|
|
|
|
|
|
The text embedding extracted by model.
|