embedding-as-service
One-Stop Solution to encode sentence to fixed length vectors from various embedding techniques
• Inspired from bert-as-service
What is it •
Installation •
Getting Started •
Supported Embeddings •
API •
What is it
**Encoding/Embedding** is a upstream task of encoding any inputs in the form of text, image, audio, video, transactional data to fixed length vector. Embeddings are quite popular in the field of NLP, there has been various Embeddings models being proposed in recent years by researchers, some of the famous one are bert, xlnet, word2vec etc. The goal of this repo is to build one stop solution for all embeddings techniques available, here we are starting with popular text embeddings for now and later on we aim to add as much technique for image, audio, video inputs also.
**`embedding-as-service`** help you to encode any given text to fixed length vector from supported embeddings and models.
💾 Installation
▴ Back to top
Here we have given the capability to use `embedding-as-service` like a module or you can run it as a server and handle queries by installing client package `embedding-as-service-client`
#### Using `embedding-as-service` as module
Install the embedding-as-servive via `pip`.
```bash
$ pip install embedding-as-service
```
> Note that the code MUST be running on **Python >= 3.6**. Again module does not support Python 2!
#### Using `embedding-as-service` as a server
Here you also need to install a client module `embedding-as-service-client`
```bash
$ pip install embedding-as-service # server
$ pip install embedding-as-service-client # client
```
> Client module need not to be on Python 3.6, it supports both Python2 and Python3
⚡ ️Getting Started
▴ Back to top
#### 1. **Intialise encoder using supported embedding** and models from
here
If using `embedding-as-service` **as a module**
```python
>>> from embedding_as_service.text.encode import Encoder
>>> en = Encoder(embedding='bert', model='bert_base_cased', max_seq_length=256)
```
If using `embedding-as-service` **as a server**
```bash
# start the server by proving embedding, model, port, max_seq_length[default=256], num_workers[default=4]
$ embedding-as-service-start --embedding bert --model bert_base_cased --port 8080 --max_seq_length 256
```
```python
>>> from embedding_as_service_client import EmbeddingClient
>>> en = EmbeddingClient(host=
, port=)
```
#### 2. Get sentences **tokens embedding**
```python
>>> vecs = en.encode(texts=['hello aman', 'how are you?'])
>>> vecs
array([[[ 1.7049843 , 0. , 1.3486509 , ..., -1.3647075 ,
0.6958289 , 1.8013777 ], ... [ 0.4913215 , 0.60877025, 0.73050433, ..., -0.64490885, 0.8525057 , 0.3080206 ]]], dtype=float32)
>>> vecs.shape
(2, 128, 768) # batch x max_sequence_length x embedding_size
```
#### 3. Using **pooling strategy**, click here for more.
Supported Pooling Methods
|Strategy|Description|
|---|---|
| `None` | no pooling at all, useful when you want to use word embedding instead of sentence embedding. This will results in a `[max_seq_len, embedding_size]` encode matrix for a sequence.|
| `reduce_mean` | take the average of all token embeddings |
| `reduce_min` | take the minumun of all token embeddings|
| `reduce_max` | take the maximum of all token embeddings |
| `reduce_mean_max` | do `reduce_mean` and `reduce_max` separately and then concat them together |
| `first_token` | get the token embedding of first token of a sentence |
| `last_token` | get the token embedding of last token of a sentence |
📋 API
▴ Back to top
1. **class** `embedding_as_service.text.encoder.Encoder`
| Argument | Type | Default | Description |
|--------------------|------|-------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `embedding` | str | *Required* | embedding method to be used, check `Embedding` column here|
| `model`| str |*Required*| Model to be used for mentioned embedding, check `Model` column here|
| `max_seq_length`| int |128| Maximum Sequence Length, default is 128|
2. **def** `embedding_as_service.text.encoder.Encoder.encode`
| Argument | Type | Default | Description |
|--------------------|------|-------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `Texts` | List[str] or List[List[str]] | *Required* | List of sentences or list of list of sentence tokens in case of `is_tokenized=True`
| `pooling`| str |(Optional)| Pooling methods to apply, here is available methods|
| `is_tokenized` | bool | `False` | set as True in case of tokens are passed for encoding |
| `batch_size` | int | `128` | maximum number of sequences handled by encoder, larger batch will be partitioned into small batches. |
3. **def** `embedding_as_service.text.encoder.Encoder.tokenize`
| Argument | Type | Default | Description |
|--------------------|------|-------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `Texts` | List[str] | *Required* | List of sentences
✅ Supported Embeddings and Models
▴ Back to top
Here are the list of supported embeddings and their respective models.
| |Embedding | Model | Embedding dimensions | Paper |
|:--|:--|:--:|:--:|--|
|:one: |**albert**|`albert_base` | 768| Read Paper :bookmark: |
|| |`albert_large` | 1024| |
|| |`albert_xlarge` | 2048| |
|| |`albert_xxlarge` | 4096| |
|:two: |**xlnet** |`xlnet_large_cased` | 1024| Read Paper :bookmark: |
|| |`xlnet_base_cased` | 768| |
|:three: |**bert** |`bert_base_uncased` | 768| Read Paper :bookmark: |
|||`bert_base_cased` | 768| |
|| |`bert_multi_cased` | 768||
|| |`bert_large_uncased` | 1024||
|| |`bert_large_cased` | 1024| |
|:four: |**elmo** |`elmo_bi_lm` | 512| Read Paper :bookmark: |
|:five: |**ulmfit** |`ulmfit_forward` | 300| Read Paper :bookmark: |
|||`ulmfit_backward` | 300| |
|:six: |**use**|`use_dan` | 512| Read Paper :bookmark: |
|| |`use_transformer_large` | 512| |
|| |`use_transformer_lite` | 512| |
|:seven: |**word2vec**|`google_news_300` | 300| Read Paper :bookmark: |
|:eight: |**fasttext**|`wiki_news_300` | 300| Read Paper :bookmark: |
|| |`wiki_news_300_sub` | 300| |
|| |`common_crawl_300` | 300| |
|| |`common_crawl_300_sub` | 300| |
|:nine: |**glove**|`twitter_200` | 200| Read Paper :bookmark: |
|| |`twitter_100` | 100| |
|| |`twitter_50` | 50| |
|| |`twitter_25` | 25| |
|| |`wiki_300` | 300| |
|| |`wiki_200` | 200| |
|| |`wiki_100` | 100| |
|| |`wiki_50` | 50| |
|| |`crawl_42B_300` | 300| |
|| |`crawl_840B_300` | 300| |
## Credits
This software uses the following open source packages:
- [XLnet](https://github.com/zihangdai/xlnet)
- [tensorflow-hub](https://www.tensorflow.org/hub)
## Contributors ✨
Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/docs/en/emoji-key)):
This project follows the [all-contributors](https://github.com/all-contributors/all-contributors) specification. Contributions of any kind welcome!
Please read the [contribution guidelines](CONTRIBUTION.md) first.
Citing
▴ Back to top
If you use embedding-as-service in a scientific publication, we would appreciate references to the following BibTex entry:
```latex
@misc{aman2019embeddingservice,
title={embedding-as-service},
author={Srivastava, Aman},
howpublished={\url{https://github.com/amansrivastava17/embedding-as-service}},
year={2019}
}
```
