https://github.com/curiousily/Deploy-BERT-for-Sentiment-Analysis-with-FastAPI

Deploy BERT for Sentiment Analysis as REST API using FastAPI, Transformers by Hugging Face and PyTorch
https://github.com/curiousily/Deploy-BERT-for-Sentiment-Analysis-with-FastAPI

bert deep-learning deploy-machine-learning deployment fastapi huggingface huggingface-transformer machine-learning python pytorch rest rest-api sentiment-analysis transformers uvicorn

Last synced: 9 days ago
JSON representation

Deploy BERT for Sentiment Analysis as REST API using FastAPI, Transformers by Hugging Face and PyTorch

• Host: GitHub
• URL: https://github.com/curiousily/Deploy-BERT-for-Sentiment-Analysis-with-FastAPI
• Owner: curiousily
• License: mit
• Created: 2020-04-26T08:35:01.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2022-12-08T09:42:11.000Z (about 2 years ago)
• Last Synced: 2024-11-30T13:12:31.481Z (13 days ago)
• Topics: bert, deep-learning, deploy-machine-learning, deployment, fastapi, huggingface, huggingface-transformer, machine-learning, python, pytorch, rest, rest-api, sentiment-analysis, transformers, uvicorn
• Language: Python
• Homepage: https://www.curiousily.com/posts/deploy-bert-for-sentiment-analysis-as-rest-api-using-pytorch-transformers-by-hugging-face-and-fastapi/
• Size: 86.9 KB
• Stars: 201
• Watchers: 4
• Forks: 60
• Open Issues: 8
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• jimsghstars - curiousily/Deploy-BERT-for-Sentiment-Analysis-with-FastAPI - Deploy BERT for Sentiment Analysis as REST API using FastAPI, Transformers by Hugging Face and PyTorch (Python)

README

        
# Deploy BERT for Sentiment Analsysi with FastAPI

Deploy a pre-trained BERT model for Sentiment Analysis as a REST API using FastAPI

## Demo

The model is trained to classify sentiment (negative, neutral, and positive) on a custom dataset from app reviews on Google Play. Here's a sample request to the API:

```bash

http POST http://127.0.0.1:8000/predict text="Good basic lists, i would like to create more lists, but the annual fee for unlimited lists is too out there"

```

The response you'll get looks something like this:

```js

{

    "confidence": 0.9999083280563354,

    "probabilities": {

        "negative": 3.563107020454481e-05,

        "neutral": 0.9999083280563354,

        "positive": 5.596495248028077e-05

    },

    "sentiment": "neutral"

}

```

You can also [read the complete tutorial here](https://www.curiousily.com/posts/deploy-bert-for-sentiment-analysis-as-rest-api-using-pytorch-transformers-by-hugging-face-and-fastapi/)

## Installation

Clone this repo:

```sh

git clone [email protected]:curiousily/Deploy-BERT-for-Sentiment-Analysis-with-FastAPI.git

cd Deploy-BERT-for-Sentiment-Analysis-with-FastAPI

```

Install the dependencies:

```sh

pipenv install --dev

```

Download the pre-trained model:

```sh

bin/download_model

```

## Test the setup

Start the HTTP server:

```sh

bin/start_server

```

Send a test request:

```sh

bin/test_request

```

## License

MIT