Spaces:
Paused
Paused
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,9 +4,101 @@ emoji: π¬
|
|
| 4 |
colorFrom: yellow
|
| 5 |
colorTo: purple
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version: 5.
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
colorFrom: yellow
|
| 5 |
colorTo: purple
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: 5.11.0
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
---
|
| 11 |
|
| 12 |
+
NLP Model Deployment with FastAPI
|
| 13 |
+
|
| 14 |
+
[](https://github.com/Chemically-Motivated-Solutions/NLPToolkit/actions)
|
| 15 |
+
[](https://github.com/Chemically-Motivated-Solutions/NLPToolkit/actions)
|
| 16 |
+
[](https://github.com/Chemically-Motivated-Solutions/NLPToolkit/network/updates)
|
| 17 |
+
[](https://www.python.org/)
|
| 18 |
+
[](https://github.com/Chemically-Motivated-Solutions/NLPToolkit/blob/main/LICENSE)
|
| 19 |
+
[](https://codecov.io/gh/Chemically-Motivated-Solutions/NLPToolkit)
|
| 20 |
+
[](https://github.com/Chemically-Motivated-Solutions/NLPToolkit/releases)
|
| 21 |
+
[](https://github.com/Chemically-Motivated-Solutions/NLPToolkit/issues)
|
| 22 |
+
|
| 23 |
+
Overview
|
| 24 |
+
This project demonstrates how to deploy Natural Language Processing (NLP) models using FastAPI, a modern web framework for building APIs with Python. The application integrates two pre-trained models from the Hugging Face Transformers library:
|
| 25 |
+
|
| 26 |
+
Sequence Classification Model: Utilized for tasks like sentiment analysis.
|
| 27 |
+
Question Answering Model: Designed to provide answers based on a given context.
|
| 28 |
+
Features
|
| 29 |
+
RESTful API Endpoints:
|
| 30 |
+
|
| 31 |
+
/predict: Accepts user input and returns model predictions.
|
| 32 |
+
/health: Provides health status of the API.
|
| 33 |
+
Model Integration:
|
| 34 |
+
|
| 35 |
+
Incorporates Hugging Face's AutoModelForSequenceClassification and AutoModelForQuestionAnswering for NLP tasks.
|
| 36 |
+
Installation
|
| 37 |
+
Clone the Repository:
|
| 38 |
+
|
| 39 |
+
bash
|
| 40 |
+
Copy code
|
| 41 |
+
git clone https://github.com/yourusername/nlp-fastapi-deployment.git
|
| 42 |
+
cd nlp-fastapi-deployment
|
| 43 |
+
Set Up a Virtual Environment:
|
| 44 |
+
|
| 45 |
+
bash
|
| 46 |
+
Copy code
|
| 47 |
+
python -m venv venv
|
| 48 |
+
source venv/bin/activate # On Windows: venv\Scripts\activate
|
| 49 |
+
Install Dependencies:
|
| 50 |
+
|
| 51 |
+
bash
|
| 52 |
+
Copy code
|
| 53 |
+
pip install -r requirements.txt
|
| 54 |
+
Usage
|
| 55 |
+
Start the FastAPI Server:
|
| 56 |
+
|
| 57 |
+
bash
|
| 58 |
+
Copy code
|
| 59 |
+
uvicorn main:app --reload
|
| 60 |
+
The API will be accessible at http://127.0.0.1:8000.
|
| 61 |
+
|
| 62 |
+
Interact with the API:
|
| 63 |
+
|
| 64 |
+
Navigate to http://127.0.0.1:8000/docs to access the interactive API documentation provided by Swagger UI.
|
| 65 |
+
|
| 66 |
+
**Example Request:**
|
| 67 |
+
|
| 68 |
+
```bash
|
| 69 |
+
curl -X POST "http://127.0.0.1:8000/predict" -H "Content-Type: application/json" -d '{"text": "Your input text here"}'
|
| 70 |
+
```
|
| 71 |
+
## Project Structure
|
| 72 |
+
```plaintext
|
| 73 |
+
nlp-fastapi-deployment/
|
| 74 |
+
βββ app/
|
| 75 |
+
β βββ __init__.py
|
| 76 |
+
β βββ main.py # Main application file
|
| 77 |
+
β βββ models.py # Pydantic models for request and response
|
| 78 |
+
β βββ nlp_models.py # Functions for loading and utilizing NLP models
|
| 79 |
+
β βββ utils.py # Utility functions
|
| 80 |
+
βββ requirements.txt # Project dependencies
|
| 81 |
+
βββ README.md # Project documentation
|
| 82 |
+
βββ .gitignore # Git ignore file
|
| 83 |
+
```
|
| 84 |
+
## Dependencies
|
| 85 |
+
- FastAPI: Web framework for building APIs with Python.
|
| 86 |
+
- Transformers: Library for state-of-the-art NLP models.
|
| 87 |
+
- Torch: Deep learning framework used by Transformers.
|
| 88 |
+
- Uvicorn: ASGI server for running FastAPI applications.
|
| 89 |
+
|
| 90 |
+
**Ensure all dependencies are listed in requirements.txt for easy installation.**
|
| 91 |
+
|
| 92 |
+
## Contributing
|
| 93 |
+
Contributions are welcome! Please fork the repository and submit a pull request with your changes.
|
| 94 |
+
|
| 95 |
+
## License
|
| 96 |
+
This project is licensed under the MIT License. See the LICENSE file for details.
|
| 97 |
+
|
| 98 |
+
## Acknowledgements
|
| 99 |
+
- Hugging Face for providing accessible NLP models.
|
| 100 |
+
- FastAPI for the high-performance API framework.
|
| 101 |
+
**For a visual guide on creating a deep learning API with FastAPI, you might find the following resource helpful:**
|
| 102 |
+
https://youtu.be/NrarIs9n24I
|
| 103 |
+
|
| 104 |
+
An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
|