OCR API
An API to extract text from Images
Technology | Project | How to Run | License
β¨ Technology
The Project was develop as using the following techs:
π» Project
This project was developed as part of the "Build a REST API Using Python and Deploy it to Microsoft Azure" course on Educative. The goal of the project is to create an API using the FastAPI framework, which can simultaneously extract text from images uploaded by users. Using FastAPI allowed us to build a performant and scalable API with minimal boilerplate code.
One of the key features of our API is its ability to extract text from images. By leveraging third-party libraries and machine learning models, we were able to build a robust OCR (Optical Character Recognition) system that can accurately recognize text from a wide variety of image formats.
Overall, this project was an excellent learning opportunity that helped us develop our Python programming skills, as well as gain experience with deploying applications on a cloud platform.
π Requirements
As educational project, and the purpose is use the concepts of CRUD, then we requirements of the our applications is to :
- Post one or more Images to Extract from images
End Points
The API has the following end points:
Type | url | Functionality |
---|---|---|
post |
"/api/v1/extract_text" | Post one or more Images |
π How to Run
To run the this project
- Clone the repo and access the directory;
- You can use the following command:
python -m venv ./venv
.\venv\Scripts\activate
pip install -r .\requirements.txt
uvicorn main:app --host localhost --port 8000 --reload
π License
The projects is under the MIT license. See the file LICENSE fore more details
Author
Made with β₯ by Rafael ππ»