rbehzadan/text-chunking-api repository overview

⁠Text Chunking REST API

This Docker image provides a REST API for chunking a given text into pieces of a specified size. It is built using Go, with the prose library for natural language processing and gorilla/mux for routing.

⁠Features

• Split text into chunks based on the specified maximum number of tokens.
• Does not split text mid-sentence.
• Log each request with method, URI, remote address, and duration.
• Configurable server port through environment variable.

⁠Usage

⁠Pull the Image

docker pull rbehzadan/text-chunking-api:latest

⁠Run the Container

docker run -d -p 8080:8080 rbehzadan/text-chunking-api

⁠Custom Port

To run the server on a different port, set the PORT environment variable:

docker run -d -p 9090:9090 -e PORT=9090 rbehzadan/text-chunking-api

⁠API Endpoints

⁠POST /chunk

• Request Body:

  {
    "text": "Your text here.",
    "max_tokens": 50
  }
  

  Copy

• Response:

  {
    "chunks": ["Chunk 1", "Chunk 2", ...]
  }
  

  Copy

• Error Responses:

  • 400 Bad Request for invalid request payload or non-positive max_tokens.
  • 500 Internal Server Error for errors during text processing.

⁠Example Request

curl -X POST http://localhost:8080/chunk -H "Content-Type: application/json" -d '{"text": "Your text here.", "max_tokens": 50}'

⁠Example Response

{
  "chunks": [
    "Your chunked text here."
  ]
}

⁠Environment Variables

• PORT: Port on which the server will run (default is 8080).

⁠Contributing

1. Fork the repository at https://github.com/rbehzadan/text-chunking-api⁠.
2. Create a new branch (git checkout -b feature-branch).
3. Make your changes.
4. Commit your changes (git commit -m 'Add new feature').
5. Push to the branch (git push origin feature-branch).
6. Create a pull request.

⁠License

This project is licensed under the MIT License. See the LICENSE⁠ file for details.

⁠Acknowledgments

• prose⁠ for NLP functionalities.
• gorilla/mux⁠ for routing.