Skip to content

pqaidevteam/pqai-encoder

Repository files navigation

Python Linting: pylint Docker build: automated Code style: black GitHub license

PQAI Encoder

PQAI service for transforming data into representations suitable as inputs for machine-learning pipelines. For example, transforming a piece of text into an embedding in a high-dimensional vector space.

The following representations are supported at the moment:

  1. Text -> Dense embedding
  2. Text -> Sequence of word vectors
  3. Text -> Bag of entities

For more detailed information, please refer to PQAI Wiki.

Routes

Method Route Description
POST /encode Returns a representation of given data

License

The project is open-source under the MIT license.

Contribute

We welcome contributions.

To make a contribution, please follow these steps:

  1. Fork this repository.
  2. Create a new branch with a descriptive name
  3. Make copy of env file as .env and docker-compose.dev.yml as docker-compose.yml
  4. Download and extract the file from https://s3.amazonaws.com/pqai.s3/public/pqai-assets-latest.zip to assets/
  5. Bring encoder to life docker-compose up
  6. Make the changes you want and add new tests, if needed
  7. Make sure all tests are passing docker exec -i dev_pqai_encoder_api python -m unittest discover ./tests/
  8. Commit your changes
  9. Submit a pull request

Support

Please create an issue if you need help.

About

Representation creation modules of PQAI

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •