darca-embeddings 0.1.1

Abstraction layer for embeddings.

Modular, backend-agnostic interface for generating text embeddings. Provides a consistent Pythonic API for embedding text using various underlying providers.

Key Features

• Unified Embedding Interface: Use one client class for multiple backends.

• Default OpenAI Support: Integrates seamlessly with OpenAI’s Embedding API.

• Extensible Design: Easy to add new backends (e.g., Hugging Face).

Quick Start

1. Install (using Make + Poetry):

   make install

2. Set your environment variables (for example, OPENAI_API_KEY for OpenAI).

3. Use the embedding client:

   from darca_embeddings import EmbeddingClient
   
   client = EmbeddingClient()
   embedding = client.get_embedding("Hello World!")
   print(embedding)

Documentation

We use Sphinx for building documentation. See docs/source/ for the reST files. You can build the docs locally by:

make docs

Contributing

Contributions are welcome! See the CONTRIBUTING.rst for more details.

License

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

Author

Roel Kist