darca-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

Install (using Make + Poetry):
```
make install
```
Set your environment variables (for example, OPENAI_API_KEY for OpenAI).

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

Release files for darca-embeddings 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for darca-embeddings 0.1.1
File	Size	Uploaded
darca_embeddings-0.1.1.tar.gz	5.1 kB	Mar 30, 2025	Details

Built distribution (wheel)

Table of built distributions (wheels) for darca-embeddings 0.1.1
File	Interpreter	ABI	Platform	Reset
darca_embeddings-0.1.1-py3-none-any.whl 6.2 kB Mar 30, 2025	Python 3	none	any	Details

Total release size: 11.3 kB

Release files / darca_embeddings-0.1.1.tar.gz

Download URL	darca_embeddings-0.1.1.tar.gz
Size	5.1 kB
Tags	Source
SHA-256 checksum How to use checksums	`90ee2136799a3e437768b0dea70177cc63fb097d23977432e2e7c88b6f269391`
BLAKE2b-256 checksum How to use checksums	`4a56137ea4b46e97e8629a13167766b758277113a159480a9dfb61940bced8b1`
Upload date	Mar 30, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.12.9`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/roelkist/darca-embeddings
Publishing commit: github.com/roelkist/darca-embeddings/tree/bc920fb066743efbeaa8d9313c204abeddc75e47

Workflow

Publishing configuration: github.com/roelkist/darca-embeddings/blob/bc920fb066743efbeaa8d9313c204abeddc75e47/.github/workflows/cd.yml
Publishing logs: github.com/roelkist/darca-embeddings/actions/runs/14159708209/attempts/1

Artifact

Subject: darca_embeddings-0.1.1.tar.gz
SHA-256 checksum: 90ee2136799a3e437768b0dea70177cc63fb097d23977432e2e7c88b6f269391 Verifying attestations

Release files / darca_embeddings-0.1.1-py3-none-any.whl

Download URL	darca_embeddings-0.1.1-py3-none-any.whl
Size	6.2 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`528211fb801cf915aded891577d7d031abf842b4aa26828a384a79a981bd03f1`
BLAKE2b-256 checksum How to use checksums	`c2006dc2cab7cf4b58cbd6ba9005fa5d8991a1efaf2479b5475210902399bcbb`
Upload date	Mar 30, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.12.9`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/roelkist/darca-embeddings
Publishing commit: github.com/roelkist/darca-embeddings/tree/bc920fb066743efbeaa8d9313c204abeddc75e47

Workflow

Publishing configuration: github.com/roelkist/darca-embeddings/blob/bc920fb066743efbeaa8d9313c204abeddc75e47/.github/workflows/cd.yml
Publishing logs: github.com/roelkist/darca-embeddings/actions/runs/14159708209/attempts/1

Artifact

Subject: darca_embeddings-0.1.1-py3-none-any.whl
SHA-256 checksum: 528211fb801cf915aded891577d7d031abf842b4aa26828a384a79a981bd03f1 Verifying attestations