chapek-embedder 0.1.0

Local bge-small-en-v1.5 embeddings, bundled offline, no Hugging Face runtime dependency.

chapek-embedder

Local bge-small-en-v1.5 embeddings, bundled offline, no Hugging Face runtime dependency.

Install

pip install chapek-embedder

Usage

from chapek_embedder import embed, MODEL_VERSION

vectors = embed(["text one", "text two"])
print(vectors.shape)  # (2, 384)
print(MODEL_VERSION)  # bge-small-en-v1.5-cls

Output

• numpy.ndarray of shape (n, 384)
• dtype is float32
• CLS pooled from the model's last hidden state
• L2-normalized per vector
• Inputs longer than 512 tokens are truncated cleanly

Compatibility

This package is designed to match Cloudflare Workers AI's @cf/baai/bge-small-en-v1.5 with pooling set to "cls".

Development

Before building a wheel, download the bundled model resources:

python scripts/download_model.py

Then install for development:

pip install -e .

Run tests with:

pytest

Model version and license

• Model version: bge-small-en-v1.5-cls
• License: MIT (BAAI weights/license)

Project

This package is part of the Chapek project (chapek.ai) and is published separately so it can be reused in constrained environments.