PyPI page
Home page
Author:
n24q02m
Summary:
Fast multi-model retrieval runtime: ONNX and GGUF embeddings, reranking, and a declarative model contract
Latest version:
1.12.0
Required dependencies:
huggingface-hub
|
loguru
|
numpy
|
onnxruntime
|
requests
|
tokenizers
|
tqdm
Optional dependencies:
llama-cpp-python
|
pillow
Downloads last day:
56
Downloads last week:
592
Downloads last month:
7,632
7-day smoothing