ankane/informers
Fast transformer inference for Ruby
Runs ONNX transformer models directly in Ruby via the Transformers.js library, supporting embedding, reranking, NER, sentiment analysis, and QA pipelines. Provides pipeline abstractions with pre-configured models from Hugging Face, including sentence transformers and specialized rerankers, eliminating the need for separate Python inference services. Handles model downloading and caching automatically while allowing custom ONNX model paths.
599 stars. Actively maintained with 2 commits in the last 30 days.
Stars
599
Forks
18
Language
Ruby
License
Apache-2.0
Category
Last pushed
Jan 09, 2026
Commits (30d)
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/ankane/informers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dnanhkhoa/python-vncorenlp
A Python wrapper for VnCoreNLP using a bidirectional communication channel.
datquocnguyen/RDRPOSTagger
A fast and accurate POS and morphological tagging toolkit (EACL 2014)
OpenSextant/SolrTextTagger
A text tagger based on Lucene / Solr, using FST technology
bentrevett/pytorch-pos-tagging
A tutorial on how to implement models for part-of-speech tagging using PyTorch and TorchText.
nschneid/arabic-tagger
AQMAR Arabic Tagger: Sequence tagger with cost-augmented structured perceptron training