kibae/pg_onnx
pg_onnx: ONNX Runtime integrated with PostgreSQL. Perform ML inference with data in your database.
This tool helps data professionals integrate machine learning predictions directly into their PostgreSQL databases. You can upload pre-trained ONNX models, and then use SQL queries to perform real-time inference on data stored within your tables. This is ideal for data scientists, machine learning engineers, and database administrators who want to operationalize ML models efficiently.
Use this if you need to run machine learning predictions directly within your PostgreSQL database using your existing data, without moving it to external services.
Not ideal if you need to train machine learning models or require extremely low-latency inference on very high-volume, real-time streaming data outside of a database context.
Stars
58
Forks
4
Language
C++
License
MIT
Category
Last pushed
Mar 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kibae/pg_onnx"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
onnx/onnx
Open standard for machine learning interoperability
PINTO0309/onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The...
NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This...
onnx/onnxmltools
ONNXMLTools enables conversion of models to ONNX