Show HN: ParseHawk – 100% Local Document AI with API, CLI, and Web UI (github.com)

8 points by francisrafal ↗ HN
I just released ParseHawk v0.1.0: Apache-2.0 licensed 100% local document AI platform that extracts JSON from PDFs, images etc. It builds on top of NuMind's NuExtract3 but additionally enforces a provided JSON schema with constrained decoding. It works on Apple Silicon with pre-bundled vllm-metal as well as Linux + NVIDIA with vllm. Looking forward to your feedback!

4 comments

[ 0.23 ms ] story [ 24.5 ms ] thread
it would be more effective for more user if it support on windows.
Our first users were working with this setup: Server running on DGX Spark and exposing Web UI and API in the local network to access it from their Windows machine.

But yes, we truly want to support all platforms and Windows support will be coming soon!