v0.0.2
weave-os/routerv0.0.2Jul 1, 2026by chonknick
Upgrading?
Release notes summary
pulpie 0.0.2 is the first release under the feyninc org. It ships the pulpie.markdown module, improves Extractor/Pipeline developer experience, ports MinerU-HTML simplify/reconstruct with byte-parity testing, adds Apple MPS auto-detection, and updates model IDs to feyninc/pulpie-orange-*.
Key Highlights
- First release under the feyninc organization.
- Ships pulpie.markdown, with the [markdown] extra now matching the docs.
- Extractor/Pipeline DX fixes including markdown cleanup, error propagation, extract_batch, and dataclass results.
- MinerU-HTML-parity simplify/reconstruct port verified with byte-parity tests against the vendored oracle.
- Apple MPS auto-detection and model IDs now resolve to feyninc/pulpie-orange-{small,base,large}.
Breaking Changes
- Model IDs now resolve to feyninc/pulpie-orange-{small,base,large}; users pinning previous chonkie-ai model IDs may need to update.
New Features
- pulpie.markdown module.
- [markdown] extra aligned with documentation.
- Markdown cleanup improvements.
- Improved error propagation.
- extract_batch API.
- Dataclass results.
- MinerU-HTML-parity simplify/reconstruct implementation.
- Apple MPS auto-detection.
- feyninc/pulpie-orange-{small,base,large} model IDs.
Full Release Notes
First release under the feyninc org.
- Ships `pulpie.markdown` (the `[markdown]` extra now matches the docs).
- Extractor/Pipeline DX fixes: markdown cleanup, error propagation, `extract_batch`, dataclass results.
- MinerU-HTML-parity `simplify`/`reconstruct` port (byte-parity tested against the vendored oracle).
- Apple MPS auto-detection.
- Model IDs now resolve to `feyninc/pulpie-orange-{small,base,large}`.
Install: `pip install "pulpie[markdown]"`Related Repositories
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
The world’s fastest framework for building websites.
:cherry_blossom: A command-line fuzzy finder