Conversation
A Python toolkit for German document pipelines: German PII detection with checksums, structural chunking that keeps § paragraphs together, compound splitting, hybrid retrieval and RAG with verified citation numbers. Published on PyPI as deutsches-ki-toolkit, Apache-2.0. Placed alphabetically in Frameworks, next to the other libraries you build German NLP with.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds one line to the Frameworks section:
Repository: https://github.com/mehrabix/deutsches-ki-toolkit
PyPI: https://pypi.org/project/deutsches-ki-toolkit/
What it is. An Apache-2.0 Python library for German document pipelines:
§ 4 Abs. 2together instead of cutting on token countdeutsches-ki pii|chunk|search|ask|evaluateon the command lineInstall with
pip install deutsches-ki-toolkit. There is a browser demo too: https://mehrabix-deutsches-ki-toolkit.hf.spaceSection. Frameworks looked like the closest fit, next to the other libraries here. It would also sit reasonably under Industry/Applications (near holmes-extractor) or Large Language Models (near GermanRAG). I am not attached to the choice — happy to move it wherever you prefer.
Placement. Alphabetically between CorpusExplorer and DKPro Core. That is the only change; no reformatting and no other lines touched.
State. Version 0.5.0 is the first stable release, so a plain
pip installpicks it up; earlier versions were pre-releases. It is young, but actively developed: CI runs on Python 3.12 and 3.13 and exercises the optional pieces (Docling, BGE-M3, GLiNER, PostgreSQL with pgvector, spaCy/Presidio, MCP) against the real libraries rather than mocks. Where the German approach only matches a careful naive baseline instead of beating it, the README says so and gives the numbers.Thanks for maintaining the list.