Files

T

stateofshit 7f189254c0 notebook: add docx→markdown converter for openwebui knowledge bases

- 000-configs/notebooks/docx_to_markdown_openwebui.ipynb (29 cells)
- mammoth + python-docx fallback, manifest dedup (SHA-256), pre-flight
  fuzzy dedup (Jaccard @ 0.97), URL extraction, gzip download
- 000-configs/notebooks/README.md: index of notebooks + how-to-add
- 000-configs/README.md: list notebooks/ subfolder in the table
- 07-tasks/docx-to-markdown-converter-notebook.md: full task writeup

2026-07-30 23:41:39 +00:00

1.3 KiB

Raw Blame History

title, status, folder, tags, created, updated, version

title

status

folder

Notebooks

Executable Jupyter / Colab notebooks that accompany research projects or workspace workflows. These are runnable artifacts (.ipynb), not docs — the companion writeup lives in 06-research/ or as a task in 07-tasks/.

How to use

Download the .ipynb from this folder (or git pull on your PC and open in Obsidian / Jupyter / Colab).
Open in Google Colab for the Cloud-Drive-backed workflows (most notebooks here assume Colab free tier + Drive mount).
Update the task file in 07-tasks/ when you re-run or modify.

Current notebooks

Notebook	Purpose	Companion task
docx_to_markdown_openwebui.ipynb	DOCX + MD → clean Markdown for Open WebUI knowledge bases (mammoth + python-docx fallback + fuzzy dedup + URL extraction)	07-tasks/docx-to-markdown-converter-notebook

When adding a new notebook

Drop the .ipynb here.
Add a row to the table above with a link.
Create or update a task in 07-tasks/<slug>.md describing what it does and how to run it.
Commit with notebook: <one-line> per the repo commit-message convention.

1.3 KiB Raw Blame History

Notebooks

How to use

Current notebooks

When adding a new notebook

1.3 KiB

Raw Blame History