Skip to main content

Documentation Index

Fetch the complete documentation index at: https://notewise.click/docs/llms.txt

Use this file to discover all available pages before exploring further.

The processing path is implemented by CorePipeline and the pipeline execution helpers.

Processing flow

1

Cache check

Unless --force is set, NoteWise checks the SQLite cache before metadata or transcript work.
2

Metadata and transcript

NoteWise resolves YouTube metadata, captions, transcript segments, chapters, and playlist context when applicable.
3

Generation

Transcript text is chunked with source defaults 4000 size and 200 overlap, then sent to the configured LiteLLM model.
4

Artifacts

NoteWise writes notes, optional quizzes, optional transcript exports, and rendered formats.
5

Persistence

Run stats, output paths, transcript content, tokens, costs, and timings are persisted to SQLite when possible.

Chapter behavior

Videos with YouTube chapters use chapter-aware generation. Without --chapter-directory-output, the result is still bundled into a final notes file. With --chapter-directory-output, NoteWise writes per-chapter Markdown files into a folder and stores .notewise-output.json ownership metadata.

Output formats

FormatBehavior
mdRaw Markdown notes. Default.
htmlMarkdown rendered with built-in CSS.
pdfUses fpdf; Latin-script text only. Unsupported Unicode falls back to Markdown.
docxUses html2docx and python-docx.

File layout

output
Video Title.md
Video Title.html
Video Title.docx
Video Title_quiz.md
Video Title_transcript.json
Video Title
01_Introduction.md
02_Main Topic.md
.notewise-output.json
Filenames are sanitized and capped at 100 characters. Batch collisions may append the video ID.
Last modified on May 1, 2026