From 0e453083de8f860877809b03de0525589120c7a5 Mon Sep 17 00:00:00 2001 From: Safi Date: Fri, 10 Apr 2026 16:24:13 +0100 Subject: [PATCH] Remove YouTube URL references from README, use generic placeholder Co-Authored-By: Claude Sonnet 4.6 --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 443b8064..77e2857b 100644 --- a/README.md +++ b/README.md @@ -193,7 +193,7 @@ When the user types `/graphify`, invoke the Skill tool with `skill: "graphify"` /graphify add https://arxiv.org/abs/1706.03762 # fetch a paper, save, update graph /graphify add https://x.com/karpathy/status/... # fetch a tweet -/graphify add https://www.youtube.com/watch?v=... # download audio, transcribe, add to graph +/graphify add # download audio, transcribe, add to graph /graphify add https://... --author "Name" # tag the original author /graphify add https://... --contributor "Name" # tag who added it to the corpus @@ -267,7 +267,7 @@ pip install 'graphifyy[video]' # one-time setup Add a YouTube video (or any public video URL) directly: ```bash -/graphify add https://www.youtube.com/watch?v=... +/graphify add ``` yt-dlp downloads audio-only (fast, small), Whisper transcribes it locally, and the transcript is fed into the same extraction pipeline as your other docs. Transcripts are cached in `graphify-out/transcripts/` so re-runs skip already-transcribed files.