thegeneralist01/archivr
1
Fork 0
mirror of https://github.com/thegeneralist01/archivr synced 2026-10-09 12:55:00 +02:00
Code Issues Activity

feat: add YouTube subtitles, local transcription, self-updating yt-dlp/Deno, X Article and thread titles (#39)

Browse source 
- Capture YouTube subtitles by default (opt-out in UI, API, CLI --no-subtitles)
- Summarize YouTube videos from subtitles; fetch on demand, then local transcription, then error
- Local transcription fallback: Whisper, Parakeet, Phonon-2 (English only)
- Runtime-resolved, self-updating yt-dlp and Deno JS runtime (fixes YouTube 403s)
- Settings > Instance > yt-dlp: status and in-app update without restart
- X Article titles from article.title, with idempotent startup backfill
- Thread title generation (single and bulk) with per-provider cheap models
- Per-provider title model settings in Settings > Instance
- Docs, mental model, AGENTS.md and transcription spec updated
This commit is contained in:
TheGeneralist 2026-10-05 19:41:06 +02:00 • committed by GitHub
parent 4f3b2968b6
commit 094f1b0457
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
35 changed files with 11377 additions and 583 deletions
Download patch file Download diff file Expand all files Collapse all files

18
flake.nix
View file

@ -225,6 +225,7 @@
ytDlp
pkgs.single-file-cli
tweetPython
pkgs.deno
] ++ lib.optionals pkgs.stdenv.isLinux [ pkgs.chromium ];
phases = [ "installPhase" ];
installPhase = ''
@ -232,8 +233,12 @@
cp ${archivr_cli_unwrapped}/bin/archivr $out/libexec/archivr/archivr
cp ${./vendor/twitter/scrape_user_tweet_contents.py} $out/libexec/archivr/scrape_user_tweet_contents.py
chmod +x $out/libexec/archivr/scrape_user_tweet_contents.py
# Pinned Deno is the fallback JS runtime for yt-dlp's YouTube challenge
# solver; a newer state-dir copy from `archivr yt-dlp update` takes precedence.
makeWrapper $out/libexec/archivr/archivr $out/bin/archivr \
--set ARCHIVR_YT_DLP ${ytDlp}/bin/yt-dlp \
--set ARCHIVR_DENO ${pkgs.deno}/bin/deno \
--set ARCHIVR_FFMPEG ${pkgs.ffmpeg}/bin/ffmpeg \
--set ARCHIVR_SINGLE_FILE ${pkgs.single-file-cli}/bin/single-file \
${lib.optionalString pkgs.stdenv.isLinux "--set ARCHIVR_CHROME ${pkgs.chromium}/bin/chromium"} \
--set ARCHIVR_TWEET_PYTHON ${tweetPython}/bin/python3 \
@ -245,6 +250,7 @@
ytDlp
pkgs.single-file-cli
tweetPython
pkgs.deno
] ++ lib.optionals pkgs.stdenv.isLinux [ pkgs.chromium ])
}
'';
@ -253,7 +259,7 @@
pname = "archivr-server-wrapped";
inherit version;
nativeBuildInputs = [ pkgs.makeWrapper ];
buildInputs = [ ytDlp tweetPython pkgs.single-file-cli ] ++ lib.optionals pkgs.stdenv.isLinux [ pkgs.chromium ];
buildInputs = [ ytDlp tweetPython pkgs.single-file-cli pkgs.deno ] ++ lib.optionals pkgs.stdenv.isLinux [ pkgs.chromium ];
phases = [ "installPhase" ];
installPhase = ''
mkdir -p $out/bin $out/libexec/archivr-server $out/share/archivr-server/static
@ -261,16 +267,20 @@
cp ${./vendor/twitter/scrape_user_tweet_contents.py} $out/libexec/archivr-server/scrape_user_tweet_contents.py
chmod +x $out/libexec/archivr-server/scrape_user_tweet_contents.py
cp -r ${frontendStatic}/* $out/share/archivr-server/static/
# Pinned Deno is the fallback JS runtime for yt-dlp's YouTube challenge
# solver; a newer state-dir copy from `archivr yt-dlp update` takes precedence.
makeWrapper $out/libexec/archivr-server/archivr-server $out/bin/archivr-server \
--set ARCHIVR_STATIC_DIR $out/share/archivr-server/static \
--set ARCHIVR_YT_DLP ${ytDlp}/bin/yt-dlp \
--set ARCHIVR_DENO ${pkgs.deno}/bin/deno \
--set ARCHIVR_FFMPEG ${pkgs.ffmpeg}/bin/ffmpeg \
--set ARCHIVR_SINGLE_FILE ${pkgs.single-file-cli}/bin/single-file \
${lib.optionalString pkgs.stdenv.isLinux "--set ARCHIVR_CHROME ${pkgs.chromium}/bin/chromium"} \
--set ARCHIVR_TWEET_PYTHON ${tweetPython}/bin/python3 \
--set ARCHIVR_TWEET_SCRAPER $out/libexec/archivr-server/scrape_user_tweet_contents.py \
--set ARCHIVR_UBLOCK_EXT ${ublockLite} \
--set ARCHIVR_COOKIE_EXT ${isdcac} \
--prefix PATH : ${lib.makeBinPath ([ ytDlp pkgs.single-file-cli tweetPython ] ++ lib.optionals pkgs.stdenv.isLinux [ pkgs.chromium ])}
--prefix PATH : ${lib.makeBinPath ([ ytDlp pkgs.single-file-cli tweetPython pkgs.deno ] ++ lib.optionals pkgs.stdenv.isLinux [ pkgs.chromium ])}
'';
};
archivr-all = pkgs.symlinkJoin {
@ -339,11 +349,13 @@
pkgs.yt-dlp
pkgs.nushell
pkgs.uv
pkgs.deno
pkgs.ffmpeg
tweetPython
];
shellHook = ''
export SHELL=${pkgs.nushell}/bin/nu
echo "nushell dev shell active – yt-dlp, uv, and tweet scraper Python on PATH"
echo "nushell dev shell active – yt-dlp, deno, uv, and tweet scraper Python on PATH"
nu
'';
};