petal-power/second-brain
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
repo for storing the second brain project
21 Commits 4 Branches 0 Tags 1.1 MiB
Python 82.4%
HTML 15.5%
Shell 1%
Dockerfile 0.9%
Mako 0.2%
d055d1798d
Go to file
Travis Herbranson d055d1798d transcripts: capture segment-level output into a new JSONB column 
Tower worker now persists faster-whisper's segment-level output
(start/end/text + word-level timing when available) alongside the
existing joined `transcript_text`. The text column stays the canonical
input the extractor reads — this is additive.

Changes:

- alembic v4: sources.transcript_segments JSONB NULL. JSONB rather than
  JSON so future equality/containment queries are indexable without a
  re-migration. Same lovebug-no-CREATE-on-petalbrain guard as prior
  migrations.

- ORM model: Optional[list] mapped to JSONB (postgresql dialect).

- transcribe.py:
  - Always pass word_timestamps=True to faster-whisper.transcribe.
  - New segment_to_dict() flattens the upstream NamedTuple-shaped
    Segment/Word into JSON-safe plain dicts so the JSONB write doesn't
    drag faster-whisper into any reader.
  - Per-word defensive conversion: a single malformed word can't drop
    the surrounding segment.

- transcribe_worker._advance: after a successful transcribe, persist
  segments into source.transcript_segments inside a try/except. If the
  JSONB write fails (oversize row, malformed dict, etc.) we log a
  warning and still commit transcript_text + status=TRANSCRIBED — the
  pipeline never crashes over the additive index.

- Tests: three new unit tests against fake Segment/Word objects cover
  the happy path (word entries serialise), the no-words case
  (`segment.words is None` → empty list), and the malformed-word skip.
  json.dumps(d) asserts JSONB-binding compatibility.

Live-verified: migration applied clean against petalbrain (`\d sources`
shows transcript_segments jsonb); ORM round-trip writes and reads the
sample payload identically. GPU large-v3 word-timestamp behaviour is
unchanged from upstream — only the tower can validate that hot path.
2026-05-25 13:40:49 -04:00
alembic transcripts: capture segment-level output into a new JSONB column 2026-05-25 13:40:49 -04:00
config postgres migration: schema, models, embeddings, alembic 2026-05-24 22:46:48 -04:00
deploy deploy/web: containerized FastAPI UI on the homelab docker network 2026-05-25 11:48:37 -04:00
prompts project init 2026-05-22 19:08:22 -04:00
reviews docs: update CLAUDE.md + migration plan to reflect shipped Postgres design 2026-05-24 22:57:31 -04:00
src/second_brain transcripts: capture segment-level output into a new JSONB column 2026-05-25 13:40:49 -04:00
tests transcripts: capture segment-level output into a new JSONB column 2026-05-25 13:40:49 -04:00
.gitignore add .gitignore 2026-05-24 21:10:53 -04:00
alembic.ini postgres migration: schema, models, embeddings, alembic 2026-05-24 22:46:48 -04:00
CLAUDE.md docs: update CLAUDE.md + migration plan to reflect shipped Postgres design 2026-05-24 22:57:31 -04:00
postgres-migration-planning.md docs: update CLAUDE.md + migration plan to reflect shipped Postgres design 2026-05-24 22:57:31 -04:00
pyproject.toml pipeline split: tower transcribe worker + claim queue + faster-whisper 2026-05-25 10:11:37 -04:00
README.md updates to project files 2026-05-24 22:23:59 -04:00
uv.lock pipeline split: tower transcribe worker + claim queue + faster-whisper 2026-05-25 10:11:37 -04:00

README.md

second-brain

A personal knowledge system built on a video/article extraction pipeline and an LLM-maintained wiki (inspired by the Karpathy LLM Wiki pattern).

What it does

  1. Pull — download YouTube videos or fetch web articles
  2. Transcribe — extract transcripts via Whisper (videos) or trafilatura (articles)
  3. Extract — single-shot Claude call produces structured notes per source
  4. Review — web UI to accept or reject extractions
  5. Compile — wiki compiler folds accepted extractions into a living Obsidian vault

Quick start

# Install dependencies
uv sync

# Copy and edit config
cp config/settings.toml config/settings.local.toml

# Queue a source
uv run second-brain add https://www.youtube.com/watch?v=...

# Run the pipeline
uv run second-brain process

# Review in the web UI
uv run second-brain serve

# Compile to wiki
uv run second-brain compile

Domains

Extractions are tagged by domain so the right prompt template is used:

Domain Focus
development Software, programming, systems
content Content creation, video production
business Entrepreneurship, marketing, ops
homelab Self-hosted infra, networking, DevOps

Extractor backends

Two backends, selectable via [extractor].backend in config/settings.toml:

  • cli (default) — shells out to claude -p --output-format json --json-schema .... Runs under your Max OAuth subscription, no per-token billing. The wrapper spawns the CLI in a throwaway tempfile.TemporaryDirectory and strips ANTHROPIC_API_KEY / ANTHROPIC_AUTH_TOKEN from the env so host CLAUDE.md, hooks, and settings don't leak in, and the subscription is used instead of the API key.
  • api — uses the anthropic Python SDK, requires ANTHROPIC_API_KEY. Install with uv sync --extra api (the SDK is an optional dependency).

Requirements

  • Python 3.12+
  • Either the claude CLI on PATH (default backend) or ANTHROPIC_API_KEY (api backend)
  • ffmpeg (for Whisper audio extraction)

In-flight work

  • Postgres + pgvector migration — SQLite is the current backing store but the project is moving to Travis's Postgres instance. Planning questions live in postgres-migration-planning.md; nothing has been migrated yet.