Nadir/backend/README.md
ZTatman 0c0ba74c09 Phase 1: restructure into backend/ and fix module import side effects
- Move all Python source files into backend/ directory
- Fix db.py: use absolute path (Path(__file__).parent) for chroma_db
  so the DB is always found regardless of where the server is launched from
- Fix store.py: guard test entry under if __name__ == "__main__" to
  prevent duplicate inserts on every import
- Fix query.py: extract query_entries(question) -> str function and
  move interactive loop under __main__ guard so it can be imported
  cleanly by FastAPI without blocking on input()
- Add .claude/launch.json with FastAPI dev server configuration

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-18 16:30:34 -04:00

1.3 KiB

Nadir — Voice Mood Diary

AI-powered voice journal with mood tracking and pattern discovery.

What It Does

  • Records voice entries and transcribes them to text
  • Uses AI to extract moods, triggers, and themes from entries
  • Stores entries in a local vector database (ChromaDB)
  • Lets you ask questions about your emotional patterns over time

Project Structure

├── main.py          # Entry point
├── app.py           # Streamlit UI
├── store.py         # Save entries to ChromaDB
├── query.py         # Query entries with RAG
├── db.py            # ChromaDB connection
├── models.py        # Data classes (MoodTag, JournalEntry)
├── PLAN.md          # [Full build plan](./PLAN.md)
├── chroma_db/       # Local vector database

Build Plan

See PLAN.md for detailed phases and step-by-step instructions.

Setup

# Install dependencies
uv sync

# Add your OpenAI API key to .env
echo "OPENAI_API_KEY=your_key_here" > .env

Running

# Run the Streamlit app
uv run streamlit run main.py

# Or run the query CLI
uv run python query.py

Status

Currently in Phase 2-3 of the build plan. Core storage and querying work; voice recording and AI metadata extraction coming next.