dolgolyov.alexei
8b8fe916f0
Backend:
- Document + MemoryEntry models with Alembic migration (GIN FTS index)
- File upload endpoint with path traversal protection (sanitized filenames)
- Background document text extraction (PyMuPDF)
- Full-text search on extracted_text via PostgreSQL tsvector/tsquery
- Memory CRUD with enum-validated categories/importance, field allow-list
- AI tools: save_memory, search_documents, get_memory (Claude function calling)
- Tool execution loop in stream_ai_response (multi-turn tool use)
- Context assembly: injects critical memory + relevant doc excerpts
- File storage abstraction (local filesystem, S3-swappable)
- Secure file deletion (DB flush before disk delete)
Frontend:
- Document upload dialog (drag-and-drop + file picker)
- Document list with status badges, search, download (via authenticated blob)
- Document viewer with extracted text preview
- Memory list grouped by category with importance color coding
- Memory editor with category/importance dropdowns
- Documents + Memory pages with full CRUD
- Enabled sidebar navigation for both sections
Review fixes applied:
- Sanitized upload filenames (path traversal prevention)
- Download via axios blob (not bare <a href>, preserves auth)
- Route ordering: /search before /{id}/reindex
- Memory update allows is_active=False + field allow-list
- MemoryEditor form resets on mode switch
- Literal enum validation on category/importance schemas
- DB flush before file deletion for data integrity
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Personal AI Assistant
A client-server web application for managing personal health and life areas with AI-powered assistance. Upload documents, chat with AI specialists, receive proactive health reminders, and track critical information across multiple life domains.
Key Features
- AI Chat with Specialists — create chats using configurable skills (e.g., cardiologist, nutritionist). Each skill shapes the AI's behavior as a domain expert.
- Document Management — upload health records, lab results, prescriptions, and consultation notes. AI extracts and indexes content for intelligent retrieval.
- Proactive Notifications — AI analyzes your health profile and schedules reminders (checkups, medication reviews) via in-app, email, or Telegram.
- PDF Compilation — request AI-generated health summaries as downloadable PDF documents.
- Global Memory — AI maintains a shared memory of critical health information across all your chats.
- Multi-language — English and Russian support.
Tech Stack
| Layer | Technology |
|---|---|
| Backend | Python 3.12, FastAPI, SQLAlchemy 2.0, Alembic |
| Frontend | React 18, TypeScript, Vite, Shadcn/ui, Tailwind CSS |
| Database | PostgreSQL 16 |
| AI | Claude API (Anthropic) |
| Notifications | WebSocket, Email (SMTP), Telegram Bot |
| Deployment | Docker Compose |
Getting Started
Prerequisites: Docker and Docker Compose installed.
# Clone the repository
git clone https://git.dolgolyov-family.by/alexei.dolgolyov/personal-ai-assistant.git
cd personal-ai-assistant
# Copy environment config
cp .env.example .env
# Edit .env with your API keys and settings
# Start all services
docker compose up -d
# Create initial admin user
docker compose exec backend python scripts/seed_admin.py
The app will be available at http://localhost.
Project Structure
personal-ai-assistant/
├── backend/ # FastAPI application
├── frontend/ # React SPA
├── telegram-bot/ # Telegram notification bot
├── nginx/ # Reverse proxy config
├── plans/ # Phase subplans
├── docker-compose.yml
└── GeneralPlan.md # Full implementation plan
License
Private project. All rights reserved.