# Data source adapters (install only what you need) kbcstorage>=0.9.0 # For Keboola adapter google-cloud-bigquery>=3.0.0 # For BigQuery adapter google-cloud-bigquery-storage>=2.0.0 # For BigQuery adapter (fast Arrow transfer) # Data processing # pandas - core tabular data processing library # pyarrow - Parquet format support and fast operations # pytz - timezone support required by DuckDB for reading timezone-aware Parquet columns pandas>=2.0.0 pyarrow>=12.0.0 pytz>=2024.1 # Analytical database # DuckDB - in-process SQL OLAP database for analytical queries duckdb>=0.9.0 # Configuration # python-dotenv - loading environment variables from .env files # pyyaml - parsing YAML configuration from data_description.md python-dotenv>=1.0.0 pyyaml>=6.0 # Progress tracking and logging # tqdm - progress bars for long-running operations (download, sync) tqdm>=4.65.0 # Web application (Google SSO portal) # flask - web framework for self-service portal # authlib - OAuth 2.0 / OpenID Connect library for Google SSO # gunicorn - WSGI server for production deployment flask>=3.0.0 authlib>=1.3.0 gunicorn>=21.0.0 # Telegram notification bot # httpx - async HTTP client for Telegram API and unix socket communication # aiohttp - async HTTP server for bot's internal send API httpx>=0.27.0 aiohttp>=3.9.0 matplotlib>=3.8.0 numpy>=1.24.0 # Desktop app authentication # PyJWT - JWT token creation and validation for desktop app auth PyJWT>=2.8.0 # Password authentication for external users # argon2-cffi - modern password hashing algorithm (Argon2id) # sendgrid - email service for setup/reset links argon2-cffi>=23.1.0 sendgrid>=6.11.0 # Corporate Memory knowledge extraction # anthropic - Claude API client for HAIKU-based knowledge extraction anthropic>=0.39.0 # OpenAI-compatible API client for LLM proxy routing (LiteLLM, OpenRouter, etc.) openai>=1.0.0 # Sample data generation (development/testing) # faker - realistic synthetic data for demo datasets faker>=24.0.0