{"id":48353680,"url":"https://github.com/codepawl/featcat","last_synced_at":"2026-04-09T14:01:22.246Z","repository":{"id":348894653,"uuid":"1200249827","full_name":"codepawl/featcat","owner":"codepawl","description":"AI-Powered Feature Catalog for teams","archived":false,"fork":false,"pushed_at":"2026-04-07T09:14:06.000Z","size":681,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-07T12:02:26.311Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/codepawl.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-03T07:38:53.000Z","updated_at":"2026-04-07T09:14:09.000Z","dependencies_parsed_at":null,"dependency_job_id":"215da03c-5188-46c6-a398-8f39014c533b","html_url":"https://github.com/codepawl/featcat","commit_stats":null,"previous_names":["codepawl/featcat"],"tags_count":6,"template":false,"template_full_name":null,"purl":"pkg:github/codepawl/featcat","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codepawl%2Ffeatcat","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codepawl%2Ffeatcat/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codepawl%2Ffeatcat/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codepawl%2Ffeatcat/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/codepawl","download_url":"https://codeload.github.com/codepawl/featcat/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/codepawl%2Ffeatcat/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31556239,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-08T10:21:54.569Z","status":"ssl_error","status_checked_at":"2026-04-08T10:21:38.171Z","response_time":54,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-04-05T10:04:50.579Z","updated_at":"2026-04-08T13:00:47.248Z","avatar_url":"https://github.com/codepawl.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# featcat\n\n![CI](https://github.com/codepawl/featcat/actions/workflows/ci.yml/badge.svg)\n![PyPI](https://img.shields.io/pypi/v/featcat)\n![Python](https://img.shields.io/pypi/pyversions/featcat)\n![License](https://img.shields.io/pypi/l/featcat)\n\n**AI-Powered Feature Catalog for Data Science Teams**\n\n[Tiếng Việt](docs/README-vi.md)\n\nfeatcat is a lightweight Feature Catalog designed for Data Science teams. It is **not** a Feature Store (no online serving) — it's a metadata management tool with an AI layer for searching, documenting, and monitoring feature quality.\n\n## The Problem\n\n- **Features scattered everywhere**: Parquet files stored across local disks, S3, and MinIO — nobody knows what features exist\n- **Missing documentation**: Dataset columns have no descriptions; new team members don't know what `avg_session_duration` means\n- **Hard to find the right features**: Starting a new project (e.g. churn prediction) with no idea which features are already available\n- **Undetected data drift**: Feature distributions change silently until model performance degrades\n\n## Key Features\n\n| Module | Description | Phase |\n|--------|-------------|-------|\n| **Catalog** | Register data sources, scan Parquet to auto-extract schema + stats | 1 |\n| **AI Discovery** | Describe a use case → AI recommends relevant features + suggests new ones | 2 |\n| **Auto-doc** | LLM automatically generates documentation for each feature | 2 |\n| **NL Query** | Ask in natural language (English or Vietnamese), AI finds relevant features | 2 |\n| **Monitoring** | PSI drift detection, null spikes, range violations | 3 |\n| **TUI** | Terminal UI with dashboard, feature browser, AI chat | 3 |\n| **S3 Support** | Read Parquet directly from S3/MinIO — never copies data locally | 1 |\n| **Caching** | Cache LLM responses to speed up doc generation and NL queries | 3 |\n\n## Quick Start\n\n```bash\n# 1. Clone and install\ngit clone https://github.com/codepawl/featcat.git \u0026\u0026 cd featcat\nuv venv \u0026\u0026 source .venv/bin/activate\nuv pip install -e \".[dev]\"\n\n# 2. Initialize catalog\nfeatcat init\n\n# 3. Register and scan a data source\nfeatcat source add device_perf /data/features/device_performance.parquet\nfeatcat source scan device_perf\n\n# 4. Browse features\nfeatcat feature list\nfeatcat feature info device_perf.cpu_usage\n\n# 5. (Optional) Enable AI features — requires Ollama\nollama serve \u0026\nollama pull qwen2.5:7b\nfeatcat discover \"churn prediction for telecom customers\"\nfeatcat ask \"features related to user behavior\"\n```\n\n## TUI (Terminal UI)\n\n```bash\nuv pip install -e \".[tui]\"\nfeatcat ui\n```\n\n\u003c!-- Screenshot placeholder --\u003e\n\u003c!-- ![featcat TUI](docs/assets/tui-screenshot.png) --\u003e\n\nKeybindings: `D` Dashboard | `F` Features | `M` Monitor | `C` Chat | `Q` Quit | `?` Help\n\n## System Health Check\n\n```bash\nfeatcat doctor\n```\n\n```\n[x] Python 3.10+\n[x] SQLite catalog exists (catalog.db)\n[x] Ollama running at localhost:11434\n[x] Model qwen2.5:7b available\n[x] 14 features registered\n[x] 10 features have docs (71.4%)\n[ ] 2 features have drift warnings\n```\n\n## Tech Stack\n\n- **Python 3.10+** | **SQLite** (metadata only, never copies data)\n- **Typer** + **Rich** (CLI) | **Textual** (TUI)\n- **PyArrow** (Parquet schema + stats) | **s3fs** (S3/MinIO)\n- **Ollama** (local LLM) | **Pydantic** (models + config)\n\n## Project Structure\n\n```\nfeatcat/\n├── catalog/        # Models, DB, scanner, storage backends\n├── llm/            # LLM abstraction (Ollama, llama.cpp)\n├── plugins/        # Discovery, Autodoc, Monitoring, NL Query\n├── utils/          # Prompts, catalog context, statistics, cache\n├── tui/            # Textual TUI (screens, widgets)\n├── config.py       # Pydantic settings\n└── cli.py          # Typer CLI entry point\n```\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodepawl%2Ffeatcat","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcodepawl%2Ffeatcat","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodepawl%2Ffeatcat/lists"}