{"id":32745809,"url":"https://github.com/aalexuser/fedot-assistant","last_synced_at":"2026-02-21T05:04:58.496Z","repository":{"id":282435854,"uuid":"943913096","full_name":"AaLexUser/Fedot-assistant","owner":"AaLexUser","description":"LLM-based multi-AutoML Orchestrator","archived":false,"fork":false,"pushed_at":"2025-07-21T07:57:27.000Z","size":13182,"stargazers_count":2,"open_issues_count":1,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-07-21T09:31:41.541Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://deepwiki.com/AaLexUser/Fedot-assistant","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AaLexUser.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"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}},"created_at":"2025-03-06T13:26:05.000Z","updated_at":"2025-07-21T07:57:31.000Z","dependencies_parsed_at":"2025-06-03T14:30:40.856Z","dependency_job_id":"321a036e-34cf-4bf6-bc57-f086df6b4f19","html_url":"https://github.com/AaLexUser/Fedot-assistant","commit_stats":null,"previous_names":["aalexuser/fedot-assistant"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/AaLexUser/Fedot-assistant","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AaLexUser%2FFedot-assistant","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AaLexUser%2FFedot-assistant/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AaLexUser%2FFedot-assistant/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AaLexUser%2FFedot-assistant/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AaLexUser","download_url":"https://codeload.github.com/AaLexUser/Fedot-assistant/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AaLexUser%2FFedot-assistant/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":282494924,"owners_count":26678640,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-11-03T02:00:05.676Z","response_time":108,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":"2025-11-03T17:06:16.236Z","updated_at":"2025-11-03T17:06:20.713Z","avatar_url":"https://github.com/AaLexUser.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# FEDOT.ASSISTANT\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./docs/FEDOT-ASSISTANT-logo.svg\" width=\"600\" alt=\"FEDOT.ASSISTANT logo\"\u003e\n\u003c/p\u003e\n\n[![Acknowledgement ITMO](https://raw.githubusercontent.com/aimclub/open-source-ops/43bb283758b43d75ec1df0a6bb4ae3eb20066323/badges/ITMO_badge.svg)](https://itmo.ru/)\n![Python](https://img.shields.io/badge/python-3.10-blue.svg)\n[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/AaLexUser/Fedot-assistant)\n\nFEDOT.ASSISTANT is an LLM-based prototype for next-generation AutoML. It combines the power of Large Language Models with automated machine learning techniques to enhance data analysis and pipeline building processes.\n\n## 🆕 What's New\n\n- CAAFE integration: LLM-driven feature engineering for tabular classification tasks. Enabled by default via `feature_transformers.enabled_models: [CAAFE]`. Requires installing the optional dependency group and setting an API key (see below).\n\n## 💾 Installation\n\n1. Install uv (A fast Python package installer and resolver):\n\n```bash\ncurl -LsSf https://astral.sh/uv/install.sh | sh\n```\n\n2. Clone the repository:\n\n```bash\ngit clone https://github.com/AaLexUser/Fedot-assistant.git\ncd Fedot-assistant\n```\n\n3. Create a new virtual environment and activate it:\n\n```bash\nuv venv --python 3.10\nsource .venv/bin/activate  # On Unix/macOS\n# Or on Windows:\n# .venv\\Scripts\\activate\n```\n\n4. Install dependencies:\n\n```bash\nuv sync\n```\n\nOptional (to use CAAFE feature generation):\n\n```bash\nuv sync --group caafe\n```\n\n## 🔧 Configuration\n\n### Environment Setup\n\nSet your OpenAI API key:\n\n```bash\nexport FEDOTLLM_LLM_API_KEY=\"your-api-key-here\"\n```\n\nOptional (CAAFE feature generation uses its own LLM settings; you can also put these into a `.env` file):\n\n```bash\nexport CAAFE_LLM_API_KEY=\"your-api-key-here\"\n# Optional overrides (defaults work with the example config)\nexport CAAFE_LLM_MODEL=\"openai/gemini-2.0-flash\"\nexport CAAFE_LLM_BASE_URL=\"https://generativelanguage.googleapis.com/v1beta/openai/\"\n```\n\n### Configuration Options\n\nThe system uses YAML configuration files you can customize. The default configuration is located at `fedotllm/configs/default.yaml`. You can create your own configuration file and specify it using the `--config-path` option.\n\n## 🚀 Quick Start\n\n### Basic Usage\n\n```bash\n# Run with default settings\nfedotllm /path/to/your/task/directory\n\n# Use specific presets\nfedotllm /path/to/your/task/directory --presets best_quality\n\n# Custom configuration\nfedotllm /path/to/your/task/directory --config-path config.yaml\n\n# Override specific settings\nfedotllm /path/to/your/task/directory -o automl.enabled=fedot -o time_limit=7200\n```\n\n### Enable or configure CAAFE (optional)\n\nCAAFE performs LLM-driven feature engineering and currently supports classification tasks only.\n\n```bash\n# Ensure optional deps are installed\nuv sync --group caafe\n\n# Run with CAAFE enabled (default), customizing parameters on the fly\nfedotllm /path/to/task \\\n  -o \"feature_transformers.enabled_models=[CAAFE]\" \\\n  -o \"feature_transformers.models.CAAFE.num_iterations=5\" \\\n  -o \"feature_transformers.models.CAAFE.optimization_metric=roc\" \\\n  -o \"feature_transformers.models.CAAFE.eval_model=lightgdm\"  # or tab_pfn\n```\n\n### Task Directory Structure\n\nYour task directory should contain:\n\n- Training data file (e.g., `train.csv`)\n- Test data file (e.g., `test.csv`)\n- Sample submission file (e.g., `sample_submission.csv`)\n- Task description file (e.g., `descriptions.txt`)\n\n### Quality Presets\n\n- `medium_quality`: Fast execution with good performance\n- `best_quality`: Maximum accuracy (default)\n\n## 🙌 Acknowledgement\nOur implementation adapts code from [AutoGluon Assistant](https://github.com/autogluon/autogluon-assistant). We thank authors of this project for providing high quality open source code!","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faalexuser%2Ffedot-assistant","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faalexuser%2Ffedot-assistant","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faalexuser%2Ffedot-assistant/lists"}