{"id":27066028,"url":"https://github.com/weaviate-tutorials/weaviate-vibe-eval","last_synced_at":"2025-04-09T19:52:03.838Z","repository":{"id":285903742,"uuid":"959707723","full_name":"weaviate-tutorials/weaviate-vibe-eval","owner":"weaviate-tutorials","description":null,"archived":false,"fork":false,"pushed_at":"2025-04-03T09:16:23.000Z","size":84,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-03T09:28:09.150Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/weaviate-tutorials.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2025-04-03T08:14:53.000Z","updated_at":"2025-04-03T09:23:41.000Z","dependencies_parsed_at":"2025-04-03T09:28:17.342Z","dependency_job_id":"e2f99066-1b71-42f9-83bc-4ddf4b35d4d7","html_url":"https://github.com/weaviate-tutorials/weaviate-vibe-eval","commit_stats":null,"previous_names":["weaviate-tutorials/weaviate-vibe-eval"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weaviate-tutorials%2Fweaviate-vibe-eval","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weaviate-tutorials%2Fweaviate-vibe-eval/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weaviate-tutorials%2Fweaviate-vibe-eval/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weaviate-tutorials%2Fweaviate-vibe-eval/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/weaviate-tutorials","download_url":"https://codeload.github.com/weaviate-tutorials/weaviate-vibe-eval/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248103903,"owners_count":21048244,"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","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":"2025-04-05T18:34:45.906Z","updated_at":"2025-04-09T19:52:03.812Z","avatar_url":"https://github.com/weaviate-tutorials.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Weaviate Vibe Check\n\nEvaluate LLMs on their ability to generate correct Weaviate code in zero-shot and few-shot scenarios.\n\n## How it works\n\nThis repo contains a script `check_weaviate_vibes.py` that runs a set of benchmarks on a given LLM.\n\nEach benchmark includes a task and a canonical implementation. The LLM is scored on its ability to generate correct Weaviate code for each task.\n\nThe generated task is run through a Docker container to automatically check the code, and the results are saved to the `results` directory.\n\nThere are variants of each benchmark, so that the LLM can be evaluated on its ability to generate correct Weaviate code as a zero-shot, or with various types of in-context examples.\n\n## Supported Models\n\n- API-based: OpenAI, Anthropic, Claude, Gemini\n- Local: Ollama-based models (planned)\n\n## Benchmark Tasks\n\n- Connect to Weaviate Cloud\n- Create and manage collections\n- Batch import\n- Querying (semantic, filters, hybrid)\n\n## Setup\n\n```bash\n# Clone repository\ngit clone git@github.com:weaviate-tutorials/weaviate-vibe-eval.git\ncd weaviate-vibe-eval\n\n# Set up environment\npython -m venv .venv\nsource .venv/bin/activate  # or .venv\\Scripts\\activate on Windows\npip install -e .\n# This should install all main dependencies - if not, see requirements.txt / pyproject.toml\n\n# Set environment variables\n# Create a .env file with your API keys:\n# ANTHROPIC_API_KEY=your_key\n# COHERE_API_KEY=your_key\n# GEMINI_API_KEY=your_key\n# OPENAI_API_KEY=your_key\n# WCD_TEST_URL=your_weaviate_cloud_url\n# WCD_TEST_KEY=your_weaviate_api_key\n\n# Build docker image\nSee [docker/README.md](docker/README.md)\n```\n\n## Usage\n\n```bash\n# Run all benchmarks\npython check_weaviate_vibes.py\n\n# Run specific tests\n# (See documentation for additional options)\n```\n\n## Project Structure\n\n```\nweaviate_vibe_eval/       # Main package\n  ├── benchmarks/         # Benchmark definitions and runner\n  ├── models/             # LLM provider implementations\n  └── utils/              # Shared utilities (Docker, code execution)\ntests/                    # Test suite\ndocker/                   # Docker environment for safe code execution\nresults/                  # Benchmark results output\n```\n\n## License\nMIT License\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fweaviate-tutorials%2Fweaviate-vibe-eval","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fweaviate-tutorials%2Fweaviate-vibe-eval","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fweaviate-tutorials%2Fweaviate-vibe-eval/lists"}