{"id":27995,"library":"nucliadb-dataset","title":"NucliaDB Dataset","description":"Python client for exporting and managing datasets from NucliaDB, a semantic search engine for unstructured data. Version 6.13.0.post6240 supports Python 3.10+. Actively maintained on GitHub.","status":"active","version":"6.13.0.post6240","language":"python","source_language":"en","source_url":"https://github.com/nuclia/nucliadb","tags":["dataset","nucliadb","machine-learning","export","client"],"install":[{"cmd":"pip install nucliadb-dataset","lang":"bash","label":"default"}],"dependencies":[{"reason":"Core client for interacting with NucliaDB API","package":"nucliadb-client","optional":false}],"imports":[{"note":"Wrong package path; correct import is from nucliadb_dataset directly","wrong":"from nucliadb.dataset import ...","symbol":"NucliaDataset","correct":"from nucliadb_dataset import NucliaDataset"}],"quickstart":{"code":"from nucliadb_dataset import NucliaDataset\nimport os\n\n# Initialize with your NucliaDB API key\napi_key = os.environ.get('NUCLIADB_API_KEY', '')\ndataset = NucliaDataset(api_key=api_key, endpoint='https://your-nucliadb-instance')\n\n# List available datasets\ndatasets = dataset.list()\nprint(datasets)\n\n# Fetch a specific dataset by ID\nif datasets:\n    ds = dataset.get(datasets[0]['id'])\n    print(ds)","lang":"python","description":"Basic usage: initialize client, list and retrieve datasets."},"warnings":[{"fix":"Update method calls: `list()` and `get()` instead of `list_datasets()` and `get_dataset()`.","message":"In v6.0+, the dataset API was restructured. Methods like `list_datasets()` were renamed to `list()` and `get_dataset()` to `get()`. Old code using deprecated method names will fail.","severity":"breaking","affected_versions":">=6.0.0"},{"fix":"Replace `region='europe-1'` with `endpoint='https://europe-1.nucliadb.com'`.","message":"The `NucliaDataset` constructor no longer accepts a `region` parameter; use `endpoint` instead.","severity":"deprecated","affected_versions":">=6.5.0"},{"fix":"Always use keyword argument: `NucliaDataset(api_key='...', endpoint='...')`.","message":"API key is required and must be passed as keyword argument `api_key`. Passing it as positional argument causes TypeError.","severity":"gotcha","affected_versions":"all"}],"env_vars":null,"last_verified":"2026-05-09T00:00:00.000Z","next_check":"2026-08-07T00:00:00.000Z","problems":[{"fix":"Run `pip install nucliadb-dataset` and verify version >=6.0.0.","cause":"Package not installed or installed with wrong name. Also possible version mismatch.","error":"ImportError: cannot import name 'NucliaDataset' from 'nucliadb_dataset'"},{"fix":"Pass `api_key` as keyword argument: `NucliaDataset(api_key='your-key')`.","cause":"API key not provided or passed incorrectly.","error":"TypeError: __init__() missing 1 required positional argument: 'api_key'"}],"ecosystem":"pypi","meta_description":null,"install_score":null,"install_tag":null,"quickstart_score":null,"quickstart_tag":null}