Course: Building Applications with Vector databases
When I am running the lab i consistently get an error
File /usr/local/lib/python3.10/site-packages/datasets/load.py:2128, in load_dataset(path, name, data_dir, data_files, split, cache_dir, features, download_config, download_mode, verification_mode, ignore_verifications, keep_in_memory, save_infos, revision, token, use_auth_token, task, streaming, num_proc, storage_options, **config_kwargs)
2123 verification_mode = VerificationMode(
2124 (verification_mode or VerificationMode.BASIC_CHECKS) if not save_infos else VerificationMode.ALL_CHECKS
2125 )
2127 # Create a dataset builder
→ 2128 builder_instance = load_dataset_builder(
2129 path=path,
2130 name=name,
2131 data_dir=data_dir,
2132 data_files=data_files,
2133 cache_dir=cache_dir,
2134 features=features,
2135 download_config=download_config,
2136 download_mode=download_mode,
2137 revision=revision,
2138 token=token,
2139 storage_options=storage_options,
2140 **config_kwargs,
2141 )
2143 # Return iterable dataset in case of streaming
2144 if streaming:
File /usr/local/lib/python3.10/site-packages/datasets/load.py:1814, in load_dataset_builder(path, name, data_dir, data_files, cache_dir, features, download_config, download_mode, revision, token, use_auth_token, storage_options, **config_kwargs)
1812 download_config = download_config.copy() if download_config else DownloadConfig()
1813 download_config.storage_options.update(storage_options)
→ 1814 dataset_module = dataset_module_factory(
1815 path,
1816 revision=revision,
1817 download_config=download_config,
1818 download_mode=download_mode,
1819 data_dir=data_dir,
1820 data_files=data_files,
1821 )
1822 # Get dataset builder class from the processing script
1823 builder_kwargs = dataset_module.builder_kwargs
File /usr/local/lib/python3.10/site-packages/datasets/load.py:1511, in dataset_module_factory(path, revision, download_config, download_mode, dynamic_modules_path, data_dir, data_files, **download_kwargs)
1506 if isinstance(e1, FileNotFoundError):
1507 raise FileNotFoundError(
1508 f"Couldn’t find a dataset script at {relative_to_absolute_path(combined_path)} or any data file in the same directory. "
1509 f"Couldn’t find ‘{path}’ on the Hugging Face Hub either: {type(e1).name}: {e1}"
1510 ) from None
→ 1511 raise e1 from None
1512 else:
1513 raise FileNotFoundError(
1514 f"Couldn’t find a dataset script at {relative_to_absolute_path(combined_path)} or any data file in the same directory."
1515 )
File /usr/local/lib/python3.10/site-packages/datasets/load.py:1478, in dataset_module_factory(path, revision, download_config, download_mode, dynamic_modules_path, data_dir, data_files, **download_kwargs)
1474 raise FileNotFoundError(
1475 msg + “. If the repo is private or gated, make sure to log in with huggingface-cli login
.”
1476 )
1477 else:
→ 1478 raise e
1479 if filename in [sibling.rfilename for sibling in dataset_info.siblings]:
1480 return HubDatasetModuleFactoryWithScript(
1481 path,
1482 revision=revision,
(…)
1485 dynamic_modules_path=dynamic_modules_path,
1486 ).get_module()
File /usr/local/lib/python3.10/site-packages/datasets/load.py:1452, in dataset_module_factory(path, revision, download_config, download_mode, dynamic_modules_path, data_dir, data_files, **download_kwargs)
1450 hf_api = HfApi(config.HF_ENDPOINT)
1451 try:
→ 1452 dataset_info = hf_api.dataset_info(
1453 repo_id=path,
1454 revision=revision,
1455 token=download_config.token,
1456 timeout=100.0,
1457 )
1458 except Exception as e: # noqa catch any exception of hf_hub and consider that the dataset doesn’t exist
1459 if isinstance(
1460 e,
1461 (
(…)
1465 ),
1466 ):
File /usr/local/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py:118, in validate_hf_hub_args.._inner_fn(*args, **kwargs)
115 if check_use_auth_token:
116 kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.name, has_token=has_token, kwargs=kwargs)
→ 118 return fn(*args, **kwargs)
File /usr/local/lib/python3.10/site-packages/huggingface_hub/hf_api.py:2150, in HfApi.dataset_info(self, repo_id, revision, timeout, files_metadata, token)
2148 hf_raise_for_status(r)
2149 data = r.json()
→ 2150 return DatasetInfo(**data)
File /usr/local/lib/python3.10/site-packages/huggingface_hub/hf_api.py:770, in DatasetInfo.init(self, **kwargs)
768 self.likes = kwargs.pop(“likes”)
769 self.paperswithcode_id = kwargs.pop(“paperswithcode_id”, None)
→ 770 self.tags = kwargs.pop(“tags”)
771 card_data = kwargs.pop(“cardData”, None) or kwargs.pop(“card_data”, None)
772 self.card_data = (
773 DatasetCardData(**card_data, ignore_metadata_errors=True) if isinstance(card_data, dict) else card_data
774 )
KeyError: ‘tags’