Skip to content

Load

default_ngc_client()

Create a default NGC client.

This should load the NGC API key from ~/.ngc/config, or from environment variables passed to the docker container.

Source code in bionemo/core/data/load.py
72
73
74
75
76
77
def default_ngc_client() -> ngcsdk.Client:
    """Create a default NGC client.

    This should load the NGC API key from ~/.ngc/config, or from environment variables passed to the docker container.
    """
    return ngcsdk.Client()

default_pbss_client()

Create a default S3 client for PBSS.

Source code in bionemo/core/data/load.py
47
48
49
50
def default_pbss_client():
    """Create a default S3 client for PBSS."""
    retry_config = Config(retries={"max_attempts": 10, "mode": "standard"})
    return boto3.client("s3", endpoint_url="https://pbss.s8k.io", config=retry_config)

load(model_or_data_tag, source=DEFAULT_SOURCE, resources=None, cache_dir=None)

Download a resource from PBSS or NGC.

Parameters:

Name Type Description Default
model_or_data_tag str

A pointer to the desired resource. Must be a key in the resources dictionary.

required
source SourceOptions

Either "pbss" (NVIDIA-internal download) or "ngc" (NVIDIA GPU Cloud). Defaults to "pbss".

DEFAULT_SOURCE
resources dict[str, Resource] | None

A custom dictionary of resources. If None, the default resources will be used. (Mostly for testing.)

None
cache_dir Path | None

The directory to store downloaded files. Defaults to BIONEMO_CACHE_DIR. (Mostly for testing.)

None

Raises:

Type Description
ValueError

If the desired tag was not found, or if an NGC url was requested but not provided.

Returns:

Type Description
Path

A Path object pointing either at the downloaded file, or at a decompressed folder containing the

Path

file(s).

Examples:

For a resource specified in 'filename.yaml' with tag 'tag', the following will download the file:

>>> load("filename/tag")
PosixPath(/tmp/bionemo/downloaded-file-name)
Source code in bionemo/core/data/load.py
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
def load(
    model_or_data_tag: str,
    source: SourceOptions = DEFAULT_SOURCE,
    resources: dict[str, Resource] | None = None,
    cache_dir: Path | None = None,
) -> Path:
    """Download a resource from PBSS or NGC.

    Args:
        model_or_data_tag: A pointer to the desired resource. Must be a key in the resources dictionary.
        source: Either "pbss" (NVIDIA-internal download) or "ngc" (NVIDIA GPU Cloud). Defaults to "pbss".
        resources: A custom dictionary of resources. If None, the default resources will be used. (Mostly for testing.)
        cache_dir: The directory to store downloaded files. Defaults to BIONEMO_CACHE_DIR. (Mostly for testing.)

    Raises:
        ValueError: If the desired tag was not found, or if an NGC url was requested but not provided.

    Returns:
        A Path object pointing either at the downloaded file, or at a decompressed folder containing the
        file(s).

    Examples:
        For a resource specified in 'filename.yaml' with tag 'tag', the following will download the file:
        >>> load("filename/tag")
        PosixPath(/tmp/bionemo/downloaded-file-name)
    """
    if resources is None:
        resources = get_all_resources()

    if cache_dir is None:
        cache_dir = BIONEMO_CACHE_DIR

    if model_or_data_tag not in resources:
        raise ValueError(f"Resource '{model_or_data_tag}' not found.")

    if source == "ngc" and resources[model_or_data_tag].ngc is None:
        raise ValueError(f"Resource '{model_or_data_tag}' does not have an NGC URL.")

    resource = resources[model_or_data_tag]
    filename = str(resource.pbss).split("/")[-1]

    extension = "".join(Path(filename).suffixes)
    processor = _get_processor(extension, resource.unpack, resource.decompress)

    if source == "pbss":
        download_fn = _s3_download
        url = resource.pbss

    elif source == "ngc":
        assert resource.ngc_registry is not None
        download_fn = NGCDownloader(filename=filename, ngc_registry=resource.ngc_registry)
        url = resource.ngc

    else:
        raise ValueError(f"Source '{source}' not supported.")

    download = pooch.retrieve(
        url=str(url),
        fname=f"{resource.sha256}-{filename}",
        known_hash=resource.sha256,
        path=cache_dir,
        downloader=download_fn,
        processor=processor,
    )

    # Pooch by default returns a list of unpacked files if they unpack a zipped or tarred directory. Instead of that, we
    # just want the unpacked, parent folder.
    if isinstance(download, list):
        return Path(processor.extract_dir)  # type: ignore

    else:
        return Path(download)