Add info for non-AWS S3 storage (#783)

This commit is contained in:
pollfly
2024-02-26 17:07:59 +02:00
committed by GitHub
parent 90faaf234e
commit 91fcaa2f24
7 changed files with 39 additions and 6 deletions

View File

@@ -202,7 +202,7 @@ clearml-serving model upload [-h] --name NAME [--tags TAGS [TAGS ...]] --project
|`--publish`| Publish the newly created model (change model state to "published" (i.e. locked and ready to deploy)|<img src="/docs/latest/icons/ico-optional-yes.svg" alt="Yes" className="icon size-md center-md" />|
|`--path`|Specify a model file/folder to be uploaded and registered| <img src="/docs/latest/icons/ico-optional-yes.svg" alt="Yes" className="icon size-md center-md" />|
|`--url`| Specify an already uploaded model url (e.g. `s3://bucket/model.bin`, `gs://bucket/model.bin`)|<img src="/docs/latest/icons/ico-optional-yes.svg" alt="Yes" className="icon size-md center-md" />|
|`--destination`|Specify the target destination for the model to be uploaded (e.g. `s3://bucket/folder/`, `gs://bucket/folder/`)|<img src="/docs/latest/icons/ico-optional-yes.svg" alt="Yes" className="icon size-md center-md" />|
|`--destination`|Specify the target destination for the model to be uploaded. For example: `s3://bucket/folder/`, `s3://host_addr:port/bucket` (for non-AWS S3-like services like MinIO), `gs://bucket-name/folder`, `azure://<account name>.blob.core.windows.net/path/to/file`|<img src="/docs/latest/icons/ico-optional-yes.svg" alt="Yes" className="icon size-md center-md" />|
</div>

View File

@@ -104,7 +104,7 @@ or with the `clearml-serving` CLI.
:::info Model Storage
You can also provide a different storage destination for the model, such as S3/GS/Azure, by passing
`--destination="s3://bucket/folder"`, `gs://bucket/folder`, `azure://<account name>.blob.core.windows.net/path/to/file`. There is no need to provide a unique
`--destination="s3://bucket/folder"`, `s3://host_addr:port/bucket` (for non-AWS S3-like services like MinIO), `gs://bucket/folder`, `azure://<account name>.blob.core.windows.net/path/to/file`. There is no need to provide a unique
path to the destination argument, the location of the model will be a unique path based on the serving service ID and the
model name
:::