Module cli

The CLI for the deepset AI Platform SDK.

upload

@cli_app.command()
def upload(paths: List[Path],
           api_key: Optional[str] = None,
           api_url: Optional[str] = None,
           workspace_name: str = DEFAULT_WORKSPACE_NAME,
           write_mode: WriteMode = WriteMode.KEEP,
           blocking: bool = True,
           timeout_s: Optional[int] = None,
           show_progress: bool = True,
           recursive: bool = False,
           use_type: Optional[List[str]] = None,
           enable_parallel_processing: bool = False,
           safe_mode: bool = False) -> None

Upload a folder to deepset AI Platform.

Arguments:

paths: Path to the folder to upload. If the folder contains unsupported file types, they're skipped. deepset supports CSV, DOCX, HTML, JSON, MD, TXT, PDF, PPTX, XLSX, XML.
api_key: deepset API key to use for authentication.
api_url: API URL to use for authentication.
workspace_name: Name of the workspace to upload the files to. It uses the workspace from the .ENV file by default.
write_mode: Specifies what to do when a file with the same name already exists in the workspace. Possible options are: KEEP - uploads the file with the same name and keeps both files in the workspace. OVERWRITE - overwrites the file that is in the workspace. FAIL - fails to upload the file with the same name.
blocking: Whether to wait for the files to be uploaded and displayed in deepset AI Platform.
timeout_s: Timeout in seconds for the blocking parameter.
show_progress: Shows the upload progress.
recursive: Uploads files from subfolders as well.
use_type: A comma-separated string of allowed file types to upload.
enable_parallel_processing: If True, deepset AI Platform ingests the files in parallel. Use this to speed up the upload process. Make sure you are not running concurrent uploads for the same files.
safe_mode: If True, disables ingesting files in parallel.

download

@cli_app.command()
def download(workspace_name: str = DEFAULT_WORKSPACE_NAME,
             file_dir: Optional[str] = None,
             name: Optional[str] = None,
             odata_filter: Optional[str] = None,
             include_meta: bool = True,
             batch_size: int = 50,
             api_key: Optional[str] = None,
             api_url: Optional[str] = None,
             show_progress: bool = True,
             safe_mode: bool = False) -> None

Download files from deepset AI Platform to your local machine.

Arguments:

workspace_name: Name of the workspace to download the files from. Uses the workspace from the .ENV file by default.
file_dir: Path to the folder where you want to download the files.
name: Name of the file to odata_filter for.
odata_filter: odata_filter to apply to the file list.
include_meta: Downloads metadata of the files.
batch_size: Batch size for file listing.
api_key: API key to use for authentication.
api_url: API URL to use for authentication.
show_progress: Shows the upload progress.
safe_mode: If True, disables ingesting files in parallel.

@cli_app.command()
def login() -> None

Run deepset-cloud login before performing any tasks in deepset AI platform using the SDK or CLI, unless you already created the .ENV file.

This command guides you through creating a global .env file at ~/.deepset-cloud/.env with your deepset AI Platform API_KEY, API_URL and DEFAULT_WORKSPACE_NAME used for all operations.

The SDK uses a cascading configuration model with the following precedence:

Explicit parameters (passed via code or CLI)
Environment variables
Local .env file in project root
Global ~/.deepset-cloud/.env file (supplements local .env)
Built-in defaults

logout

@cli_app.command()
def logout() -> None

Log out of deepset AI Platform. This command deletes the .ENV file created during login.

Example:

deepset-cloud logout

list_files

@cli_app.command()
def list_files(api_key: Optional[str] = None,
               api_url: Optional[str] = None,
               name: Optional[str] = None,
               odata_filter: Optional[str] = None,
               workspace_name: str = DEFAULT_WORKSPACE_NAME,
               batch_size: int = 10,
               timeout_s: Optional[int] = None) -> None

List files that exist in the specified deepset workspace.

Arguments:

api_key: deepset API key to use for authentication.
api_url: API URL to use for authentication.
workspace_name: Name of the workspace to list the files from. Uses the workspace from the .ENV file by default.
name: Name of the file to odata_filter for.
odata_filter: odata_filter to apply to the file list.
batch_size: Batch size to use for the file list.
timeout_s: The timeout for this request, in seconds. Example: deepset-cloud list-files --batch-size 10

Example using an odata filter to show only files whose category is "news": deepset-cloud list-files --odata-filter 'category eq "news"'

list_upload_sessions

@cli_app.command()
def list_upload_sessions(api_key: Optional[str] = None,
                         api_url: Optional[str] = None,
                         is_expired: Optional[bool] = False,
                         workspace_name: str = DEFAULT_WORKSPACE_NAME,
                         batch_size: int = 10,
                         timeout_s: Optional[int] = None) -> None

List the details of all upload sessions for the specified workspace, including closed sessions.

Arguments:

api_key: deepset API key to use for authentication.
api_url: API URL to use for authentication.
workspace_name: Name of the workspace to list the files from. Uses the workspace from the .ENV file by default.
is_expired: Whether to list expired upload sessions.
batch_size: Batch size to use for the file list.
timeout_s: Timeout in seconds for the API requests. Example: deepset-cloud list-upload-sessions --workspace-name default

get_upload_session

@cli_app.command()
def get_upload_session(session_id: UUID,
                       api_key: Optional[str] = None,
                       api_url: Optional[str] = None,
                       workspace_name: str = DEFAULT_WORKSPACE_NAME) -> None

Fetch an upload session from deepset AI Platform. This method is useful for checking

the status of an upload session after uploading files to deepset.

Arguments:

session_id: ID of the upload session whose status you want to check.
api_key: deepset API key to use for authentication.
api_url: API URL to use for authentication.
workspace_name: Name of the workspace where you upload your files. Uses the workspace from the .ENV file by default. Example: deepset-cloud get-upload-session --workspace-name default

version_callback

def version_callback(value: bool) -> None

Show the SDK version and exit.

Arguments:

value: Value of the version option. Example: deepset-cloud --version

main

@cli_app.callback()
def main(_: Optional[bool] = typer.Option(
    None,
    "--version",
    callback=version_callback,
    is_eager=True,
    help="Show the SDK version and exit.")) -> None

The CLI for the deepset SDK.

This documentation uses Python type hints to provide information about the arguments and return values. Typer turns these type hints into a CLI interface. To see how these arguments are used in the CLI, check the Typer documentation: https://typer.tiangolo.com/tutorial/arguments/optional or run deepset-cloud <command> --help to see the arguments for a specific command.

Boolean values are converted to -no-<variable> or -<variable> flags in the CLI. For example, to disable the progress bar, use --no-show-progress.

Lists can be passed by using the same flag multiple times. For example, to scan only .txt and .pdf files, when uploading use --use-type .txt --use-type .pdf.

run_packaged

def run_packaged() -> None

Run the packaged CLI.

This is the entrypoint for the package to enable running the CLI using typer.

Example:

deepset cloud run-packaged

Was this page helpful?

upload​

download​

login​

logout​

list_files​

list_upload_sessions​

get_upload_session​

version_callback​

main​

run_packaged​

upload

download

login

logout

list_files

list_upload_sessions

get_upload_session

version_callback

main

run_packaged