Module files

This module contains async functions for uploading files and folders to deepset Cloud.

list_files

async def list_files(
        api_key: Optional[str] = None,
        api_url: Optional[str] = None,
        workspace_name: str = DEFAULT_WORKSPACE_NAME,
        name: Optional[str] = None,
        odata_filter: Optional[str] = None,
        batch_size: int = 100,
        timeout_s: Optional[int] = None) -> AsyncGenerator[List[File], None]

List all files in a workspace.

Arguments:

api_key: deepset Cloud 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. It uses the workspace from the .ENV file by default.
name: Name of the file to odata_filter for.
odata_filter: The odata_filter to apply to the file list. For example, odata_filter="category eq 'news'" lists files with metadata {"meta": {"category": "news"}}.
timeout_s: The timeout in seconds for this API call.
batch_size: Batch size for the listing.

Returns:

List of files.

list_upload_sessions

async def list_upload_sessions(
    api_key: Optional[str] = None,
    api_url: Optional[str] = None,
    workspace_name: str = DEFAULT_WORKSPACE_NAME,
    is_expired: Optional[bool] = None,
    batch_size: int = 100,
    timeout_s: Optional[int] = None
) -> AsyncGenerator[List[UploadSessionDetail], None]

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

Arguments:

api_key: deepset Cloud 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. It uses the workspace from the .ENV file by default.
is_expired: Whether to list expired upload sessions.
batch_size: Batch size for the listing.
timeout_s: Timeout in seconds for the API requests.

Returns:

List of files.

get_upload_session

async def get_upload_session(
        session_id: UUID,
        api_key: Optional[str] = None,
        api_url: Optional[str] = None,
        workspace_name: str = DEFAULT_WORKSPACE_NAME) -> UploadSessionStatus

Get the status of an upload session.

Arguments:

session_id: ID of the upload session to get the status for.
api_key: deepset Cloud 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.

Returns:

List of files.

upload

async 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,
                 desired_file_types: Optional[List[str]] = None,
                 enable_parallel_processing: bool = False) -> S3UploadSummary

Upload a folder to deepset Cloud.

Arguments:

paths: Path to the folder to upload. If the folder contains unsupported files, they're skipped. during the upload. Supported file formats are txt, pdf, docx, pptx, xlsx, xml, csv, html, md, json.
api_key: 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 upload to finish.
timeout_s: Timeout in seconds for the upload.
show_progress: Shows the upload progress.
recursive: Uploads files from subdirectories as well.
desired_file_types: A list of allowed file types to upload, defaults to ['.txt', '.pdf'].
enable_parallel_processing: If True, the deepset Cloud will ingest the files in parallel. Use this to speed up the upload process and if you are not running concurrent uploads for the same files.

download

async def download(workspace_name: str = DEFAULT_WORKSPACE_NAME,
                   file_dir: Optional[Union[Path, 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,
                   timeout_s: Optional[int] = None) -> None

Download a folder to deepset Cloud.

Downloads all files from a workspace to a local folder.

Arguments:

workspace_name: Name of the workspace to upload the files to. It uses the workspace from the .ENV file by default.
file_dir: Path to the folder to download.
name: Name of the file to odata_filter by.
odata_filter: odata_filter by file meta data.
include_meta: Whether to include the file meta in the folder.
batch_size: Batch size for the listing.
api_key: API key to use for authentication.
api_url: API URL to use for authentication.
show_progress: Shows the upload progress.
timeout_s: Timeout in seconds for the download.

upload_texts

async def upload_texts(
        files: List[DeepsetCloudFile],
        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,
        enable_parallel_processing: bool = False) -> S3UploadSummary

Upload raw texts to deepset Cloud.

Arguments:

files: List of DeepsetCloudFile objects to upload.
api_key: deepset Cloud 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 listed and displayed in deepset Cloud. This may take a couple of minutes.
timeout_s: Timeout in seconds for the blocking parameter.
show_progress: Shows the upload progress.
enable_parallel_processing: If True, the deepset Cloud will ingest the files in parallel. Use this to speed up the upload process and if you are not running concurrent uploads for the same files.

Example:

import asyncio
from deepset_cloud_sdk.workflows.async_client.files import upload_texts, DeepsetCloudFile

async def my_async_context() -> None:
    await upload_texts(
        api_key="<deepsetCloud_API_key>",
        workspace_name="<default_workspace>",  # optional, by default the environment variable "DEFAULT_WORKSPACE_NAME" is used
        files=[
            DeepsetCloudFile(
                name="example.txt",
                text="this is text",
                meta={"key": "value"},  # optional
            )
        ],
        blocking=True,  # optional, by default True
        timeout_s=300,  # optional, by default 300
    )

# Run the async function
if __name__ == "__main__":
    asyncio.run(my_async_context())

upload_bytes

async def upload_bytes(
        files: List[DeepsetCloudFileBytes],
        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,
        enable_parallel_processing: bool = False) -> S3UploadSummary

Upload files in byte format.

Arguments:

files: List of DeepsetCloudFileBytes objects to upload.
api_key: deepset Cloud 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 in the workspace with the file you're uploading. FAIL - fails to upload the file if a file with the same name already exists in the workspace.
blocking: Whether to wait for the files to be listed and displayed in deepset Cloud. This may take a couple of minutes.
timeout_s: Timeout in seconds for the blocking parameter.
show_progress: Shows the upload progress.
enable_parallel_processing: If True, the deepset Cloud will ingest the files in parallel. Use this to speed up the upload process and if you are not running concurrent uploads for the same files.