⬆️Uploads
Viewing & uploading your document manually in Metamaze
Last updated
Viewing & uploading your document manually in Metamaze
Last updated
When navigation to the training uploads, you arrive upon an overview of all your uploads with training data. Each line in this overview shows an upload with its properties. An upload can consist of several documents.
The overview consists of several columns:
Status
Processing Document(s) in the upload are being processed by Metamaze AI
Input required Document(s) in the upload have been processed but some or all documents require human input to be finalised
Processed Document(s) in the upload have been fully processed
Failed Processing failed for document(s) in the upload
Number of documents
Shows the number of document in the upload with a breakdown by status
Upload ID
The unique ID associated with the upload
Uploaded on
The date the files were uploaded
Uploaded by
User who made the upload, in case the upload was done through the UI
Filtering uploads based on criteria is handy to find your upload(s) quickly. Note: When extra fields for your organisation have been defined, they will also be shown in the filter options.
Selecting uploads allows you to perform an action on multiple uploads:
Retry upload(s) This will re-send an upload through your AI pipeline, performing a new OCR, re-creating documents and making predictions when possible
Performing document classification and page management predictions in training is not possible. This is because our document classification training specifically considers documents with the status "Input required." In our commitment to guiding our users to work with high standards of data quality, we consistently advise our users to verify AI predictions thoroughly before making a document part of the training data.
Delete Deletes the selected upload(s) from the training data set
When you click an upload, you can view extra details such as when it was uploaded, which steps of the pipeline it went through and what the current status is of the upload and the documents in the upload.
Users with the right permission (check out: Roles & permissions) can manually upload files by using the Upload button.
A new window will appear where you can select the relevant files. You can either drag and drop the files into the window or search for the files via the explorer screen using the 'Browse' button.
A document will be created for each file in the upload.
A document will be created for each page in the upload.
All files will be merged into one document.
Document type and language
You can select the relevant document type and language of the uploaded files in the corresponding dropdown lists. If you do not specify these, the language will be detected automatically, and the document type will be left to specify. The document type and language can be modified later in the document meta data. It is necessary to assign a document type and a language to a document before you can start annotating it.
Manually uploading data is limited to 20 files per batch.
See Uploading datafor more information.
To upload documents via API, use the upload api call as described in the API documentation
If you do not want to integrate the API yet or don't want to make use of the out of the box integration options available in the project settings ( Input ), feel free to send us an export in any common format.
Examples include
ZIP file containing PDF's, transferred via Sharepoint, e-mail, SFTP, Blob Storage, ...
Individual MSG, EML, PDF, JPEG, TIFF, ... files transferred via SFTP or file share.
Exports of mailboxes in PST format.
