Viewing & uploading your document manually in Duco Adaptive IDP
Overview
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:
|
Column |
Description |
|
Status |
Processing Document(s) in the upload are being processed by Duco Adaptive IDP AI
|
|
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 |
Filters
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.
Bulk actions
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
Upload details
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.
Uploading files to training
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.
Document options
1. Each file is a document
A document will be created for each file in the upload.
2. Each page is a document
A document will be created for each page in the upload.
3. All files are one document
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.
Limitations
Manually uploading data is limited to 20 files per batch.
See Uploading datafor more information.
Uploading documents via API
To upload documents via API, use the upload api call as described in the API documentation
Transferring an initial set of documents to Duco Adaptive IDP
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.