Agenty Buckets feature is used to upload documents, images temporarily to process through OCR, Textract or any other agents available in Agenty products stack.
We can use the Bucket feature to bulk upload thousands of images, pdf etc from our computer hard-drive and then OCR them using the OCR agent to extract the text from images or scanned pdf documents.
- Go to the Buckets page from left side bar
- Click on New Bucket button and a dialog box will open
- Enter the
Nameof bucket, select the
Regionand optional description
- Click on the Add button to create a bucket
- Now, you can see this newly created bucket in your Buckets list.
- Click on the Add documents under the bucket where you want to upload documents
- The uploader window will open, where we need to click on the Add files button to browse and select the files from your computer.
- You may select multiple files (up-to 1000 per upload) with a size limit of 25mb each depending on your Agenty pricing plan
- As we select the files, they will appear in queued files list on this page yet to be uploaded
- Click on the Start upload button to upload all files.
Note: Do not close this window, because the uploader is running on your browser
Attach Bucket with Agent
Now, the documents has been uploaded in the bucket we created, so we can use this bucket to process with our OCR agent to extract the text from these scanned pdf documents.
- Go to your OCR agent page
- Click on the Input tab
- Choose "Select a bucket" option in Input Type
- Now choose your bucket to process
- And save it by clicking on Save button
- Now, you can start or schedule the agent to extract text from all the files in this bucket
- Go to Buckets > Select bucket you want to update
- Click on Rename button and a dialog box will appear
- Here you can change the name or description of a bucket and save that back