This deployment (model) extracts all unique words from a PDF file and counts the occurrence of each word in the document.
The deployment returns an excel file containing two columns: the first contains all the unique words identified in the document whereas the second column shows the number of occurrences of the specific word in that row.
The model (deployment) expects a PDF file with text. Upload your PDF file and click ‘run code’.
Depending on the size of the data input (your PDF) it can take longer to process your request. Usually, it’s within a second (with a cold start it may take a few seconds).
The output of the model is an excel file that you can download. Once the request is finished, click ‘download file’ and open it to see the results.
The uploading document is limited to .pdf files only.