You can setup LlamaParse by choosing the LlamaParse node and the Parse PDF File action:
And, once you selected that, you can specify file binary data to parse:
For binary data, it is best to dynamically fetch them from another source (trigger), such as a WebHook:
In this example, you can send a PDF directly with a curl request:
curl -X POST \
-H "Content-Type: application/pdf" \
--data-binary @document.pdf \
http://localhost:5678/<YOUR_WEBHOOK_NAME>/<YOUR_WEBHOOK_PATH>
And you can take the webhook output as input for LlamaParse: