Using PDFs
Let’s explore how to convert an invoice from a PDF file into a structured table that can be used for reporting and combined with data from other invoices.
Below is the original PDF:
Our goal is to extract the data from the PDF and organize it in a usable structured format.
The typical process involves converting your PDF to a TEXT file using an external tool, then uploading the resulting text or CSV file.
- Convert the PDF to a text file using a tool like this PDF-to-text converter. It's crucial to have a solid understanding of how to use this tool effectively.
- Create a Copilot chat and upload the text file.
- Ask the AI to regenerate a structured table from the text. AI can handle unstructured data (only the Generalist model can perform this task).
find order items in the document
show it as table with name of an item, rate, and amount
While the described above process is manual, it can be automated. You'll need to implement a script that automatically feeds the text files into the system.
If you need a repeatable workflow, we can set up an automated conversion script on our end.