it i possible to search the information in pdf files using Rasa Pro? we does not have any OPENAI_API_KEY. without OPENAI_API_KEY key need to extract the info from PDF.
Can you please provide some examples?
I haven’t used Rasa Pro specifically for PDF searching without an OpenAI API key, but from my experience, what usually works is extracting the text from the PDFs first using Python libraries like PyMuPDF or pdfplumber, then feeding that text into Rasa for processing. This way, you’re not relying on any external APIs or keys, just local tools. For example, I’ve used PyMuPDF to pull all the text out of a PDF pretty easily, and then passed that text to Rasa’s NLU pipeline to extract the info I needed. It’s a bit manual but works well if you want to keep everything self-contained. Just be aware that if your PDFs have complex layouts or lots of tables, you might need to do some extra parsing to get clean results.