How to handle tables and images?

PDF is the data source and it has tables and Images. How to handle them?

HI @vijivenkadesh the easiest way to get started with PDFs as your sata source is to use Pinecone Assistant, which is a service that allows you to upload documents, ask questions, and receive responses that reference your documents. Currently, it supports .txt and .pdf file types .

For your use case:

  • You could upload your tables as PDF or text documents to Pinecone Assistant
  • The assistant would process the contents by chunking and embedding the text
  • You could then ask questions about the data and get responses grounded in your documents

However, there are some limitations to consider:

  • Currently only .txt and .pdf files are supported
  • There are storage limits depending on your plan:
    • Starter plan: 1GB max file storage per assistant
    • Standard/Enterprise plans: 10GB max file storage per assistant