How to get the contents of the nodes

[sacsac944]

Does Pageindex get the contents of the nodes as well or should it be done using some other framework? In the examples, the node content is not present in the tree and we might not have access to the source document during runtime.

Also does it support multiple modalities like tables and images apart from text in the documents?

[zmtomorrow]

Hi, currently you could do that by using the page number to extract the content from the original pdf. We also plan to add that function from our API end.