Analyzing .pdf files

Ask the Community
,
1

Hello there! I am trying to build a workflow which categorizes some data and after gives recommendations about it, however we need to get data from non-structured files, as .pdf - and it can’t be transformed into tabular ones.

Which is the better way to build this workflow knowing that all my inputs will be like that? Should I create an agent through AIP agent studio or there is any other building tool in Palantir for reading unstructured data?

2

Hi @3fa3923f7a1a538d759c you can use media sets in Pipeline Builder! Try taking a look at this example/tutorial: https://www.palantir.com/docs/foundry/building-pipelines/create-batch-pipeline-pb-media-set/