First of three ingestion pipelines that will help us understand and coordinate information throughout a scientific paper. This one will use llmsherpa to extract the text and section structure of the paper. We've already validated this on our example paper, just need to refactor out into an ingestion pipeline.
First of three ingestion pipelines that will help us understand and coordinate information throughout a scientific paper. This one will use
llmsherpato extract the text and section structure of the paper. We've already validated this on our example paper, just need to refactor out into an ingestion pipeline.