This step uses Google natural language processing to extract entities and sentiment from text content.
Note that we also include similar capability based on Huggingface and Spacy as part of the Python REST Service, which ships with the product.
As with the Vision step, provide an endpoint ands then select the entities that you want to store.
Before using this step ensure you have created your entities in Control Hub. They should all be type keyword for this step.
Select Show Advanced Options
Define the maximum number of items to process concurrently in Bounded Capacity.
Define the maximum number of items that can be queued.
Limiting either of these will reduce the memory use but increase the time taken.
