✳flâneur — a map of the web's best reading
Usage Pattern - LlamaIndex 🦙 0.8.49
docs.llamaindex.ai · saved by 1 readers
Most commonly, node-postprocessors will be used in a query engine, where they are applied to the nodes returned from a retriever, and before the response synthesis step. Or used as a standalone object for filtering retrieved nodes: As you may have noticed, the postprocessors take NodeWithScore objects as inputs, which is just a wrapper class with a Node and a score value. The base class is BaseNodePostprocessor, and the API interface is very simple: A dummy node-postprocessor can be implemented in just a few lines of code: 🦙
Explore this link on the map →