jay-joshy / question_cli

0 stars 0 forks source link

consider new node_processor #15

Open jay-joshy opened 2 months ago

jay-joshy commented 2 months ago

https://docs.llamaindex.ai/en/stable/examples/node_postprocessor/OptimizerDemo/

This postprocessor optimizes token usage by removing sentences that are not relevant to the query (this is done using embeddings).The percentile cutoff is a measure for using the top percentage of relevant sentences. The threshold cutoff can be specified instead, which uses a raw similarity cutoff for picking which sentences to keep.

Would want to:

  1. test out to make sure it does as advertized
  2. ?is it worth adding if it adds more complexity to the manuscripot?