Summary
This chapter explored how to refine search results with various postprocessors, generate responses using different synthesizers, and ensure structured outputs with specific parsers.
We also explored how to construct query engines while integrating the various components that we discussed in the previous chapters.
This chapter also covered handling diverse data sources with RouterQueryEngine
and decomposing complex queries with SubQuestionQueryEngine
, and also demonstrated quiz creation in our tutoring app.
See you in the next chapter, where we’ll talk about chatbots, agents, and conversation tracking with LlamaIndex.