To get the top-level summary, you can:
- Extract summaries of the more granular call transcripts
- Index these summary documents using a
SummaryIndex
which will use all the documents - And query the LLM to produce a final summary
Though I wonder if you'll be able to fit all the summaries within the context window. If not, then you should look at node postprocessors to compress the prompt. LongLLMLingua can be used for this.