#!/bin/bash
# Messreihe: 4 Indizes (2000/400) x 3 Suchvarianten mit Reranker x 2 Fragensätze
cd "$(dirname "$0")/.."
P=/Users/Philipp/opt/anaconda3/envs/docling/bin/python
until [ -f vectorstore_docling_2000_hdr/index_info.json ] && [ -f vectorstore_docling_2000/index_info.json ] && [ -f vectorstore_pypdf_2000_hdr/index_info.json ]; do sleep 30; done
for GS in human synthetic; do
  [ $GS = human ] && G=eval/goldset_kafka_human.csv || G=eval/goldset_kafka.csv
  for I in pypdf_2000 pypdf_2000_hdr docling_2000 docling_2000_hdr; do
    for M in dense hybrid union; do
      tag="m2000_${GS}_${I}_${M}"
      caffeinate -i $P eval_retrieval.py --goldset $G --index ./vectorstore_$I --report eval/kafka_${tag}.txt --mode $M > eval/eval_${tag}.log 2>&1
      printf "%-10s %-18s %-7s " "$GS" "$I" "$M"
      grep -E '^  (Recall@|MRR)' eval/kafka_${tag}.txt | awk '{printf "%s %s  ", $1, $2}'; echo
    done
  done
done
echo FERTIG