start_eval.sh
1.96 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
#!/usr/bin/env bash
# Search evaluation quick entrypoints. Run from any cwd; resolves repo root.
set -euo pipefail
ROOT="$(cd "$(dirname "$0")/../.." && pwd)"
cd "$ROOT"
PY="${ROOT}/.venv/bin/python"
TENANT_ID="${TENANT_ID:-163}"
QUERIES="${REPO_EVAL_QUERIES:-scripts/evaluation/queries/queries.txt}"
START_FROM_QUERY="${REPO_EVAL_START_FROM_QUERY:-}"
usage() {
echo "Usage: $0 batch|batch-rebuild|serve"
echo " batch — batch eval: live search every query, LLM only for missing labels (top_k=50)"
echo " batch-rebuild — deep rebuild: build --force-refresh-labels (search recall pool + full-corpus rerank + batched LLM; expensive)"
echo " serve — eval UI (default http://0.0.0.0:\${EVAL_WEB_PORT:-6010}/; also: ./scripts/start_eval_web.sh)"
echo "Env: TENANT_ID (default 163), REPO_EVAL_QUERIES, REPO_EVAL_START_FROM_QUERY, EVAL_WEB_HOST, EVAL_WEB_PORT (default 6010)"
}
case "${1:-}" in
batch)
cmd=(
"$PY" scripts/evaluation/build_annotation_set.py batch
--tenant-id "$TENANT_ID"
--queries-file "$QUERIES"
--top-k 50
--language en
)
if [ -n "$START_FROM_QUERY" ]; then
cmd+=(--start-from-query "$START_FROM_QUERY")
fi
exec "${cmd[@]}"
;;
batch-rebuild)
cmd=(
"$PY" scripts/evaluation/build_annotation_set.py build
--tenant-id "$TENANT_ID"
--queries-file "$QUERIES"
--search-depth 500
--rerank-depth 10000
--reset-artifacts
--force-refresh-rerank
--force-refresh-labels
--language en
)
if [ -n "$START_FROM_QUERY" ]; then
cmd+=(--start-from-query "$START_FROM_QUERY")
fi
exec "${cmd[@]}"
;;
serve)
EVAL_WEB_PORT="${EVAL_WEB_PORT:-6010}"
EVAL_WEB_HOST="${EVAL_WEB_HOST:-0.0.0.0}"
exec "$PY" scripts/evaluation/serve_eval_web.py serve \
--tenant-id "$TENANT_ID" \
--queries-file "$QUERIES" \
--host "$EVAL_WEB_HOST" \
--port "$EVAL_WEB_PORT"
;;
*)
usage
exit 1
;;
esac