a97d0bbcfd
scripts/generate_synthetic_pdfs.py builds real PDF/1.4 documents with a hand-written xref so we can generate tens of thousands of ~2 KB PDFs locally. Helvetica only covers latin-1, which is fine for a load generator (throughput, not retrieval relevance); the docstring calls this out so no one mistakes the output for a quality corpus. scripts/load_ingest.py drives POST /ingest/folder, then polls a hypothetical /documents/stats endpoint every poll-interval seconds to track terminal-state progression. Writes a JSON history report so results can be diffed between runs. scripts/locustfile_search.py defines a SearchUser profile mixing hybrid / lexical / semantic queries against POST /search plus a health-check sampler. Asserts non-empty results so a "200 with zero hits" regression surfaces as a failure rather than a green percentile graph. RUNBOOK gains a Load testing section with CPU/GPU SLO tables for both axes (sustained docs/min, search latency p50/p95/p99). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
73 lines
2.1 KiB
Python
73 lines
2.1 KiB
Python
"""Locust load profile for the LegacyHUB hybrid search API.
|
|
|
|
Run:
|
|
|
|
pip install locust
|
|
locust -f scripts/locustfile_search.py \
|
|
--host http://localhost:8000 \
|
|
--users 50 --spawn-rate 5 --run-time 5m
|
|
|
|
Or headless with HTML report:
|
|
|
|
locust -f scripts/locustfile_search.py --host http://localhost:8000 \
|
|
--headless --users 100 --spawn-rate 10 --run-time 10m \
|
|
--html load_search.html
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import random
|
|
|
|
from locust import HttpUser, between, task
|
|
|
|
|
|
QUERIES = [
|
|
"ГОСТ 21.501-93 рабочие чертежи",
|
|
"класс бетона B25",
|
|
"регламент технического обслуживания",
|
|
"контроль качества сварных соединений",
|
|
"схема электропитания корпус 3",
|
|
"журнал ремонтов узлов",
|
|
"правила производства земляных работ",
|
|
"акты приемки скрытых работ",
|
|
"fundament concrete grade",
|
|
"maintenance schedule appendix",
|
|
]
|
|
|
|
MODES = ["hybrid", "hybrid", "hybrid", "lexical", "semantic"]
|
|
|
|
|
|
class SearchUser(HttpUser):
|
|
wait_time = between(0.5, 2.5)
|
|
api_prefix = "/api/v1"
|
|
|
|
@task(8)
|
|
def hybrid_search(self):
|
|
body = {
|
|
"query": random.choice(QUERIES),
|
|
"limit": random.choice([5, 10, 20]),
|
|
"filters": {
|
|
"document_id": None,
|
|
"source_path": None,
|
|
"block_type": None,
|
|
"min_ocr_confidence": None,
|
|
},
|
|
"search_mode": random.choice(MODES),
|
|
}
|
|
with self.client.post(
|
|
f"{self.api_prefix}/search",
|
|
json=body,
|
|
name="POST /search",
|
|
catch_response=True,
|
|
) as res:
|
|
if res.status_code != 200:
|
|
res.failure(f"HTTP {res.status_code}: {res.text[:120]}")
|
|
return
|
|
data = res.json()
|
|
if not data.get("results"):
|
|
res.failure("empty results")
|
|
|
|
@task(1)
|
|
def health(self):
|
|
self.client.get(f"{self.api_prefix}/health", name="GET /health")
|