cryptorugmunch
cfd75fd1a0
- Exclude generated SDK (sdks/python) and operational scripts from ruff lint - Add targeted per-file ignores for ASYNC*, S310, S603, S607, S108, S314, S102, PIE810, SIM102 in scripts/ - Auto-fix safe categories (I001, F401, W292, F841, PIE790, RUF100, etc.) - Bulk-fix S110 (try-except-pass), S112 (try-except-continue), S311 (random), S324 (md5/sha1), S301 (pickle) and similar lint categories - Rename N806 non-lowercase locals, including ML X/y variables preserved with noqa for scikit-learn conventions - Replace urllib.request calls with httpx.AsyncClient / httpx.Client (S310) - Wrap blocking os.path/os calls in asyncio.get_running_loop().run_in_executor - Replace subprocess.run with asyncio.create_subprocess_exec in async contexts - Store asyncio.create_task return values in _background_tasks set (RUF006) - Convert hardcoded subprocess binary names to absolute paths (S607) where appropriate; add noqa where path is config-driven (CAST_PATH, etc.) - Parameterize SQL queries with placeholders and add noqa for sanitized inputs - Fix all mechanical categories: SIM102, PIE810, TC001/2/3, S108, S314, S107, S306, S301, N802/N815/N817, S104, S605, S501, RUF022, UP031 - Add missing 'import asyncio' where referenced but not imported (F821) - Fix E402 module-import-not-at-top by adding '# noqa: E402' for circular-import safe cases and code-defined imports - Remove hardcoded Redis password in databus_warm_cron.py; use env vars Tests: - Add tests/unit/core/test_ai_router.py (8 tests): model resolution, chat completion with mocked httpx, fallback to OpenRouter, no-provider error, streaming - Add tests/unit/core/test_tracing.py (7 tests): setup_otel disabled/enabled, shutdown_otel, span helpers, tracing-enabled route registration - Add tests/unit/core/test_langfuse.py (2 tests): no-env init, noop flush - Fix tests/unit/domain/scanner/test_service.py to import from the moved app.domains.scanners.core.service Result: 'ruff check .' passes with 0 errors (was 1470). Pytest: 808 passed, 1 skipped (no regressions).
65 lines
2 KiB
Python
65 lines
2 KiB
Python
#!/usr/bin/env python3
|
|
"""Ingest SIGMOD 2023 Pump & Dump dataset into RAG known_scams.
|
|
36,696 labeled messages from Telegram pump channels - ground truth training data.
|
|
"""
|
|
|
|
import asyncio
|
|
import csv
|
|
import logging
|
|
import sys
|
|
|
|
import httpx
|
|
|
|
sys.path.insert(0, "/root/backend")
|
|
|
|
CSV_PATH = "/root/tools/dark-collection/sigmod-pnd/Data/Telegram/Labeled/pred_pump_message.csv"
|
|
RAG_URL = "http://localhost:8000/api/v1/rag/ingest"
|
|
BATCH = 100 # Ingest in batches to avoid overwhelming the API
|
|
|
|
|
|
async def ingest():
|
|
with open(CSV_PATH) as f:
|
|
reader = csv.DictReader(f, delimiter="\t")
|
|
rows = list(reader)
|
|
|
|
print(f"Loading {len(rows)} P&D messages...")
|
|
|
|
count = 0
|
|
async with httpx.AsyncClient(timeout=30) as client:
|
|
for i, row in enumerate(rows):
|
|
# Build a searchable document
|
|
msg = row.get("message", "")[:1000]
|
|
channel = row.get("channel_id", "unknown")
|
|
date = row.get("date", "")
|
|
label = row.get("pred_label", "0")
|
|
|
|
payload = {
|
|
"collection": "known_scams",
|
|
"content": f"[SIGMOD P&D] Channel {channel} - {date}: {msg}",
|
|
"metadata": {
|
|
"source": "sigmod_pnd_2023",
|
|
"channel_id": channel,
|
|
"date": date,
|
|
"pred_label": float(label),
|
|
"scam_type": "pump_and_dump",
|
|
"dataset": "SIGMOD 2023",
|
|
},
|
|
}
|
|
|
|
try:
|
|
r = await client.post(
|
|
RAG_URL, json=payload, headers={"X-RMI-Key": "rmi-internal-2026"}
|
|
)
|
|
if r.status_code == 200:
|
|
count += 1
|
|
except Exception:
|
|
logging.getLogger(__name__).warning("swallowed exception", exc_info=True)
|
|
|
|
if (i + 1) % 500 == 0:
|
|
print(f" Progress: {i + 1}/{len(rows)} ({count} ingested)")
|
|
|
|
print(f"Done: {count}/{len(rows)} ingested into known_scams")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(ingest())
|