133 lines
5.1 KiB
Python
133 lines
5.1 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
scripts/import_markdown.py
|
|
CLI-Tool zum Importieren von Markdown-Dateien in Qdrant.
|
|
WP-15b: Implementiert den Two-Pass Workflow (Pre-Scan + Processing).
|
|
Sorgt dafür, dass der LocalBatchCache vor der Verarbeitung robust gefüllt wird.
|
|
Indiziert Notizen nach ID, Titel und Dateiname für maximale Link-Kompatibilität.
|
|
VERSION: 2.4.1
|
|
"""
|
|
import asyncio
|
|
import os
|
|
import argparse
|
|
import logging
|
|
from pathlib import Path
|
|
from dotenv import load_dotenv
|
|
|
|
# Setzt das Level global auf INFO, damit der Fortschritt im Log sichtbar ist
|
|
logging.basicConfig(level=logging.INFO, format='%(asctime)s [%(levelname)s] %(message)s')
|
|
|
|
# Importiere den neuen Async Service und stelle Python-Pfad sicher
|
|
import sys
|
|
sys.path.append(os.getcwd())
|
|
|
|
from app.core.ingestion import IngestionService
|
|
from app.core.parser import pre_scan_markdown
|
|
|
|
logger = logging.getLogger("importer")
|
|
|
|
async def main_async(args):
|
|
vault_path = Path(args.vault).resolve()
|
|
if not vault_path.exists():
|
|
logger.error(f"Vault path does not exist: {vault_path}")
|
|
return
|
|
|
|
# 1. Service initialisieren
|
|
logger.info(f"Initializing IngestionService (Prefix: {args.prefix})")
|
|
service = IngestionService(collection_prefix=args.prefix)
|
|
|
|
logger.info(f"Scanning {vault_path}...")
|
|
files = list(vault_path.rglob("*.md"))
|
|
# Exclude .obsidian folder if present
|
|
files = [f for f in files if ".obsidian" not in str(f)]
|
|
files.sort()
|
|
|
|
logger.info(f"Found {len(files)} markdown files.")
|
|
|
|
# =========================================================================
|
|
# PASS 1: Global Pre-Scan (WP-15b Harvester)
|
|
# Füllt den LocalBatchCache für die semantische Kanten-Validierung.
|
|
# Nutzt ID, Titel und Filename für robusten Look-up.
|
|
# =========================================================================
|
|
logger.info(f"🔍 [Pass 1] Pre-scanning {len(files)} files for global context cache...")
|
|
for f_path in files:
|
|
try:
|
|
ctx = pre_scan_markdown(str(f_path))
|
|
if ctx:
|
|
# 1. Look-up via Note ID (UUID oder Frontmatter ID)
|
|
service.batch_cache[ctx.note_id] = ctx
|
|
|
|
# 2. Look-up via Titel (Wichtig für Wikilinks [[Titel]])
|
|
service.batch_cache[ctx.title] = ctx
|
|
|
|
# 3. Look-up via Dateiname (Wichtig für Wikilinks [[Filename]])
|
|
fname = os.path.splitext(f_path.name)[0]
|
|
service.batch_cache[fname] = ctx
|
|
|
|
except Exception as e:
|
|
logger.warning(f"⚠️ Could not pre-scan {f_path.name}: {e}")
|
|
|
|
logger.info(f"✅ Context Cache populated for {len(files)} notes.")
|
|
|
|
# =========================================================================
|
|
# PASS 2: Processing (Semantic Batch-Verarbeitung)
|
|
# Nutzt den gefüllten Cache zur binären Validierung semantischer Kanten.
|
|
# =========================================================================
|
|
stats = {"processed": 0, "skipped": 0, "errors": 0}
|
|
sem = asyncio.Semaphore(5) # Max 5 parallele Dateien für Cloud-Stabilität
|
|
|
|
async def process_with_limit(f_path):
|
|
async with sem:
|
|
try:
|
|
# Nutzt den nun gefüllten Batch-Cache in der process_file Logik
|
|
res = await service.process_file(
|
|
file_path=str(f_path),
|
|
vault_root=str(vault_path),
|
|
force_replace=args.force,
|
|
apply=args.apply,
|
|
purge_before=True
|
|
)
|
|
return res
|
|
except Exception as e:
|
|
return {"status": "error", "error": str(e), "path": str(f_path)}
|
|
|
|
logger.info(f"🚀 [Pass 2] Starting semantic processing in batches...")
|
|
|
|
batch_size = 20
|
|
for i in range(0, len(files), batch_size):
|
|
batch = files[i:i+batch_size]
|
|
logger.info(f"Processing batch {i} to {i+len(batch)}...")
|
|
|
|
tasks = [process_with_limit(f) for f in batch]
|
|
results = await asyncio.gather(*tasks)
|
|
|
|
for res in results:
|
|
if res.get("status") == "success":
|
|
stats["processed"] += 1
|
|
elif res.get("status") == "error":
|
|
stats["errors"] += 1
|
|
logger.error(f"Error in {res.get('path')}: {res.get('error')}")
|
|
else:
|
|
stats["skipped"] += 1
|
|
|
|
logger.info(f"Done. Stats: {stats}")
|
|
if not args.apply:
|
|
logger.info("DRY RUN. Use --apply to write to DB.")
|
|
|
|
def main():
|
|
load_dotenv()
|
|
default_prefix = os.getenv("COLLECTION_PREFIX", "mindnet")
|
|
|
|
parser = argparse.ArgumentParser(description="Two-Pass Markdown Ingestion for Mindnet")
|
|
parser.add_argument("--vault", default="./vault", help="Path to vault root")
|
|
parser.add_argument("--prefix", default=default_prefix, help="Collection prefix")
|
|
parser.add_argument("--force", action="store_true", help="Force re-index all files")
|
|
parser.add_argument("--apply", action="store_true", help="Perform writes to Qdrant")
|
|
|
|
args = parser.parse_args()
|
|
|
|
# Starte den asynchronen Haupt-Loop
|
|
asyncio.run(main_async(args))
|
|
|
|
if __name__ == "__main__":
|
|
main() |