William Valentin
6c13a60f57
- obsidian-reindex-server.py: HTTP endpoint on port 18810 for triggering incremental Obsidian vault reindex from n8n - Updated n8n Implementation Handoff: Obsidian Semantic Index section, new reindex workflow, updated verification commands
125 lines
3.6 KiB
Python
125 lines
3.6 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Obsidian Vault Reindex Endpoint
|
|
Lightweight HTTP server that triggers an incremental Obsidian vault reindex.
|
|
|
|
Listens on 0.0.0.0:18810 (configurable via PORT env var).
|
|
Called by n8n webhooks or systemd timers.
|
|
|
|
Endpoints:
|
|
POST /reindex -> trigger incremental reindex, returns JSON stats
|
|
GET /reindex/status -> check last index state
|
|
GET /healthz -> returns ok
|
|
"""
|
|
|
|
import http.server
|
|
import json
|
|
import os
|
|
import subprocess
|
|
import sys
|
|
import threading
|
|
from pathlib import Path
|
|
|
|
PORT = int(os.environ.get("PORT", 18810))
|
|
|
|
REINDEX_SCRIPT = str(
|
|
Path.home()
|
|
/ ".hermes/skills/note-taking/rag-search/scripts/reindex_obsidian.sh"
|
|
)
|
|
STATE_FILE = (
|
|
Path.home() / ".hermes/data/rag-search/obsidian_index_state.json"
|
|
)
|
|
|
|
# Lock to prevent concurrent reindexing
|
|
_reindex_lock = threading.Lock()
|
|
|
|
|
|
def run_reindex() -> dict:
|
|
"""Run the incremental reindex script. Returns stats dict."""
|
|
if not _reindex_lock.acquire(blocking=False):
|
|
return {"error": "reindex already in progress", "status": "locked"}
|
|
|
|
try:
|
|
result = subprocess.run(
|
|
[REINDEX_SCRIPT],
|
|
capture_output=True,
|
|
text=True,
|
|
timeout=600, # 10 min max for full reindex
|
|
)
|
|
if result.returncode != 0:
|
|
return {
|
|
"error": "reindex failed",
|
|
"exit_code": result.returncode,
|
|
"stderr": result.stderr.strip()[:500],
|
|
}
|
|
try:
|
|
return json.loads(result.stdout)
|
|
except json.JSONDecodeError:
|
|
return {
|
|
"error": "invalid json output",
|
|
"stdout": result.stdout.strip()[:500],
|
|
}
|
|
except subprocess.TimeoutExpired:
|
|
return {"error": "reindex timed out (600s)"}
|
|
except Exception as e:
|
|
return {"error": str(e)}
|
|
finally:
|
|
_reindex_lock.release()
|
|
|
|
|
|
def get_status() -> dict:
|
|
"""Read the last index state file."""
|
|
if not STATE_FILE.exists():
|
|
return {"indexed": False, "message": "no state file"}
|
|
try:
|
|
return json.loads(STATE_FILE.read_text())
|
|
except (json.JSONDecodeError, IOError) as e:
|
|
return {"error": str(e)}
|
|
|
|
|
|
class ReindexHandler(http.server.BaseHTTPRequestHandler):
|
|
def do_GET(self):
|
|
path = self.path.rstrip("/")
|
|
if path == "/healthz":
|
|
self._json_response({"status": "ok"})
|
|
elif path == "/reindex/status":
|
|
self._json_response(get_status())
|
|
else:
|
|
self._json_response({"error": "not found"}, status=404)
|
|
|
|
def do_POST(self):
|
|
path = self.path.rstrip("/")
|
|
if path == "/reindex":
|
|
# Run in background thread so we can respond
|
|
result = run_reindex()
|
|
status = 200 if "error" not in result else 500
|
|
self._json_response(result, status=status)
|
|
else:
|
|
self._json_response({"error": "not found"}, status=404)
|
|
|
|
def _json_response(self, data, status=200):
|
|
body = json.dumps(data, indent=2).encode()
|
|
self.send_response(status)
|
|
self.send_header("Content-Type", "application/json")
|
|
self.send_header("Content-Length", str(len(body)))
|
|
self.end_headers()
|
|
self.wfile.write(body)
|
|
|
|
def log_message(self, format, *args):
|
|
# Minimal logging
|
|
pass
|
|
|
|
|
|
def main():
|
|
server = http.server.HTTPServer(("0.0.0.0", PORT), ReindexHandler)
|
|
print(f"obsidian-reindex-server listening on 0.0.0.0:{PORT}", flush=True)
|
|
try:
|
|
server.serve_forever()
|
|
except KeyboardInterrupt:
|
|
pass
|
|
server.server_close()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|