OpenWebUI integration

scripts/backfill_openwebui.py

@@ -0,0 +1,52 @@
+#!/usr/bin/env python3
+import os, sys
+from pathlib import Path
+import requests, orjson
+
+OWUI_URL = os.getenv("OPENWEBUI_URL", "").rstrip("/")
+OWUI_KEY = os.getenv("OPENWEBUI_API_KEY", "")
+OWUI_KB  = os.getenv("OPENWEBUI_KB_NAME", "Homelab Library")
+
+LIB = Path(os.getenv("LIBRARY_ROOT", "./library"))
+TRN = Path(os.getenv("TRANSCRIPT_ROOT", "./transcripts"))
+
+def headers():
+    return {"Authorization": f"Bearer {OWUI_KEY}"} if OWUI_KEY else {}
+
+def get_or_create_kb():
+    if not OWUI_URL or not OWUI_KEY:
+        print("OpenWebUI not configured.")
+        sys.exit(1)
+    r = requests.get(f"{OWUI_URL}/api/v1/knowledge/list", headers=headers(), timeout=15)
+    r.raise_for_status()
+    for kb in r.json().get("data", []):
+        if kb.get("name") == OWUI_KB:
+            return kb["id"]
+    r = requests.post(f"{OWUI_URL}/api/v1/knowledge/create",
+                      headers={**headers(), "Content-Type":"application/json"},
+                      data=orjson.dumps({"name": OWUI_KB, "description": "All local content indexed by podx"}))
+    r.raise_for_status()
+    return r.json()["data"]["id"]
+
+def upload_and_attach(path: Path, kb_id: str):
+    with open(path, "rb") as f:
+        r = requests.post(f"{OWUI_URL}/api/v1/files/", headers=headers(), files={"file": (path.name, f)}, timeout=60*10)
+    r.raise_for_status()
+    file_id = r.json()["data"]["id"]
+    r = requests.post(f"{OWUI_URL}/api/v1/knowledge/{kb_id}/file/add",
+                      headers={**headers(), "Content-Type":"application/json"},
+                      data=orjson.dumps({"file_id": file_id}), timeout=60)
+    r.raise_for_status()
+    print(f"Uploaded {path}")
+
+def main():
+    kb_id = get_or_create_kb()
+    # transcripts
+    for txt in TRN.glob("*.txt"):
+        upload_and_attach(txt, kb_id)
+    # web snapshots
+    for txt in LIB.glob("web/**/*.txt"):
+        upload_and_attach(txt, kb_id)
+
+if __name__ == "__main__":
+    main()