push

ragg/ingest_all.py

@@ -1,6 +1,7 @@
 # ingest_all.py
 import os
 from ragg.rag_backend import ingest_pdfs_from_folder, get_embeddings
+# from ragg.rag_backend import ingest_pdfs_from_folder, get_embeddings
 from langchain_community.vectorstores import Chroma
 
 def ingest_all_levels():
@@ -37,7 +38,7 @@ def ingest_all_levels():
 
 
         # ✅ Temporarily replace the function used in rag_backend
-        import rag_backend
+        import ragg.rag_backend as rag_backend
         rag_backend.get_vectorstore = get_vectorstore_for_level
 
         # ✅ Ingest PDFs for this level

ragg/ingest_trigger.py

@@ -1,32 +1,54 @@
 import os
-import subprocess
 import sys
-from flask import Blueprint, jsonify
+import subprocess
+import threading
+import traceback
+from flask import Blueprint, jsonify, request
 
 ingest_trigger_bp = Blueprint("ingest_trigger_bp", __name__)
 
+# Prevent concurrent executions
+_ingest_lock = threading.Lock()
+
+@ingest_trigger_bp.route("/ingest/ping", methods=["GET"])
+def ingest_ping():
+    return jsonify({"ok": True, "cwd": os.getcwd()}), 200
+
 @ingest_trigger_bp.route("/ingest", methods=["POST"])
 def run_ingest():
-    """
-    Trigger the ingestion manually via Postman.
-    Runs rag/ingest_all.py script inside the Hugging Face container.
-    """
+    if not _ingest_lock.acquire(blocking=False):
+        return jsonify({"status": "busy", "message": "Ingestion already in progress"}), 409
+
     try:
-        script_path = os.path.join(os.path.dirname(__file__), "ingest_all.py")
-        print(f"🔹 Running ingestion script: {script_path}")
+        # Run as module to ensure package imports work
+        module_name = os.getenv("INGEST_MODULE", "ragg.ingest_all")
+
+        print("Trigger called", flush=True)
+        print("Module:", module_name, flush=True)
+        print("CWD:", os.getcwd(), flush=True)
+        print("PYTHONPATH:", sys.path, flush=True)
 
         result = subprocess.run(
-            [sys.executable, "-m", "rag.ingest_all"],   # <-- run as package module
+            [sys.executable, "-m", module_name],
             capture_output=True,
             text=True,
             cwd=None,
-            timeout=int(os.getenv("INGEST_TIMEOUT_SEC", "1800"))
+            timeout=int(os.getenv("INGEST_TIMEOUT_SEC", "1800"))  # default 30 min
         )
 
+        payload = {
+            "status": "success" if result.returncode == 0 else "error",
+            "returncode": result.returncode,
+            "stdout": result.stdout[-20000:],  # trim if very long
+            "stderr": result.stderr[-20000:],
+        }
+        return jsonify(payload), 200 if result.returncode == 0 else 500
+
+    except Exception:
         return jsonify({
-            "status": "success",
-            "stdout": result.stdout,
-            "stderr": result.stderr
-        })
-    except Exception as e:
-        return jsonify({"status": "error", "message": str(e)}), 500
+            "status": "error",
+            "message": "trigger crashed",
+            "traceback": traceback.format_exc()
+        }), 500
+    finally:
+        _ingest_lock.release()