Create metadata.py

utils/metadata.py

@@ -0,0 +1,25 @@
+from transformers import pipeline
+
+model = "dslim/bert-base-NER"
+ner = pipeline("ner", model=model, tokenizer=model, grouped_entities=True)
+
+def extract_metadata(text):
+    if not text.strip():
+        return {"error": "No input provided."}
+
+    text = text[:1000]
+    entities = ner(text)
+
+    result = {
+        "DATE": [],
+        "PERSON": [],
+        "ORGANIZATION": [],
+        "LOCATION": []
+    }
+
+    for ent in entities:
+        label = ent["entity_group"]
+        if label in result and ent["word"] not in result[label]:
+            result[label].append(ent["word"])
+
+    return result