Create app.py

app.py

@@ -0,0 +1,58 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import pipeline
+
+app = FastAPI()
+
+# Load NER pipeline
+ner_pipeline = pipeline(
+    "ner",
+    model="dslim/bert-large-NER",
+    aggregation_strategy="simple"
+)
+
+class RequestData(BaseModel):
+    sentence: str
+
+@app.get("/")
+def health():
+    return {"status": "ok"}
+
+@app.post("/predict")
+def predict(data: RequestData):
+
+    predictions = ner_pipeline(data.sentence)
+
+    allowed = {"PER", "ORG", "LOC"}
+
+    entities = []
+    seen = set()
+
+    for pred in predictions:
+
+        label = pred["entity_group"]
+
+        if label not in allowed:
+            continue
+
+        start = pred["start"]
+        end = pred["end"]
+
+        key = (start, end)
+
+        if key in seen:
+            continue
+
+        seen.add(key)
+
+        entities.append({
+            "text": pred["word"],
+            "start": start,
+            "end": end,
+            "label": label,
+            "score": float(pred["score"])
+        })
+
+    return {
+        "entities": entities
+    }