Create app/sentiment.py

app/sentiment.py

@@ -0,0 +1,28 @@
+"""
+Tiny wrapper around HF transformers sentiment pipeline with in‑memory cache.
+"""
+from transformers import pipeline
+from functools import lru_cache
+import hashlib, logging
+
+_sentiment = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")
+
+class SentimentCache:
+    latest_id: int = 0
+    latest_result: dict = {}
+
+    @classmethod
+    def _hash(cls, text: str) -> str:
+        return hashlib.sha256(text.encode()).hexdigest()
+
+    @classmethod
+    @lru_cache(maxsize=128)
+    def _analyze(cls, text: str):
+        return _sentiment(text)[0]
+
+    @classmethod
+    def compute(cls, text: str):
+        res = cls._analyze(text)
+        cls.latest_id += 1
+        cls.latest_result = {"text": text, **res}
+        logging.info("🧠 sentiment computed")