Create app.py

app.py

@@ -0,0 +1,64 @@
+# app.py — HuggingFace Space (FastAPI)
+# Serves our fine-tuned sentiment model as a REST API
+# Deploy this to: huggingface.co/spaces/YOUR_USERNAME/creatorpulse-api
+
+from fastapi import FastAPI
+from pydantic import BaseModel
+from typing import List
+from transformers import pipeline
+import os
+
+app = FastAPI(title="CreatorPulse Sentiment API")
+
+# ── Load model once on startup ─────────────────────────────────────────────────
+HF_USERNAME = os.getenv("HF_USERNAME", "ningaraddi")
+MODEL_REPO  = f"{HF_USERNAME}/creatorpulse-sentiment"
+
+print(f"Loading model from {MODEL_REPO}...")
+
+classifier = pipeline(
+    "sentiment-analysis",
+    model=MODEL_REPO,
+    tokenizer=MODEL_REPO,
+    truncation=True,
+    max_length=128,
+    device=-1        # CPU on free tier — fast enough for our use case
+)
+
+print("✅ Model loaded and ready.")
+
+# ── Request / Response schemas ──────────────────────────────────────────────────
+class ClassifyRequest(BaseModel):
+    texts: List[str]      # up to 100 comments at once
+
+class PredictionResult(BaseModel):
+    text:       str
+    label:      str       # POSITIVE | NEUTRAL | NEGATIVE
+    confidence: float
+
+class ClassifyResponse(BaseModel):
+    predictions: List[PredictionResult]
+
+# ── Health check ────────────────────────────────────────────────────────────────
+@app.get("/")
+def health():
+    return {"status": "ok", "model": MODEL_REPO}
+
+# ── Main classify endpoint ──────────────────────────────────────────────────────
+@app.post("/classify", response_model=ClassifyResponse)
+def classify(request: ClassifyRequest):
+    # Limit to 100 texts per call to avoid timeout
+    texts = request.texts[:100]
+
+    results = classifier(texts, batch_size=16)
+
+    predictions = [
+        PredictionResult(
+            text=text,
+            label=result["label"],          # POSITIVE / NEUTRAL / NEGATIVE
+            confidence=round(result["score"], 4)
+        )
+        for text, result in zip(texts, results)
+    ]
+
+    return ClassifyResponse(predictions=predictions)