Update app.py

app.py

@@ -2,62 +2,43 @@ from fastapi import FastAPI
 from pydantic import BaseModel
 from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
 import torch
-import logging
 
-# ===============================
-# 🔧 Logging setup
-# ===============================
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger("forex-sentiment")
-
-app = FastAPI(title="Forex Sentiment API", version="2.0")
+app = FastAPI(title="Forex Sentiment API", version="1.0")
 
 # ===============================
-# 🚀 Model configuration
+# Load Models
 # ===============================
-FINBERT_MODEL = "ProsusAI/finbert"
-LONGFORMER_MODEL = "Miruzen/LongFormer_Skripsi"
+finbert_name = "ProsusAI/finbert"
+longformer_name = "Miruzen/LongFormer_Skripsi"
 
 device = 0 if torch.cuda.is_available() else -1
-logger.info(f"🧠 Using device: {'GPU' if device == 0 else 'CPU'}")
 
-# ===============================
-# 📦 Load Models
-# ===============================
-logger.info("📥 Loading FinBERT model...")
+print("📥 Loading FinBERT model...")
 finbert = pipeline(
     "text-classification",
-    model=FINBERT_MODEL,
-    tokenizer=FINBERT_MODEL,
+    model=finbert_name,
+    tokenizer=finbert_name,
     return_all_scores=True,
-    device=device
+    device=device,
 )
 
-logger.info("📥 Loading LongFormer model...")
+print("📥 Loading LongFormer model...")
 longformer = pipeline(
     "text-classification",
-    model=LONGFORMER_MODEL,
-    tokenizer=LONGFORMER_MODEL,
+    model=longformer_name,
+    tokenizer=longformer_name,
     return_all_scores=True,
-    device=device
+    device=device,
 )
 
-logger.info("✅ Models loaded successfully!")
 
-
-# ===============================
-# 🧾 Input Schema
-# ===============================
 class InputData(BaseModel):
     title: str | None = None
     content: str | None = None
 
 
-# ===============================
-# 🧩 Helper Functions
-# ===============================
 def extract_scores(predictions):
-    """Convert pipeline output into standardized sentiment dict"""
+    """Convert HF model output into {positive, neutral, negative} dict."""
     scores = {"positive": 0.0, "neutral": 0.0, "negative": 0.0}
     for item in predictions[0]:
         label = item["label"].lower()
@@ -67,67 +48,39 @@ def extract_scores(predictions):
             scores["negative"] = item["score"]
         elif "neu" in label:
             scores["neutral"] = item["score"]
+    dominant = max(scores, key=scores.get)
+    return {"label": dominant, "scores": scores}
 
-    sentiment = max(scores, key=scores.get)
-    return {"label": sentiment, "scores": scores}
 
-
-# ===============================
-# 🔍 Main Endpoint
-# ===============================
 @app.post("/analyze")
 def analyze(data: InputData):
-    logger.info(f"📰 Incoming request: title='{data.title}' | content='{data.content}'")
-
-    result = {}
-    errors = []
-
-    try:
-        if data.title:
-            logger.info("⚙️ Analyzing title with FinBERT...")
-            finbert_out = finbert(data.title)
-            result["title"] = extract_scores(finbert_out)
-        else:
-            result["title"] = None
-
-        if data.content:
-            logger.info("⚙️ Analyzing content with LongFormer...")
-            longformer_out = longformer(data.content)
-            result["content"] = extract_scores(longformer_out)
-        else:
-            result["content"] = None
-
-        # 🧮 Mood score sederhana
-        mood_score = (
-            (result.get("title", {}).get("scores", {}).get("positive", 0) +
-             result.get("content", {}).get("scores", {}).get("positive", 0))
-            - (result.get("title", {}).get("scores", {}).get("negative", 0) +
-               result.get("content", {}).get("scores", {}).get("negative", 0))
-        )
-
-        logger.info("✅ Analysis completed successfully")
-
-        return {
-            "title": result.get("title"),
-            "content": result.get("content"),
-            "mood_score": mood_score,
-            "status": "ok"
-        }
-
-    except Exception as e:
-        logger.exception("❌ Error during sentiment analysis")
-        errors.append(str(e))
-        return {
-            "title": None,
-            "content": None,
-            "errors": errors,
-            "status": "error"
-        }
+    title_result, content_result = None, None
+
+    if data.title:
+        finbert_out = finbert(data.title)
+        title_result = extract_scores(finbert_out)
+
+    if data.content:
+        longformer_out = longformer(data.content)
+        content_result = extract_scores(longformer_out)
+
+    mood_score = (
+        (title_result["scores"].get("positive", 0) if title_result else 0)
+        + (content_result["scores"].get("positive", 0) if content_result else 0)
+        - (title_result["scores"].get("negative", 0) if title_result else 0)
+        - (content_result["scores"].get("negative", 0) if content_result else 0)
+    )
+
+    return {
+        "status": "ok",
+        "mood_score": mood_score,
+        "details": {     # 🔹 <── inilah kunci penting yang ditunggu Supabase!
+            "title": title_result,
+            "content": content_result,
+        },
+    }
 
 
-# ===============================
-# 🩵 Health Check
-# ===============================
 @app.get("/")
 def root():
-    return {"message": "✅ Forex Sentiment API active and ready!"}
+    return {"message": "Forex Sentiment API active!"}