Compatibility adjust

app.py

@@ -1,22 +1,52 @@
 from fastapi import FastAPI
 from pydantic import BaseModel
-import requests
-import os
+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")
 
 # ===============================
-# Konfigurasi
+# 🚀 Model configuration
 # ===============================
-HF_ROUTER_URL = "https://router.huggingface.co/hf-inference/models"
-HF_API_KEY = os.getenv("HF_API_KEY")
-
 FINBERT_MODEL = "ProsusAI/finbert"
 LONGFORMER_MODEL = "Miruzen/LongFormer_Skripsi"
 
+device = 0 if torch.cuda.is_available() else -1
+logger.info(f"🧠 Using device: {'GPU' if device == 0 else 'CPU'}")
 
 # ===============================
-# Input Schema
+# 📦 Load Models
+# ===============================
+logger.info("📥 Loading FinBERT model...")
+finbert = pipeline(
+    "text-classification",
+    model=FINBERT_MODEL,
+    tokenizer=FINBERT_MODEL,
+    return_all_scores=True,
+    device=device
+)
+
+logger.info("📥 Loading LongFormer model...")
+longformer = pipeline(
+    "text-classification",
+    model=LONGFORMER_MODEL,
+    tokenizer=LONGFORMER_MODEL,
+    return_all_scores=True,
+    device=device
+)
+
+logger.info("✅ Models loaded successfully!")
+
+
+# ===============================
+# 🧾 Input Schema
 # ===============================
 class InputData(BaseModel):
     title: str | None = None
@@ -24,93 +54,80 @@ class InputData(BaseModel):
 
 
 # ===============================
-# Helper Functions
+# 🧩 Helper Functions
 # ===============================
-def call_hf_model(model_name: str, text: str):
-    """Kirim teks ke model Hugging Face menggunakan router API baru"""
-    headers = {
-        "Authorization": f"Bearer {HF_API_KEY}",
-        "Content-Type": "application/json",
-    }
-
-    payload = {
-        "inputs": text,
-        "options": {"wait_for_model": True}
-    }
-
-    url = f"{HF_ROUTER_URL}/{model_name}"
-    response = requests.post(url, headers=headers, json=payload)
-
-    if response.status_code != 200:
-        raise Exception(
-            f"HF API error ({response.status_code}): {response.text}"
-        )
-
-    return response.json()
-
-
 def extract_scores(predictions):
-    """Convert HF model output into {positive, neutral, negative} dict."""
+    """Convert pipeline output into standardized sentiment dict"""
     scores = {"positive": 0.0, "neutral": 0.0, "negative": 0.0}
+    for item in predictions[0]:
+        label = item["label"].lower()
+        if "pos" in label:
+            scores["positive"] = item["score"]
+        elif "neg" in label:
+            scores["negative"] = item["score"]
+        elif "neu" in label:
+            scores["neutral"] = item["score"]
 
-    # Router API sometimes returns either list of lists or single list
-    data = predictions[0] if isinstance(predictions, list) else predictions
-    if isinstance(data, list) and len(data) > 0 and isinstance(data[0], dict):
-        for item in data:
-            label = item.get("label", "").lower()
-            if "pos" in label:
-                scores["positive"] = item["score"]
-            elif "neg" in label:
-                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
+# 🔍 Main Endpoint
 # ===============================
 @app.post("/analyze")
 def analyze(data: InputData):
-    print("🚀 Incoming request:", data)
-    print("📡 Using router endpoint:", HF_ROUTER_URL)
-    print("🔑 Using key starts with:", HF_API_KEY[:10])
+    logger.info(f"📰 Incoming request: title='{data.title}' | content='{data.content}'")
 
     result = {}
     errors = []
 
-
-    if data.title:
-        try:
-            finbert_out = call_hf_model(FINBERT_MODEL, data.title)
+    try:
+        if data.title:
+            logger.info("⚙️ Analyzing title with FinBERT...")
+            finbert_out = finbert(data.title)
             result["title"] = extract_scores(finbert_out)
-        except Exception as e:
-            errors.append(f"Title analysis error: {e}")
+        else:
+            result["title"] = None
 
-    if data.content:
-        try:
-            longformer_out = call_hf_model(LONGFORMER_MODEL, data.content)
+        if data.content:
+            logger.info("⚙️ Analyzing content with LongFormer...")
+            longformer_out = longformer(data.content)
             result["content"] = extract_scores(longformer_out)
-        except Exception as e:
-            errors.append(f"Content analysis error: {e}")
+        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")
 
-    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)
-    )
+        return {
+            "title": result.get("title"),
+            "content": result.get("content"),
+            "mood_score": mood_score,
+            "status": "ok"
+        }
 
-    return {
-        "mood_score": mood_score,
-        "details": result,
-        "errors": errors,
-        "status": "ok" if not errors else "partial"
-    }
+    except Exception as e:
+        logger.exception("❌ Error during sentiment analysis")
+        errors.append(str(e))
+        return {
+            "title": None,
+            "content": None,
+            "errors": errors,
+            "status": "error"
+        }
 
 
+# ===============================
+# 🩵 Health Check
+# ===============================
 @app.get("/")
 def root():
-    return {"message": "Forex Sentiment API active via router.huggingface.co!"}
+    return {"message": "✅ Forex Sentiment API active and ready!"}