fix duplicate issue

app.py

@@ -1,35 +1,46 @@
+import os
 from flask import Flask, request, jsonify
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
+# ⚙️ Khắc phục lỗi không ghi được cache khi deploy trên HFS
+os.environ["HF_HOME"] = "/app/cache"
+os.environ["TRANSFORMERS_CACHE"] = "/app/cache/transformers"
+
 app = Flask(__name__)
 
-# Load model
+# 🚀 Load mô hình
 model_name = "VietAI/vit5-base"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
 
 @app.route("/summarize", methods=["POST"])
 def summarize():
-    data = request.json
-    text = data.get("text", "")
-    if not text.strip():
-        return jsonify({"error": "Missing text"}), 400
+    data = request.get_json()
+    text = data.get("text", "").strip()
+
+    if not text:
+        return jsonify({"error": "Missing 'text' field"}), 400
 
+    # ⚠️ Giới hạn đầu vào (ViT5-base tối đa 512 tokens)
     inputs = tokenizer.encode(text, return_tensors="pt", max_length=512, truncation=True)
+
+    # ✅ Tham số sinh văn bản chống lặp + chất lượng cao
     summary_ids = model.generate(
         inputs,
         max_length=100,
-        min_length=30,
+        min_length=10,
         num_beams=4,
-        length_penalty=2.0,
+        no_repeat_ngram_size=3,
+        repetition_penalty=2.5,
+        length_penalty=1.0,
         early_stopping=True
     )
     summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
     return jsonify({"summary": summary})
 
 @app.route("/", methods=["GET"])
-def root():
-    return "ViT5 summarization API is running."
+def index():
+    return "✅ ViT5 summarization API is running."
 
 if __name__ == "__main__":
     app.run(host="0.0.0.0", port=7860)