Update app.py

app.py

@@ -1,9 +1,11 @@
-import os
-os.system("pip install numpy<2 --quiet")
-
+from flask import Flask, request, jsonify
+from flask_cors import CORS  # To handle CORS if needed
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
+app = Flask(__name__)
+CORS(app)  # Enable CORS for frontend communication
+
 MODEL_NAME = "tanusrich/Mental_Health_Chatbot"
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
@@ -22,22 +24,28 @@ except Exception as e:
 
 @app.route("/chat", methods=["POST"])
 def chat():
-    data = request.json
-    user_input = data.get("message", "")
+    try:
+        data = request.json
+        user_input = data.get("message", "").strip()
+
+        if not user_input:
+            return jsonify({"error": "Message is required"}), 400
 
-    if not user_input:
-        return jsonify({"error": "Message is required"}), 400
+        inputs = tokenizer(user_input, return_tensors="pt").to(device)
 
-    inputs = tokenizer(user_input, return_tensors="pt").to(device)
+        with torch.no_grad():
+            outputs = model.generate(
+                input_ids=inputs["input_ids"], 
+                attention_mask=inputs["attention_mask"], 
+                max_length=150
+            )
 
-    with torch.no_grad():
-        outputs = model.generate(
-            input_ids=inputs["input_ids"], 
-            attention_mask=inputs["attention_mask"], 
-            max_length=150
-        )
+        response_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-    response_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        return jsonify({"response": response_text})
 
-    return jsonify({"response": response_text})
+    except Exception as e:
+        return jsonify({"error": f"Internal Server Error: {str(e)}"}), 500
 
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=5000, debug=True)