Update app.py

app.py

@@ -22,9 +22,6 @@ model.to(device)
 # model_name = "roberta-base"
 # tokenizer = RobertaTokenizer.from_pretrained(model_name, map_location=torch.device('cpu'))
 
-def count_words(text):
-    words = text.split()  # Split the text into a list of words
-    return len(words)
     
 def text_to_sentences(text):
     clean_text = text.replace('\n', ' ')
@@ -63,37 +60,38 @@ def predict(query):
     return real
 
 def findRealProb(data):
-    if data is None or len(data) == 0:
-        return jsonify({'error': 'No query provided'})
-    if len(data) > 9400:
-        return jsonify({'error': 'Cannot analyze more than 9400 characters!'})
-    if count_words(data) > 1500:
-        return jsonify({'error': 'Cannot analyze more than 1500 words'})
-    
-    # return {"Real": predict(data)}
-    chunksOfText = (chunks_of_900(data))
-    results = []
-    for chunk in chunksOfText:
-        outputv1 = predict(chunk)
-        # outputv2 = predict(chunk, modelv2, tokenizerv2)
-        label = "CG"
-        if(outputv1>=0.5):
-            label = "OR"
-        results.append({"Text":chunk, "Label": label, "Confidence":(outputv1)})    
-    ans = 0
-    cnt = 0
-    for result in results:
-        length = len(result["Text"])
-        confidence = result["Confidence"]
-        cnt += length
-        ans = ans + (confidence)*(length)
-    realProb = ans/cnt
-    label = "AI"
-    if realProb > 0.7:
-        label = "Human"
-    elif realProb > 0.3 and realProb < 0.7:
-        label = "Might be AI"
-    return jsonify({"Real": realProb, "Fake": 1-realProb, "Label": label,  "Chunks": results})
+    with app.app_context():
+        if data is None or len(data) == 0:
+            return jsonify({'error': 'No query provided'})
+        if len(data) > 9400:
+            return jsonify({'error': 'Cannot analyze more than 9400 characters!'})
+        if len(data.split()) > 1500:
+            return jsonify({'error': 'Cannot analyze more than 1500 words'})
+        
+        # return {"Real": predict(data)}
+        chunksOfText = (chunks_of_900(data))
+        results = []
+        for chunk in chunksOfText:
+            outputv1 = predict(chunk)
+            # outputv2 = predict(chunk, modelv2, tokenizerv2)
+            label = "CG"
+            if(outputv1>=0.5):
+                label = "OR"
+            results.append({"Text":chunk, "Label": label, "Confidence":(outputv1)})    
+        ans = 0
+        cnt = 0
+        for result in results:
+            length = len(result["Text"])
+            confidence = result["Confidence"]
+            cnt += length
+            ans = ans + (confidence)*(length)
+        realProb = ans/cnt
+        label = "AI"
+        if realProb > 0.7:
+            label = "Human"
+        elif realProb > 0.3 and realProb < 0.7:
+            label = "Might be AI"
+        return jsonify({"Real": realProb, "Fake": 1-realProb, "Label": label,  "Chunks": results})
 
 demo = gr.Interface(
         fn=findRealProb,