Create app.py

app.py

@@ -0,0 +1,88 @@
+from flask import Flask, request
+from transformers import RobertaForSequenceClassification, RobertaTokenizer, RobertaConfig
+import torch
+import gradio as gr
+import os
+import re
+app = Flask(__name__)
+
+ACCESS_TOKEN = os.environ["ACCESS_TOKEN"]
+config = RobertaConfig.from_pretrained("PirateXX/ChatGPT-Text-Detector", use_auth_token= ACCESS_TOKEN)
+model = RobertaForSequenceClassification.from_pretrained("PirateXX/ChatGPT-Text-Detector", use_auth_token= ACCESS_TOKEN, config = config)
+
+model_name = "roberta-base"
+tokenizer = RobertaTokenizer.from_pretrained(model_name, map_location=torch.device('cpu'))
+
+# function to break text into an array of sentences
+def text_to_sentences(text):
+    re.sub(r'(?<=[.!?])(?=[^\s])', r' ', text)
+    return re.split(r'[.!?]', text)
+
+# function to concatenate sentences into chunks of size 600 or less
+def chunks_of_600(text, chunk_size=600):
+    sentences = text_to_sentences(text)
+    chunks = []
+    current_chunk = ""
+    for sentence in sentences:
+        if len(current_chunk + sentence) <= chunk_size:
+            current_chunk += sentence
+        else:
+            chunks.append(current_chunk)
+            current_chunk = sentence
+    chunks.append(current_chunk)
+    return chunks
+    
+def predict(query, device="cpu"):
+    tokens = tokenizer.encode(query)
+    all_tokens = len(tokens)
+    tokens = tokens[:tokenizer.model_max_length - 2]
+    used_tokens = len(tokens)
+    tokens = torch.tensor([tokenizer.bos_token_id] + tokens + [tokenizer.eos_token_id]).unsqueeze(0)
+    mask = torch.ones_like(tokens)
+
+    with torch.no_grad():
+        logits = model(tokens.to(device), attention_mask=mask.to(device))[0]
+        probs = logits.softmax(dim=-1)
+
+    fake, real = probs.detach().cpu().flatten().numpy().tolist()
+    return real
+
+def findRealProb(text):
+    chunksOfText = (chunks_of_600(text))
+    results = []
+    for chunk in chunksOfText:
+        output = predict(chunk)
+        results.append([output, len(chunk)])
+    
+    ans = 0
+    for prob, length in results:
+        ans = ans + prob*length
+    realProb = ans/len(text)
+    return {"Real": realProb, "Fake": 1-realProb, "results": results, "text": text}
+
+def upload_file():
+    if 'pdfFile' in request.files:
+        pdf_file = request.files['pdfFile']
+        text = ""
+        with pdfplumber.open(pdf_file) as pdf:
+            cnt = 0
+            for page in pdf.pages:
+                cnt+=1
+                text+=(page.extract_text(x_tolerance = 1))
+                print(text)
+                if cnt>5: 
+                    break
+            return findRealProb(text)
+            # return jsonify({'text': text})
+    else:
+        return {"error":'No PDF file found in request'}
+
+
+demo = gr.Interface(
+        fn=upload_file, 
+        inputs=gr.File(), 
+         article = "Visit <a href = \"https://ai-content-detector.online/\">AI Content Detector</a> for better user experience!",
+        outputs=gr.outputs.JSON(),
+        interpretation="default",
+
+demo.launch(show_api=False)