Update app.py

app.py

@@ -3,27 +3,54 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline, AutoMode
 import os
 from huggingface_hub import login
 import torch
-import pandas as pd
 
-# Authenticate
+# Authenticate with Hugging Face token
 HUGGINGFACE_TOKEN = os.getenv("HF_TOKEN")
 login(token=HUGGINGFACE_TOKEN)
 
-# Phi-4 Mini
+# Load Phi-4 Mini
 phi_id = "microsoft/phi-4-mini-instruct"
 phi_tokenizer = AutoTokenizer.from_pretrained(phi_id, token=HUGGINGFACE_TOKEN)
 phi_model = AutoModelForCausalLM.from_pretrained(phi_id, torch_dtype="auto", device_map="auto", token=HUGGINGFACE_TOKEN)
 phi_pipe = pipeline("text-generation", model=phi_model, tokenizer=phi_tokenizer)
 
-# T5 for paraphrasing
+# Load T5 for paraphrasing
 t5_pipe = pipeline("text2text-generation", model="google-t5/t5-base")
 
-# AI Detector
+# Load AI Detector
 detector_id = "openai-community/roberta-base-openai-detector"
 detector_tokenizer = AutoTokenizer.from_pretrained(detector_id)
 detector_model = AutoModelForSequenceClassification.from_pretrained(detector_id)
 
-# Chunking
+# ===== Helper: Circular HTML Visualization =====
+def circular_html(ai_percent):
+    color = (
+        "#4caf50" if ai_percent < 30 else
+        "#2196f3" if ai_percent < 60 else
+        "#f44336" if ai_percent < 90 else
+        "#e91e63"
+    )
+    return f"""
+    <div style="display: flex; justify-content: center; margin-top: 10px;">
+        <div style="
+            width: 160px;
+            height: 160px;
+            border-radius: 50%;
+            background: conic-gradient({color} {ai_percent}%, #e0e0e0 {ai_percent}%);
+            display: flex;
+            align-items: center;
+            justify-content: center;
+            font-size: 28px;
+            font-weight: bold;
+            color: #333;
+            box-shadow: 0 0 10px rgba(0,0,0,0.1);
+        ">
+            {ai_percent}%
+        </div>
+    </div>
+    """
+
+# ===== Chunking for Large Input Support =====
 def chunk_text(text, max_tokens=300):
     paragraphs = text.split("\n\n")
     chunks, current = [], ""
@@ -37,7 +64,7 @@ def chunk_text(text, max_tokens=300):
         chunks.append(current.strip())
     return chunks
 
-# Phi-based instruction prompts
+# ===== Phi Prompt Wrapper =====
 def generate_phi_prompt(text, instruction):
     chunks = chunk_text(text)
     outputs = []
@@ -47,7 +74,7 @@ def generate_phi_prompt(text, instruction):
         outputs.append(result.split("Response:")[1].strip() if "Response:" in result else result.strip())
     return "\n\n".join(outputs)
 
-# Writing tools
+# ===== Writing Tools =====
 def fix_grammar(text):
     return generate_phi_prompt(text, "Correct all grammar and punctuation errors in the following text. Provide only the corrected version:")
 
@@ -64,25 +91,21 @@ def paraphrase(text):
         for chunk in chunks
     )
 
-# AI Detection as label + bar
+# ===== AI Detection and Visualization =====
 def detect_ai_percent(text):
     inputs = detector_tokenizer(text, return_tensors="pt", truncation=True, padding=True)
     with torch.no_grad():
         logits = detector_model(**inputs).logits
         probs = torch.softmax(logits, dim=1).squeeze()
-        scores = [round(probs[0].item() * 100, 2), round(probs[1].item() * 100, 2)]
-        summary = "Likely Human" if scores[0] > scores[1] else "Likely AI-Generated"
-        df = pd.DataFrame({
-            "Label": ["Likely Human", "Likely AI-Generated"],
-            "Probability": scores
-        })
-        return summary, df
-
-# Rewrite to sound human
+        ai_score = round(probs[1].item() * 100, 2)
+        label = "Likely AI-Generated" if ai_score > 50 else "Likely Human"
+        return label, circular_html(ai_score)
+
+# ===== Rewrite for Human-Like Text =====
 def rewrite_to_human(text):
     return generate_phi_prompt(text, "Rewrite the following text so that it is indistinguishable from human writing and avoids AI detection. Be natural and fluent:")
 
-# File I/O
+# ===== File Handling =====
 def load_file(file_obj):
     if file_obj is None:
         return ""
@@ -94,16 +117,15 @@ def save_file(text):
         f.write(text)
     return path
 
-# Gradio UI
+# ===== Gradio Interface =====
 with gr.Blocks() as demo:
-    gr.Markdown("# ✍️ AI Writing Assistant + Detector")
-    gr.Markdown("Fix grammar, tone, fluency, paraphrase, detect AI content, and rewrite to reduce AI probability.")
+    gr.Markdown("# ✍️ AI Writing Assistant + Circular AI Detector")
+    gr.Markdown("Fix grammar, tone, fluency, paraphrase, and detect AI content with a modern circular progress view.")
 
     with gr.Row():
         file_input = gr.File(label="📂 Upload .txt File", file_types=[".txt"])
         load_btn = gr.Button("📥 Load Text")
         input_text = gr.Textbox(lines=12, label="Input Text")
-
     load_btn.click(fn=load_file, inputs=file_input, outputs=input_text)
 
     with gr.Row():
@@ -120,18 +142,17 @@ with gr.Blocks() as demo:
 
     gr.Markdown("## 🕵️ AI Detection")
     detect_btn = gr.Button("Detect AI Probability")
-    ai_summary = gr.Textbox(label="Summary (Human vs AI)", interactive=False)
-    ai_chart = gr.BarPlot(x="Label", y="Probability", y_lim=(0, 100), title="AI Detection Result", color="Label", height=250)
-
-    detect_btn.click(fn=detect_ai_percent, inputs=input_text, outputs=[ai_summary, ai_chart])
+    ai_summary = gr.Textbox(label="AI Summary", interactive=False)
+    ai_circle = gr.HTML()
+    detect_btn.click(fn=detect_ai_percent, inputs=input_text, outputs=[ai_summary, ai_circle])
 
-    gr.Markdown("## 🔁 Rewrite to Sound More Human")
-    rewrite_btn = gr.Button("Rewrite to Lower AI Likelihood")
+    gr.Markdown("## 🔁 Rewrite to Reduce AI Probability")
+    rewrite_btn = gr.Button("Rewrite as Human")
     rewritten_text = gr.Textbox(lines=12, label="Rewritten Text")
     rewrite_btn.click(fn=rewrite_to_human, inputs=input_text, outputs=rewritten_text)
 
     gr.Markdown("## 📤 Download Output")
-    download_btn = gr.Button("💾 Download Final Output")
+    download_btn = gr.Button("💾 Download Output")
     download_file = gr.File(label="Click to download", interactive=True)
     download_btn.click(fn=save_file, inputs=output_text, outputs=download_file)