Update app.py

app.py

@@ -1,124 +1,150 @@
 import gradio as gr
-import os
-import threading
-import base64
-from io import BytesIO
 from groq import Groq
-from diffusers import StableDiffusionPipeline
-import torch
+import os
+import threading  # Import threading module
 
-# 🔹 Initialize Groq API Client (FREE)
-groq_client = Groq(api_key=os.getenv("GROQ_API_KEY"))
+# Initialize Groq client with your API key
+client = Groq(api_key=os.environ["GROQ_API_KEY"])
 
-# 🔹 Load Text-to-Image Models (Updated to use diffusers for Stable Diffusion)
+# Load Text-to-Image Models
 model1 = gr.load("models/prithivMLmods/SD3.5-Turbo-Realism-2.0-LoRA")
 model2 = gr.load("models/Purz/face-projection")
 
-# ✅ Load Stable Diffusion Model Properly (Using diffusers)
-model3 = StableDiffusionPipeline.from_pretrained(
-    "stablediffusion/stable-diffusion-2-1",
-    torch_dtype=torch.float16
-).to("cuda")  # Move to GPU if available
-
-# 🔹 Stop Event for Threading
+# Stop event for threading (image generation)
 stop_event = threading.Event()
 
-# 🔹 Convert PIL image to Base64
-def pil_to_base64(pil_image, image_format="jpeg"):
-    buffered = BytesIO()
-    pil_image.save(buffered, format=image_format)
-    base64_string = base64.b64encode(buffered.getvalue()).decode("utf-8")
-    return base64_string, image_format
-
-# 🔹 Function for Visual Question Answering (VQA) with Mixtral-8x7B
-def answer_question(text, image, temperature=0.0, max_tokens=1024):
-    base64_string, file_format = pil_to_base64(image)
-
-    messages = [
-        {
-            "role": "user",
-            "content": [
-                {"type": "text", "text": text},
-                {"type": "image_url", "image_url": f"data:image/{file_format};base64,{base64_string}"}
-            ]
-        }
-    ]
+# Function to generate tutor output (lesson, question, feedback)
+def generate_tutor_output(subject, difficulty, student_input):
+    prompt = f"""
+    You are an expert tutor in {subject} at the {difficulty} level. 
+    The student has provided the following input: "{student_input}"
+    
+    Please generate:
+    1. A brief, engaging lesson on the topic (2-3 paragraphs)
+    2. A thought-provoking question to check understanding
+    3. Constructive feedback on the student's input
     
-    chat_response = groq_client.chat.completions.create(
-        model="mixtral-8x7b-32768",
-        messages=messages,
-        temperature=temperature,
-        max_tokens=max_tokens
+    Format your response as a JSON object with keys: "lesson", "question", "feedback"
+    """
+    
+    completion = client.chat.completions.create(
+        messages=[{
+            "role": "system",
+            "content": f"You are the world's best AI tutor, renowned for your ability to explain complex concepts in an engaging, clear, and memorable way and giving math examples. Your expertise in {subject} is unparalleled, and you're adept at tailoring your teaching to {difficulty} level students."
+        }, {
+            "role": "user",
+            "content": prompt,
+        }],
+        model="mixtral-8x7b-32768",  # Model for text generation
+        max_tokens=1000,
     )
+    
+    return completion.choices[0].message.content
 
-    return chat_response.choices[0].message.content
-
-# 🔹 Function to Generate Three Images (Multi-Output)
-def generate_images(prompt):
+# Function to generate images based on model selection
+def generate_images(text, selected_model):
     stop_event.clear()
-    img1 = model1.predict(prompt)
-    img2 = model2.predict(prompt)
 
-    # ✅ Fix: Use Stable Diffusion correctly
-    img3 = model3(prompt).images[0]  # Get first image
+    if selected_model == "Model 1 (Turbo Realism)":
+        model = model1
+    elif selected_model == "Model 2 (Face Projection)":
+        model = model2
+    else:
+        return ["Invalid model selection."] * 3
 
-    return img1, img2, img3
+    results = []
+    for i in range(3):
+        if stop_event.is_set():
+            return ["Image generation stopped by user."] * 3
 
-# 🔹 Clear All Fields
-def clear_all():
-    return "", None, "", None, None, None
+        modified_text = f"{text} variation {i+1}"
+        result = model(modified_text)
+        results.append(result)
 
-# 🔹 Set up Gradio Interface
+    return results
+
+# Set up the Gradio interface
 with gr.Blocks() as demo:
-    gr.Markdown("# 🎓 AI Tutor, VQA & Image Generation")
+    gr.Markdown("# 🎓 Your AI Tutor with Visuals & Images")
 
-    # 🔹 Section 1: Visual Question Answering (Groq)
-    gr.Markdown("## 🖼️ Visual Question Answering (Mixtral-8x7B)")
+    # Section for generating Text-based output (lesson, question, feedback)
     with gr.Row():
         with gr.Column(scale=2):
-            question = gr.Textbox(placeholder="Ask about the image...", lines=2)
-            image = gr.Image(type="pil")
-            with gr.Row():
-                temperature = gr.Slider(label="Temperature", minimum=0.0, maximum=1.0, value=0.0, step=0.1)
-                max_tokens = gr.Slider(label="Max Tokens", minimum=128, maximum=2048, value=1024, step=128)
+            # Input fields for subject, difficulty, and student input for textual output
+            subject = gr.Dropdown(
+                ["Math", "Science", "History", "Literature", "Code", "AI"], 
+                label="Subject", 
+                info="Choose the subject of your lesson"
+            )
+            difficulty = gr.Radio(
+                ["Beginner", "Intermediate", "Advanced"], 
+                label="Difficulty Level", 
+                info="Select your proficiency level"
+            )
+            student_input = gr.Textbox(
+                placeholder="Type your query here...", 
+                label="Your Input", 
+                info="Enter the topic you want to learn"
+            )
+            submit_button_text = gr.Button("Generate Lesson & Question", variant="primary")
         
         with gr.Column(scale=3):
-            output_text = gr.Textbox(lines=10, label="Mixtral VQA Response")
+            # Output fields for lesson, question, and feedback
+            lesson_output = gr.Markdown(label="Lesson")
+            question_output = gr.Markdown(label="Comprehension Question")
+            feedback_output = gr.Markdown(label="Feedback")
     
+    # Section for generating Visual output
     with gr.Row():
-        clear_btn = gr.Button("Clear", variant="secondary")
-        submit_btn_vqa = gr.Button("Submit", variant="primary")
-
-    # 🔹 Section 2: Image Generation (3 Outputs)
-    gr.Markdown("## 🎨 AI-Generated Images (3 Variations)")
-    with gr.Row():
-        prompt = gr.Textbox(placeholder="Describe the image you want...", lines=2)
-        generate_btn = gr.Button("Generate Images", variant="primary")
-
-    with gr.Row():
-        image1 = gr.Image(label="Image 1")
-        image2 = gr.Image(label="Image 2")
-        image3 = gr.Image(label="Image 3")
-
-    # 🔹 VQA Processing
-    submit_btn_vqa.click(
-        fn=answer_question,
-        inputs=[question, image, temperature, max_tokens],
-        outputs=[output_text]
-    )
-
-    # 🔹 Image Generation Processing
-    generate_btn.click(
-        fn=generate_images,
-        inputs=[prompt],
-        outputs=[image1, image2, image3]
+        with gr.Column(scale=2):
+            # Input fields for text and model selection for image generation
+            model_selector = gr.Radio(
+                ["Model 1 (Turbo Realism)", "Model 2 (Face Projection)"],
+                label="Select Image Generation Model",
+                value="Model 1 (Turbo Realism)"
+            )
+            submit_button_visual = gr.Button("Generate Visuals", variant="primary")
+        
+        with gr.Column(scale=3):
+            # Output fields for generated images
+            output1 = gr.Image(label="Generated Image 1")
+            output2 = gr.Image(label="Generated Image 2")
+            output3 = gr.Image(label="Generated Image 3")
+    
+    gr.Markdown("""
+    ### How to Use
+    1. **Text Section**: Select a subject and difficulty, type your query, and click 'Generate Lesson & Question' to get your personalized lesson, comprehension question, and feedback.
+    2. **Visual Section**: Select the model for image generation, then click 'Generate Visuals' to receive 3 variations of an image based on your topic.
+    3. Review the AI-generated content to enhance your learning experience!
+    """)
+    
+    def process_output_text(subject, difficulty, student_input):
+        try:
+            tutor_output = generate_tutor_output(subject, difficulty, student_input)
+            parsed = eval(tutor_output)  # Convert string to dictionary
+            return parsed["lesson"], parsed["question"], parsed["feedback"]
+        except:
+            return "Error parsing output", "No question available", "No feedback available"
+    
+    def process_output_visual(text, selected_model):
+        try:
+            images = generate_images(text, selected_model)  # Generate images
+            return images[0], images[1], images[2]
+        except:
+            return None, None, None
+    
+    # Generate Text-based Output
+    submit_button_text.click(
+        fn=process_output_text,
+        inputs=[subject, difficulty, student_input],
+        outputs=[lesson_output, question_output, feedback_output]
     )
-
-    # 🔹 Clear All Inputs
-    clear_btn.click(
-        fn=clear_all,
-        inputs=[],
-        outputs=[question, image, output_text, image1, image2, image3]
+    
+    # Generate Visual Output
+    submit_button_visual.click(
+        fn=process_output_visual,
+        inputs=[student_input, model_selector],
+        outputs=[output1, output2, output3]
     )
 
 if __name__ == "__main__":