Update app.py

app.py

@@ -30,7 +30,7 @@ def generate_tutor_output(subject, difficulty, student_input):
     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."
+            "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. Your expertise in {subject} is unparalleled, and you're adept at tailoring your teaching to {difficulty} level students."
         }, {
             "role": "user",
             "content": prompt,
@@ -63,14 +63,40 @@ def generate_images(text, selected_model):
 
     return results
 
+# New function for processing visual input
+def process_visual_input(image, task, question=""):
+    """Processes the uploaded image based on the selected task."""
+    if task == "Image Captioning":
+        prompt = "Describe this image in detail."
+    elif task == "OCR (Text Extraction)":
+        prompt = "Extract all readable text from this image."
+    elif task == "Visual Question Answering":
+        prompt = f"Answer this question based on the image: {question}"
+    else:
+        return "Invalid task selected."
+
+    # Sending image + prompt to the model
+    completion = client.chat.completions.create(
+        messages=[{
+            "role": "system",
+            "content": "You are an expert AI that analyzes images and provides captions, extracts text, or answers visual questions."
+        }, {
+            "role": "user",
+            "content": prompt,
+        }],
+        model="llava-1.5-7b",  # Using a vision-language model
+        max_tokens=500,
+    )
+
+    return completion.choices[0].message.content
+
 # Set up the Gradio interface
 with gr.Blocks() as demo:
     gr.Markdown("# 🎓 Your AI Tutor with Visuals & Images")
 
-    # Section for generating Text-based output (lesson, question, feedback)
+    # Section 1: Text-based Learning (Lesson, Question, Feedback)
     with gr.Row():
         with gr.Column(scale=2):
-            # Input fields for subject, difficulty, and student input for textual output
             subject = gr.Dropdown(
                 ["Math", "Science", "History", "Literature", "Code", "AI"], 
                 label="Subject", 
@@ -89,15 +115,13 @@ with gr.Blocks() as demo:
             submit_button_text = gr.Button("Generate Lesson & Question", variant="primary")
         
         with gr.Column(scale=3):
-            # 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
+    # Section 2: Text-based Image Generation
     with gr.Row():
         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",
@@ -106,18 +130,40 @@ with gr.Blocks() as demo:
             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!
-    """)
-    
+
+    # Section 3: Visual Input Processing
+    with gr.Row():
+        with gr.Column(scale=2):
+            image_input = gr.Image(label="Upload an Image", type="filepath")
+            task_selector = gr.Radio(
+                ["Image Captioning", "OCR (Text Extraction)", "Visual Question Answering"],
+                label="Select Image Processing Task",
+                value="Image Captioning"
+            )
+            question_input = gr.Textbox(
+                placeholder="Enter question (only for VQA)", 
+                label="Question (Optional)",
+                visible=False
+            )
+            submit_button_visual_input = gr.Button("Process Image", variant="primary")
+        
+        with gr.Column(scale=3):
+            visual_output = gr.Markdown(label="Image Analysis Result")
+
+    # Toggle visibility of question input for VQA
+    def toggle_question_visibility(task):
+        return gr.update(visible=(task == "Visual Question Answering"))
+
+    task_selector.change(
+        fn=toggle_question_visibility, 
+        inputs=[task_selector], 
+        outputs=[question_input]
+    )
+
+    # Process text-based learning
     def process_output_text(subject, difficulty, student_input):
         try:
             tutor_output = generate_tutor_output(subject, difficulty, student_input)
@@ -126,21 +172,27 @@ with gr.Blocks() as demo:
         except:
             return "Error parsing output", "No question available", "No feedback available"
     
+    # Process image generation
     def process_output_visual(text, selected_model):
         try:
-            images = generate_images(text, selected_model)  # Generate images
+            images = generate_images(text, selected_model)
             return images[0], images[1], images[2]
         except:
             return None, None, None
-    
-    # Generate Text-based Output
+
+    # Process visual input (image)
+    submit_button_visual_input.click(
+        fn=process_visual_input,
+        inputs=[image_input, task_selector, question_input],
+        outputs=[visual_output]
+    )
+
     submit_button_text.click(
         fn=process_output_text,
         inputs=[subject, difficulty, student_input],
         outputs=[lesson_output, question_output, feedback_output]
     )
     
-    # Generate Visual Output
     submit_button_visual.click(
         fn=process_output_visual,
         inputs=[student_input, model_selector],