Feb 5

1. 08:58

   Create index.js

   VIATEUR-AI
   Verified signature

   ff394a4
2. 08:54

   Create yarn.lock

   VIATEUR-AI
   Verified signature

   f44f751
3. 08:53

   Create vite.config.js

   VIATEUR-AI
   Verified signature

   3d27550
4. 08:52

   Create package.json

   VIATEUR-AI
   Verified signature

   d6e4ffb
5. 08:51

   Create package-lock.json

   VIATEUR-AI
   Verified signature

   fa66939
6. 08:47

   Create nginx.conf

   VIATEUR-AI
   Verified signature

   ae89f36
7. 08:46

   Create index.html

   VIATEUR-AI
   Verified signature

   a77ebb2
8. 08:45

   Create eslint.config.js

   VIATEUR-AI
   Verified signature

   05f9b18
9. 08:45

   Update README.md

   VIATEUR-AI
   Verified signature

   084956d
10. 08:43

    Update README.md

    VIATEUR-AI
    Verified signature

    f4f5667
11. 08:42

    Create Dockerfile

    VIATEUR-AI
    Verified signature

    37122d8
12. 08:41

    Create .gitignore

    VIATEUR-AI
    Verified signature

    a0e80ec
13. 08:40

    Update .gitattributes

    VIATEUR-AI
    Verified signature

    eada46c
14. 08:40

    Delete requirements.txt

    VIATEUR-AI
    Verified signature

    0ae033a
15. 08:40

    Delete app.py

    VIATEUR-AI
    Verified signature

    15d28f0
16. 08:33

    Update requirements.txt

    VIATEUR-AI
    Verified signature

    d501a5f
17. 08:31

    Update requirements.txt

    VIATEUR-AI
    Verified signature

    9d81c60
18. 08:29

    Update requirements.txt

    VIATEUR-AI
    Verified signature

    cfa9537
19. 08:29

    import gradio as gr import cv2 import mediapipe as mp mp_hands = mp.solutions.hands hands = mp_hands.Hands(static_image_mode=False, max_num_hands=2, min_detection_confidence=0.5, min_tracking_confidence=0.5) # AI feedback logic based on hand positions def surgical_feedback_webcam(video_path): cap = cv2.VideoCapture(video_path) feedback_messages = [] while cap.isOpened(): ret, frame = cap.read() if not ret: break frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) result = hands.process(frame_rgb) if result.multi_hand_landmarks: for hand_landmarks in result.multi_hand_landmarks: wrist_y = hand_landmarks.landmark[mp_hands.HandLandmark.WRIST].y if wrist_y < 0.3: feedback_messages.append("Gabanya height y'igikoresho.") else: feedback_messages.append("Position y'amaboko ni nziza.") cap.release() return "\n".join(feedback_messages[-5:]) # last 5 feedbacks with gr.Blocks() as demo: gr.Markdown("# Full Interactive 3D Surgical Training AI") gr.Markdown("Reba 3D mannequin, ukoreshe webcam cyangwa wandike surgical action, AI izaguha feedback ako kanya.") with gr.Row(): # Left: 3D mannequin gr.HTML( """ <model-viewer src="assets/mannequin.glb" alt="3D Mannequin" auto-rotate camera-controls style="width: 400px; height: 400px;"> </model-viewer> """ ) # Right: User input + feedback with gr.Column(): user_input = gr.Textbox(label="Describe your surgical action") video_input = gr.Video(label="Or upload hand movement video") feedback = gr.Textbox(label="AI Feedback") # Text input feedback user_input.submit(lambda x: "Byiza! Komeza gutya." if x=="" else "AI Feedback: "+x, user_input, feedback) # Video input feedback video_input.upload(surgical_feedback_webcam, video_input, feedback) demo.launch()

    VIATEUR-AI
    Verified signature

    a66209f
20. 08:26

    import gradio as gr # Simple AI feedback def surgical_feedback(action_description): action = action_description.lower() if "scalpel too high" in action: return "Gabanya umuvuduko w'igikoresho." elif "cut too deep" in action: return "Gabanya depth y'igikata." elif "incorrect angle" in action: return "Hindura angle y'igikoresho." else: return "Byiza! Komeza gutya." with gr.Blocks() as demo: gr.Markdown("# 3D Surgical Training AI Prototype") gr.Markdown( "Reba mannequin hasi, wandike uko wakoze igikorwa, AI izaguha feedback." ) with gr.Row(): # 3D mannequin gr.HTML( """ <model-viewer src="assets/mannequin.glb" alt="3D Mannequin" auto-rotate camera-controls style="width: 400px; height: 400px;"> </model-viewer> """ ) # User input + AI feedback with gr.Column(): user_input = gr.Textbox(label="Describe your surgical action") feedback = gr.Textbox(label="AI Feedback") user_input.submit(surgical_feedback, user_input, feedback) demo.launch()

    VIATEUR-AI
    Verified signature

    a01cf00
21. 08:21

    gradio

    VIATEUR-AI
    Verified signature

    6a0f40e
22. 08:20

    import gradio as gr # Simple AI feedback logic def surgical_feedback(action_description): action = action_description.lower() if "scalpel too high" in action: return "Gabanya umuvuduko w'igikoresho." elif "cut too deep" in action: return "Gabanya depth y'igikata." elif "incorrect angle" in action: return "Hindura angle y'igikoresho." else: return "Byiza! Komeza gutya." with gr.Blocks() as demo: gr.Markdown("# Surgical Training AI Prototype") gr.Markdown( "Reba mannequin hasi, wandike uko wakoze igikorwa, AI izaguha feedback." ) with gr.Row(): # Left: 3D mannequin embed gr.HTML( """ <model-viewer src="assets/mannequin.glb" alt="3D Mannequin" auto-rotate camera-controls style="width: 400px; height: 400px;"> </model-viewer> """ ) # Right: User input + AI feedback with gr.Column(): user_input = gr.Textbox(label="Describe your surgical action") feedback = gr.Textbox(label="AI Feedback") user_input.submit(surgical_feedback, user_input, feedback) demo.launch()

    VIATEUR-AI
    Verified signature

    1367b8e
23. 08:20

    initial commit

    VIATEUR-AI
    Verified signature

    2dcdbfe