Update app.py

app.py

@@ -1,7 +1,10 @@
 import streamlit as st
 import gradio as gr
 from gradio_client import Client
-from PIL import Image 
+import re
+import torch
+from transformers import pipeline
+
 
 fuyu_client = Client("https://adept-fuyu-8b-demo.hf.space/")
 def get_caption(image_in):
@@ -23,15 +26,44 @@ def get_caption(image_in):
     
     return truncated_caption
 
-image_1 = st.file_uploader("Drag and drop an image here, or click to select one", type=["png", "jpg", "jpeg"])
+#image_1 = st.file_uploader("Drag and drop an image here, or click to select one", type=["png", "jpg", "jpeg"])
 
 # Display the uploaded image
-if image_1 is not None:
+#if image_1 is not None:
     # Read the image
-     image = Image.open(image_1)
-
+    # image = Image.open(image_1)
+    
     # Display the image
-    st.image(image, caption="Uploaded Image", use_column_width=True)
-    get_caption(image)
+    #st.image(image, caption="Uploaded Image", use_column_width=True)
+    #get_caption(image)
 
+def infer(image_in):
+    gr.Info("Getting image caption with Fuyu...")
+    user_prompt = get_caption(image_in)
+    write(user_prompt)
+    return user_prompt
 
+with gr.Blocks(css=css) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.HTML(f"""
+        <h2 style="text-align: center;">LLM Agent from a Picture</h2>
+        <p style="text-align: center;">{description}</p>
+        """)
+        
+        with gr.Row():
+            with gr.Column():
+                image_in = gr.Image(
+                    label = "Image reference",
+                    type = "filepath",
+                    elem_id = "image-in"
+                )
+                submit_btn = gr.Button("Make LLM system from my pic !")
+    submit_btn.click(
+        fn = infer,
+        inputs = [
+            image_in
+        ],
+        outputs =[
+            result
+        ]
+    )