Update app.py

app.py

@@ -78,10 +78,9 @@ def prompt(inputs):
         - Any visible brand logos or distinguishing marks (e.g., Tesla logo)
         - Details of any visible damage (e.g., scratches, dents)
         - Vehicle’s region or country (based on the license plate or other clues)
-        If some details are unclear or not visible, return `None` for those fields. Do not guess or provide inaccurate information."""
-        ),
+        If some details are unclear or not visible, return `None` for those fields. Do not guess or provide inaccurate information."""),
         HumanMessage(
-            content=[
+            content=[ 
                 {"type": "text", "text": "Analyze the vehicle in the image and extract as many details as possible, including type, license plate, make, model, year, condition, damage, etc."},
                 {"type": "text", "text": instructions},  # include any other format instructions here
                 {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{inputs['image']}", "detail": "low"}}
@@ -101,48 +100,54 @@ def MLLM_response(inputs):
 pipeline = image_encoding | prompt | MLLM_response | parser
 
 # Streamlit Interface for uploading images and showing results
-st.header("Upload a Vehicle Image for Information Extraction")
-
-uploaded_image = st.file_uploader("Choose a JPEG image", type="jpeg")
-
-if uploaded_image is not None:
-    # Display the uploaded image
-    image = PILImage.open(uploaded_image)
-    st.image(image, caption="Uploaded Image", use_column_width=True)
-
-    # Convert the uploaded image to base64
-    image_path = "/tmp/uploaded_image.jpeg"
-    with open(image_path, "wb") as f:
-        f.write(uploaded_image.getbuffer())
-
-    # Process the image through the pipeline
-    output = pipeline.invoke({"image_path": image_path})
-
-    # Show the results in a user-friendly format
-    st.subheader("Extracted Vehicle Information")
-    st.json(output)
-
-    # Optionally, display more vehicle images from the folder
-    img_dir = "/content/images"
-    image_paths = glob.glob(os.path.join(img_dir, "*.jpeg"))
-    display_image_grid(image_paths)
-
-# You can also allow users to upload and process a batch of images
-st.sidebar.header("Batch Image Upload")
-
-batch_images = st.sidebar.file_uploader("Upload Images", type="jpeg", accept_multiple_files=True)
-
-if batch_images:
-    batch_input = [{"image_path": f"/tmp/{file.name}"} for file in batch_images]
-    for file in batch_images:
-        with open(f"/tmp/{file.name}", "wb") as f:
-            f.write(file.getbuffer())
-    
-    # Process the batch and display the results in a DataFrame
-    batch_output = pipeline.batch(batch_input)
-    df = pd.DataFrame(batch_output)
-    st.dataframe(df)
-
-    # Show images in a grid
-    image_paths = [f"/tmp/{file.name}" for file in batch_images]
-    display_image_grid(image_paths)
+st.header("Upload Vehicle Images for Information Extraction")
+
+# Option to select either single or batch image upload
+upload_option = st.radio("Select Upload Type", ["Single Image Upload", "Batch Images Upload"])
+
+# Single Image Upload
+if upload_option == "Single Image Upload":
+    st.subheader("Upload a Single Vehicle Image")
+    uploaded_image = st.file_uploader("Choose a JPEG image", type="jpeg")
+
+    if uploaded_image is not None:
+        # Display the uploaded image
+        image = PILImage.open(uploaded_image)
+        st.image(image, caption="Uploaded Image", use_column_width=True)
+
+        # Convert the uploaded image to base64
+        image_path = "/tmp/uploaded_image.jpeg"
+        with open(image_path, "wb") as f:
+            f.write(uploaded_image.getbuffer())
+
+        # Process the image through the pipeline
+        output = pipeline.invoke({"image_path": image_path})
+
+        # Show the results in a user-friendly format
+        st.subheader("Extracted Vehicle Information")
+        st.json(output)
+
+        # Optionally, display more vehicle images from the folder
+        img_dir = "/content/images"
+        image_paths = glob.glob(os.path.join(img_dir, "*.jpeg"))
+        display_image_grid(image_paths)
+
+# Batch Images Upload
+elif upload_option == "Batch Images Upload":
+    st.sidebar.header("Batch Image Upload")
+    batch_images = st.sidebar.file_uploader("Upload Images", type="jpeg", accept_multiple_files=True)
+
+    if batch_images:
+        batch_input = [{"image_path": f"/tmp/{file.name}"} for file in batch_images]
+        for file in batch_images:
+            with open(f"/tmp/{file.name}", "wb") as f:
+                f.write(file.getbuffer())
+
+        # Process the batch and display the results in a DataFrame
+        batch_output = pipeline.batch(batch_input)
+        df = pd.DataFrame(batch_output)
+        st.dataframe(df)
+
+        # Show images in a grid
+        image_paths = [f"/tmp/{file.name}" for file in batch_images]
+        display_image_grid(image_paths)