Refactor demo interface in main.py and update .gitignore to exclude cached examples

.gitignore

@@ -1,3 +1,4 @@
 .venv
 __pycache__
 .pytest_cache
+gradio_cached_examples

main.py

@@ -26,53 +26,6 @@ else:
 gr.set_static_paths(["assets"])
 
 
-def run():
-    global model
-    model = init_model()
-
-    demo = gr.Interface(
-        fn=predict,
-        inputs=[
-            gr.Image(type="pil", label="Input Image"),
-            gr.Textbox(
-                label="Prompts",
-                placeholder="Enter prompts separated by commas (e.g., neoplastic cells, inflammatory cells)",
-            ),
-        ],
-        outputs=gr.Image(type="pil", label="Prediction"),
-        title="BiomedParse Demo",
-        description=description,
-        allow_flagging="never",
-        examples=[
-            ["examples/144DME_as_F.jpeg", "edema"],
-            ["examples/C3_EndoCV2021_00462.jpg", "polyp"],
-            ["examples/CT-abdomen.png", "liver, pancreas, spleen"],
-            ["examples/covid_1585.png", "left lung"],
-            ["examples/covid_1585.png", "right lung"],
-            ["examples/covid_1585.png", "COVID-19 infection"],
-            ["examples/ISIC_0015551.jpg", "lesion"],
-            ["examples/LIDC-IDRI-0140_143_280_CT_lung.png", "lung nodule"],
-            ["examples/LIDC-IDRI-0140_143_280_CT_lung.png", "COVID-19 infection"],
-            [
-                "examples/Part_1_516_pathology_breast.png",
-                "connective tissue cells",
-            ],
-            [
-                "examples/Part_1_516_pathology_breast.png",
-                "neoplastic cells",
-            ],
-            [
-                "examples/Part_1_516_pathology_breast.png",
-                "neoplastic cells, inflammatory cells",
-            ],
-            ["examples/T0011.jpg", "optic disc"],
-            ["examples/T0011.jpg", "optic cup"],
-            ["examples/TCGA_HT_7856_19950831_8_MRI-FLAIR_brain.png", "glioma"],
-        ],
-    )
-    return demo
-
-
 description = """Upload a biomedical image and enter prompts (separated by commas) to detect specific features.
 
 The model understands these prompts:
@@ -96,6 +49,64 @@ This Space is based on the [BiomedParse model](https://microsoft.github.io/Biome
 """
 
 
+examples = [
+    ["examples/144DME_as_F.jpeg", "edema"],
+    ["examples/C3_EndoCV2021_00462.jpg", "polyp"],
+    ["examples/CT-abdomen.png", "liver, pancreas, spleen"],
+    ["examples/covid_1585.png", "left lung"],
+    ["examples/covid_1585.png", "right lung"],
+    ["examples/covid_1585.png", "COVID-19 infection"],
+    ["examples/ISIC_0015551.jpg", "lesion"],
+    ["examples/LIDC-IDRI-0140_143_280_CT_lung.png", "lung nodule"],
+    ["examples/LIDC-IDRI-0140_143_280_CT_lung.png", "COVID-19 infection"],
+    ["examples/Part_1_516_pathology_breast.png", "connective tissue cells"],
+    ["examples/Part_1_516_pathology_breast.png", "neoplastic cells"],
+    [
+        "examples/Part_1_516_pathology_breast.png",
+        "neoplastic cells, inflammatory cells",
+    ],
+    ["examples/T0011.jpg", "optic disc"],
+    ["examples/T0011.jpg", "optic cup"],
+    ["examples/TCGA_HT_7856_19950831_8_MRI-FLAIR_brain.png", "glioma"],
+]
+
+
+def run():
+    global model
+    model = init_model()
+
+    with gr.Blocks() as demo:
+        gr.Markdown("# BiomedParse Demo")
+        gr.Markdown(description)
+
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(type="pil", label="Input Image")
+                input_text = gr.Textbox(
+                    label="Prompts",
+                    placeholder="Enter prompts separated by commas (e.g., neoplastic cells, inflammatory cells)",
+                )
+            with gr.Column():
+                output_image = gr.Image(type="pil", label="Prediction")
+
+        predict_btn = gr.Button("Submit")
+        predict_btn.click(
+            fn=predict,
+            inputs=[input_image, input_text],
+            outputs=output_image,
+        )
+
+        gr.Examples(
+            examples=examples,
+            inputs=[input_image, input_text],
+            outputs=output_image,
+            fn=predict,
+            cache_examples=False,
+        )
+
+    return demo
+
+
 demo = run()
 
 if __name__ == "__main__":