Update app.py

app.py

@@ -2,6 +2,12 @@ import gradio as gr
 from transformers import pipeline
 import json
 from datetime import datetime
+import os
+
+LOG_FILE = "/tmp/log.jsonl"
+
+if not os.path.exists(LOG_FILE):
+    with open(LOG_FILE, "w"): pass
 
 model = pipeline("token-classification", model="benchaffe/Bert-RAdam-Large", aggregation_strategy="simple")
 
@@ -21,25 +27,26 @@ def log_interaction(input_text, prediction):
         "input": input_text,
         "prediction": to_serializable(prediction)
     }
-    with open("log.jsonl", "a") as f:
+    with open(LOG_FILE, "a") as f:
         f.write(json.dumps(log_entry) + "\n")
 
-def predict(text):
+def predict_and_log(text):
     result = model(text)
     log_interaction(text, result)
-    return result
+    return result, gr.File.update(value=LOG_FILE)
 
 with gr.Blocks() as demo:
     gr.Markdown("## Biomedical Abbreviation Identifier")
-    
-    with gr.Row():
-        input_box = gr.Textbox(label="Enter biomedical text")
-        output_box = gr.JSON(label="Model Prediction")
-    
-    run_button = gr.Button("Submit")
-    run_button.click(fn=predict, inputs=input_box, outputs=output_box)
-    
-    gr.Markdown("### Download Interaction Logs")
-    gr.File(label="Download Logs", value="log.jsonl")
+
+    input_box = gr.Textbox(label="Enter biomedical text")
+    output_box = gr.JSON(label="Model Prediction")
+    download_file = gr.File(label="Download Logs", value=LOG_FILE)
+
+    submit_btn = gr.Button("Submit")
+    submit_btn.click(
+        fn=predict_and_log,
+        inputs=input_box,
+        outputs=[output_box, download_file]
+    )
 
 demo.launch()