Create app.py

app.py

@@ -0,0 +1,91 @@
+from transformers import RobertaTokenizer, EncoderDecoderModel
+import pandas as pd
+import gradio as gr
+
+
+model = EncoderDecoderModel.from_pretrained("imamnurby/rob2rand_chen_w_prefix_c_fc")
+tokenizer = RobertaTokenizer.from_pretrained("imamnurby/rob2rand_chen_w_prefix_c_fc")
+
+def generate_preds(gen_mode, desc):
+    desc = desc.lower()
+    if gen_mode=="Channel":
+        desc = "GENERATE TRIGGER AND ACTION CHANNEL ONLY <pf> " + desc
+    elif gen_mode=="Function":
+        desc = "GENERATE BOTH CHANNEL AND FUNCTION FOR TRIGGER AND ACTION <pf> " + desc
+    
+    
+    
+    input_ids = tokenizer.encode(desc, return_tensors='pt')
+    
+    # activate beam search and early_stopping
+    preds = model.generate(
+        input_ids, 
+        max_length=100, 
+        num_beams=10,
+        num_return_sequences=10,
+        early_stopping=True
+    )
+    
+    output_list = []
+    for item in preds:
+        output_list.append(tokenizer.decode(item, skip_special_tokens=True))
+    
+    if gen_mode=="Channel":
+        trigger = [x.split("<sep>")[0].strip() for x in output_list]
+        # trigger_desc = ["dummy" for x in output_list]
+        action = [x.split("<sep>")[1].strip() for x in output_list]
+        # action_desc = ["dummy" for x in output_list]
+        df = {"Trigger": trigger,
+              # "Trigger Description": trigger_desc,
+              "Action": action,
+              # "Action Description": action_desc
+             }
+    elif gen_mode=="Function":
+        trigger = [x.split("<sep>")[1].strip() for x in output_list]
+        trigger_desc = ["dummy" for x in output_list]
+        action = [x.split("<sep>")[3].strip() for x in output_list]
+        action_desc = ["dummy" for x in output_list]
+        df = {"Trigger": trigger,
+              # "Trigger Description": trigger_desc,
+              "Action": action,
+              # "Action Description": action_desc
+             }
+    return pd.DataFrame(df)
+
+demo = gr.Blocks()
+with demo:
+    gr.Markdown("<h1><center>RecipeGen: Automated TAPs Generation Tool</center></h1>")
+    gr.Markdown("<center>This demo allows you to generate TAPs (Trigger Action Programs) using functionality description described in English. You can learn the working detail of our tool from our paper<center>")
+    gr.Markdown("<h3>Instructions<h3>")
+    gr.Markdown("""
+    1. Select the generation granularity (i.e., Channel, Function, or Field)
+    2. Describe your intended functionality 
+    3. Specify the beam width
+    4. Specify the number of returned sequences
+    5. Click **Generate**; the generated TAPs along with the description of each component will show in the **Results**
+    """)
+    gr.Markdown("NOTE: **#Returned Sequences** should be LESS THAN OR EQUAL **Beam Width**")
+    with gr.Tabs():
+        with gr.TabItem("Channel/Function"):    
+            with gr.Column():
+                gen_mode = gr.Radio(label="Granularity", choices=["Channel", "Function"])
+                desc = gr.Textbox(label="Functionality Description", placeholder="Describe the functionality here")
+                num_beams = gr.Slider(minimum=2, maximum=500, value=2, step=1, label="Beam Width")
+                num_returned_seqs = gr.Slider(minimum=2, maximum=500, value=2, step=1, label="#Returned Sequences")
+                with gr.Row():
+                    generate = gr.Button("Generate")
+                gr.Markdown("<h1><center>Results</center></h1>")
+                results = gr.Dataframe(headers=["Trigger", "Trigger Description", "Action", "Action Description"], row_count=100)
+        
+        with gr.TabItem("Field"):    
+            with gr.Column():
+                desc = gr.Textbox(label="Functionality Description", placeholder="Describe the functionality here")
+                num_beams = gr.Slider(minimum=2, maximum=500, value=2, step=1, label="Beam Width")
+                num_returned_seqs = gr.Slider(minimum=2, maximum=500, value=2, step=1, label="#Returned Sequences")
+                with gr.Row():
+                    generate_field = gr.Button("Generate")
+                gr.Markdown("<h1><center>Results</center></h1>")
+                results_field = gr.Dataframe(headers=["Trigger", "Trigger Description", "Trigger Fields", "Action", "Action Description", "Action Fields"])
+    
+    generate.click(generate_preds, inputs=[gen_mode, desc], outputs=[results])
+demo.launch()