api script and removed retriever info

app.py

@@ -80,20 +80,11 @@ with gr.Blocks(title="DeepV for RTL (Model-Agnostic)", theme=gr.themes.Soft()) a
                     elem_id="verilog-output"
                 )
                 copy_button = gr.Button("📋", variant="secondary", elem_id="copy-button")
-
-            with gr.Tab("Retrieved Items (names + scores)"):
-                retrieved_list = gr.Textbox(
-                    label="Retriever summary",
-                    lines=8,
-                    interactive=False
-                )
-            with gr.Tab("Preview of Retrieved Context (raw)"):
-                retrieved_raw = gr.HighlightedText(label="(first K documents)", combine_adjacent=True)
             
             with gr.Row():
                 clear_btn = gr.ClearButton(
                     value="Clear All",
-                    components=[spec, api_key, out_code, retrieved_list, retrieved_raw]
+                    components=[spec, api_key, out_code]
                 )
                 
     def copy_to_clipboard_fn(text):
@@ -113,7 +104,7 @@ with gr.Blocks(title="DeepV for RTL (Model-Agnostic)", theme=gr.themes.Soft()) a
     ).then(
         fn=run_generation,
         inputs=[spec, use_rag, top_k, model_choice, api_key, temperature, top_p, max_new_tokens],
-        outputs=[out_code, retrieved_list, retrieved_raw],
+        outputs=[out_code],
     ).then(
         fn=hide_loading,
         inputs=[],

deepv_api_tutorial.py

@@ -0,0 +1,61 @@
+from gradio_client import Client
+import os
+
+# This will be the URL of DeepV's Gradio App
+GRADIO_APP_URL = "paulcalzada/DeepV"  # Replace with your actual app URL
+
+try:
+    # Initialize the Gradio client
+    client = Client(GRADIO_APP_URL)
+    print("DeepV Gradio client initialized successfully!")
+
+    # input design spec to prompt LLM
+    design_spec = "Create me a 2x1 multiplexer with the following module header: module mux2x1(input wire a, input wire b, input wire sel, output wire y);"
+
+    # number of retrieved documents for RAG
+    k_value = 1
+
+    # Set if you would like to use DeepV's RAG technique
+    rag_enabled = True
+
+    # Select your model: gpt-4o, gpt-4o-mini, gpt-4.1, gpt-5-chat-latest
+    model_name = "gpt-4o"
+
+    openai_key = "" # Replace with your actual OpenAI API key
+    # Note: Your OpenAI API key is only active for this session and is not saved or stored. 
+
+    # Customize some generation parameters (temperature, top_p, max_tokens)
+    temp_value = 0.5
+    top_p_value = 0.9
+    max_tokens = 1024
+
+    # --- Call the Gradio app's API endpoint ---
+    # The `predict` method corresponds to a component's action.
+    response = client.predict(
+        design_spec,
+        rag_enabled,
+        k_value,
+        model_name,
+        openai_key,
+        temp_value,
+        top_p_value,
+        max_tokens,
+        api_name="/run_generation" # Assuming 'run_generation' is exposed as an API
+    )
+
+    # --- Process the response ---
+    # The response will be a list or tuple of outputs, in the order
+    # defined by the `outputs` parameter of your `run_btn.click` function.
+    # Your outputs are: [out_code, retrieved_list, retrieved_raw]
+    
+    generated_code = response[0]
+
+    print("\n--- API Call Successful! ---")
+    print("\nGenerated Verilog Code:")
+    print("-------------------------")
+    print(generated_code)
+
+except Exception as e:
+    print(f"An error occurred: {e}")
+    print("Please ensure your Gradio app is running and the URL is correct.")
+    print("You might also need to find the correct `fn_index` if the API call fails.")