Update app.py

app.py

@@ -3,8 +3,8 @@ import gradio as gr
 
 client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1")
 
-# Define the initial prompt
-initial_prompt = """
+# Your static prompt
+static_prompt = """
 Simulate a GenAI-based interview scenario for the position of Solution Architect with a candidate named "John Doe." Follow these steps:
 
 1. Start with a friendly greeting and welcome message. Ask John to introduce himself briefly.
@@ -31,11 +31,9 @@ Remember to maintain a natural and polite conversational tone throughout the int
 """
 
 def format_prompt(message, history):
-    # Start with the initial prompt for the first interaction
-    if not history:
-        return initial_prompt
-
     prompt = "<s>"
+    # Add the static prompt as the first message
+    prompt += f"[INST] {static_prompt} [/INST]"
     for user_prompt, bot_response in history:
         prompt += f"[INST] {user_prompt} [/INST]"
         prompt += f" {bot_response}</s> "
@@ -43,7 +41,7 @@ def format_prompt(message, history):
     return prompt
 
 def generate(
-    message, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
+    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
 ):
     temperature = float(temperature)
     if temperature < 1e-2:
@@ -59,15 +57,9 @@ def generate(
         seed=42,
     )
 
-    formatted_prompt = format_prompt(message, history)
+    formatted_prompt = format_prompt(prompt, history)
 
-    stream = client.text_generation(
-        formatted_prompt,
-        **generate_kwargs,
-        stream=True,
-        details=True,
-        return_full_text=False,
-    )
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
 
     for response in stream:
@@ -75,7 +67,7 @@ def generate(
         yield output
     return output
 
-additional_inputs = [
+additional_inputs=[
     gr.Slider(
         label="Temperature",
         value=0.9,
@@ -111,19 +103,12 @@ additional_inputs = [
         step=0.05,
         interactive=True,
         info="Penalize repeated tokens",
-    ),
+    )
 ]
 
 gr.ChatInterface(
     fn=generate,
-    inputs=[gr.Textbox(label="Interviewer", type="text", default=initial_prompt)],
-    outputs=gr.Chatbot(
-        show_label=False,
-        show_share_button=False,
-        show_copy_button=True,
-        likeable=True,
-        layout="panel",
-    ),
+    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
     additional_inputs=additional_inputs,
-    title="""Mistral 7B""",
+    title="""Mistral 7B"""
 ).launch(show_api=False)