Update app.py

app.py

@@ -15,7 +15,7 @@ def format_prompt(message, history):
   return prompt
 
 def generate(
-    prompt, 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:
@@ -41,6 +41,30 @@ def generate(
         yield output
     return output
 
+def foo(prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
+    temperature = float(temperature)
+    if temperature < 1e-2:
+        temperature = 1e-2
+    top_p = float(top_p)
+
+    generate_kwargs = dict(
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        do_sample=True,
+        seed=42,
+    )
+
+    formatted_prompt = format_prompt(prompt, [])
+
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    output = ""
+
+    for response in stream:
+        output += response.token.text
+        yield output
+    return output
 
 additional_inputs=[
     gr.Slider(
@@ -98,5 +122,10 @@ with gr.Blocks(css=css) as demo:
         additional_inputs=additional_inputs,
         examples=[["What is the secret to life?"], ["Write me a recipe for pancakes."]]
     )
+    gr.Interface(fn=greet, 
+                 additional_inputs=additional_inputs,
+                 inputs="textbox", 
+                 outputs="textbox")
+
 
 demo.queue(concurrency_count=75, max_size=100).launch(debug=True)