Update app.py

app.py

@@ -9,20 +9,20 @@ client = InferenceClient(model)
 def fn_text(
     prompt,
     history,
-    system_prompt,
+    #system_prompt,
     max_tokens,
     temperature,
     top_p,
 ):
-    #messages = [{"role": "user", "content": prompt}]
+    #messages = [{"role": "system", "content": system_prompt}]
     #history.append(messages[0])
+    
+    #messages.append({"role": "user", "content": prompt})
+    #history.append(messages[1])
 
-    messages = [{"role": "system", "content": system_prompt}]
+    messages = [{"role": "user", "content": prompt}]
     history.append(messages[0])
     
-    messages.append({"role": "user", "content": prompt})
-    history.append(messages[1])
-    
     stream = client.chat.completions.create(
         model = model,
         messages = history,
@@ -41,7 +41,7 @@ app_text = gr.ChatInterface(
     fn = fn_text,
     type = "messages",
     additional_inputs = [
-        gr.Textbox(value="You are a helpful assistant.", label="System Prompt"),
+        #gr.Textbox(value="You are a helpful assistant.", label="System Prompt"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max Tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-P"),
@@ -117,30 +117,4 @@ app = gr.ChatInterface(
 )
 
 if __name__ == "__main__":
-    app.launch()
-
-# Pipeline
-
-import gradio as gr
-from transformers import pipeline
-
-pipe = pipeline(model = "google/gemma-2-2b-it")
-
-def fn(input):
-    output = pipe(
-        input,
-        max_new_tokens = 2048
-    )
-    return output[0]["generated_text"]#[len(input):]
-
-app = gr.Interface(
-    fn = fn,
-    inputs = [gr.Textbox(label = "Input")],
-    outputs = [gr.Textbox(label = "Output")],
-    title = "Google Gemma",
-    description = "Pipeline",
-    examples = [
-        ["Hello, World."]
-    ]
-).launch()
-"""
+    app.launch()