Update app.py

app.py

@@ -1,43 +1,47 @@
+import os
+from groq import Groq 
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
-
-# Load the model and tokenizer
-model_name = "models/codellama/CodeLlama-34b-Instruct-hf"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
-
-# Create a pipeline for chatbot interaction
-pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
-
-# Function to handle chatbot interaction
-def chatbot_interaction(user_input, history=[]):
-    # Append user message to the conversation history
-    history.append(("user", user_input))
-
-    # Format the conversation history for the model
-    conversation = "\n".join([f"{role}: {message}" for role, message in history])
-
-    # Generate response from the model
-    response = pipe(conversation, max_length=1024, do_sample=True)[0]['generated_text']
-
-    # Extract the assistant's response and append it to the history
-    assistant_message = response[len(conversation):].strip()
-    history.append(("assistant", assistant_message))
-
-    return history, history
-
-# Gradio interface
-with gr.Blocks() as demo:
-    chatbot = gr.Chatbot()
-    msg = gr.Textbox(label="Your message:")
-    clear = gr.Button("Clear")
-
-    def respond(message, chat_history):
-        chat_history, updated_history = chatbot_interaction(message, chat_history)
-        return updated_history, ""
-
-    msg.submit(respond, [msg, chatbot], [chatbot, msg])
-    clear.click(lambda: None, None, chatbot)  # Clear the chat
-
-# Launch the Gradio app
+    
+client = Groq(api_key = os.environ.get("GROQ_API_KEY"), )
+
+system_prompt = {
+                "role": "system",
+                "content":
+                "You are a useful assistant. You reply with efficient answers. "
+                }
+
+async def chat_groq(message, history):
+    
+    messages = [system_prompt]
+    
+    for msg in history:
+        messages.append({"role": "user", "content": str(msg[0])})
+        messages.append({"role": "assistant", "content": str(msg[1])})
+        
+    messages.append({"role": "user", "content": str (message)})
+    
+    response_content = ''
+    
+    stream = client.chat.completions.create(
+                                            model="codellama-CodeLlama-34b-Instruct-hf",
+                                            messages=messages,
+                                            max_tokens=1024,
+                                            temperature=1.3,
+                                            stream=True
+                                        )
+
+    for chunk in stream:
+        content = chunk.choices[0].delta.content
+        if content:
+            response_content += chunk. choices[0].delta.content 
+        yield response_content
+
+with gr. Blocks(theme=gr.themes.Monochrome(), fill_height=True) as demo:
+    gr.ChatInterface(chat_groq,
+                     clear_btn=None, 
+                     undo_btn=None, 
+                     retry_btn=None,
+                    )
+
+demo.queue()
 demo.launch()