Update app.py

app.py

@@ -3,10 +3,10 @@ import os
 import gradio as gr
 import threading
 import time
-from gradio_client import Client
+from groq import Groq
 
-# Initialize Gradio client
-client = Client("Nymbo/Llama-3.1-405B-Instruct")
+# Initialize Groq client
+client = Groq()
 
 # Constants
 MAX_SIZE = 1.1 * 1024 * 1024 * 1024  # 1.1GB in bytes
@@ -37,28 +37,52 @@ def generate_and_save_data():
     while True:
         try:
             # Generate a prompt
-            prompt_result = client.predict(
-                message="give me a single prompt to prompt an ai model, simulating what users could want from you. ensure that it is diverse and high quality. for each, choose a random writing style (though it has to be a common one), random length and random clarity of the prompt. ensure that it is a single prompt, and just the prompt itself, nothing else. eg, don't close the prompt in quotation marks or say Here is a single prompt that meets your requirements or anything similar to that",
-                system_message="",
-                max_tokens=1024,
+            completion = client.chat.completions.create(
+                model="gemma2-9b-it",
+                messages=[
+                    {
+                        "role": "user",
+                        "content": "give me a single prompt to prompt an ai model, simulating what users could want from you. ensure that it is diverse and high quality. for each, choose a random writing style (though it has to be a common one), random length and random clarity of the prompt. ensure that it is a single prompt, and just the prompt itself, nothing else. eg, don't close the prompt in quotation marks or say Here is a single prompt that meets your requirements or anything similar to that"
+                    }
+                ],
                 temperature=1,
+                max_tokens=1024,
                 top_p=1,
-                api_name="/chat"
+                stream=True,
+                stop=None,
             )
-            prompt = prompt_result['message']
-            prompt_tokens = len(prompt.split())
+
+            prompt = ""
+            prompt_tokens = 0
+            for chunk in completion:
+                content = chunk.choices[0].delta.content
+                if content:
+                    prompt += content
+                    prompt_tokens += len(content.split())
 
             # Use the generated prompt to query the model again
-            response_result = client.predict(
-                message=prompt,
-                system_message="",
-                max_tokens=5000,
+            second_completion = client.chat.completions.create(
+                model="gemma2-9b-it",
+                messages=[
+                    {
+                        "role": "user",
+                        "content": prompt
+                    }
+                ],
                 temperature=1,
+                max_tokens=5000,
                 top_p=1,
-                api_name="/chat"
+                stream=True,
+                stop=None,
             )
-            response = response_result['message']
-            response_tokens = len(response.split())
+
+            response = ""
+            response_tokens = 0
+            for chunk in second_completion:
+                content = chunk.choices[0].delta.content
+                if content:
+                    response += content
+                    response_tokens += len(content.split())
 
             # Update the combined token count
             combined_tokens += (prompt_tokens + response_tokens)
@@ -76,10 +100,12 @@ def generate_and_save_data():
                 current_file = os.path.join(DATA_DIRECTORY, f'data{file_index}.csv')
                 file_paths.append(current_file)
                 # Create the new file with headers
-                data.to_csv(current_file, index=False)
+                with open(current_file, 'w') as f:
+                    data.to_csv(f, header=True, index=False)
             else:
                 # Append data to the current file
-                data.to_csv(current_file, mode='a', header=False, index=False)
+                with open(current_file, 'a') as f:
+                    data.to_csv(f, header=False, index=False)
 
             # Wait for the next update interval
             time.sleep(UPDATE_INTERVAL)
@@ -137,4 +163,4 @@ with gr.Blocks() as app:
     token_refresh = gr.Button("Refresh Token Count")
     token_refresh.click(update_token_display, outputs=token_display)
 
-app.launch(show_error=True)
+app.launch()