Update app.py

app.py

@@ -20,7 +20,16 @@ for model_name, model_endpoint in API_ENDPOINTS.items():
     CHOICES.append(model_name)
     CLIENTS[model_name] = InferenceClient(model_endpoint, headers = { "Authorization": f"Bearer {API_TOKEN}" })
 
-def predict(input, access_key, model, temperature, top_p, top_k, rep_p, max_tokens, stop_seqs, seed):
+def format(input, chat_history, : str) -> str:
+    instructions = instructions.strip(" ").strip("\n")
+    prompt = instructions
+    for turn in chat_history:
+        user_message, bot_message = turn
+        prompt = f"{prompt}\n{USER_NAME}: {user_message}\n{BOT_NAME}: {bot_message}"
+    prompt = f"{prompt}\n{USER_NAME}: {message}\n{BOT_NAME}:"
+    return prompt
+    
+def predict(instruction, history, input, access_key, model, temperature, top_p, top_k, rep_p, max_tokens, stop_seqs, seed):
 
     if (access_key != KEY):
         print(">>> MODEL FAILED: Input: " + input + ", Attempted Key: " + access_key)
@@ -53,11 +62,13 @@ def maintain_cloud():
     
 with gr.Blocks() as demo:
     with gr.Row(variant = "panel"):
-        gr.Markdown("⚛️ This is a private LLM Space owned within STC Holdings!\n\n\nhttps://discord.gg/6JRtGawz7B")
+        gr.Markdown("🔯 This is a private LLM CHAT Space owned within STC Holdings!\n\n\nhttps://discord.gg/6JRtGawz7B")
             
     with gr.Row():
         with gr.Column():
-            input = gr.Textbox(label = "Input", lines = 4)
+            history = gr.Chatbot(elem_id = "chatbot")
+            input = gr.Textbox(label = "Input", lines = 2)
+            instruction = gr.Textbox(label = "Instruction", lines = 4)
             access_key = gr.Textbox(label = "Access Key", lines = 1)
             run = gr.Button("▶")
             cloud = gr.Button("☁️")
@@ -76,7 +87,7 @@ with gr.Blocks() as demo:
         with gr.Column():
             output = gr.Textbox(label = "Output", value = "", lines = 50)
 
-    run.click(predict, inputs = [input, access_key, model, temperature, top_p, top_k, rep_p, max_tokens, stop_seqs, seed], outputs = [output, input])
+    run.click(predict, inputs = [instruction, history, input, access_key, model, temperature, top_p, top_k, rep_p, max_tokens, stop_seqs, seed], outputs = [output, input])
     cloud.click(maintain_cloud, inputs = [], outputs = [input, output])
     
 demo.queue(concurrency_count = 500, api_open = True).launch(show_api = True)