Update app.py

app.py

@@ -71,29 +71,30 @@ def chat_inf(system_prompt,prompt,history,client_choice,seed,temp,tokens,top_p,r
     print("\n######### HIST "+str(in_len))
     print("\n######### TOKENS "+str(tokens))
     if (in_len+tokens) > 8000:
-        yield [(prompt,"Wait. I need to compress our Chat history...")]
-        hist=compress_history(history,client_choice,seed,temp,tokens,top_p,rep_p,chat_mem)
-        yield [(prompt,"History has been compressed, processing request...")]
-        history = [(prompt,hist)]
-    generate_kwargs = dict(
-        temperature=temp,
-        max_new_tokens=tokens,
-        top_p=top_p,
-        repetition_penalty=rep_p,
-        do_sample=True,
-        seed=seed,
-    )
-    #formatted_prompt=prompt   
-    formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history[0-chat_mem:])
-    print("\n######### PROMPT "+str(len(formatted_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 [(prompt,output)]
-    history.append((prompt,output))
-    memory=history
-    yield history
+        yield [(prompt,"Wait, that's too many tokens, please reduce the Chat Memory value")]
+        #hist=compress_history(history,client_choice,seed,temp,tokens,top_p,rep_p,chat_mem)
+        #yield [(prompt,"History has been compressed, processing request...")]
+        #history.append((prompt,hist))
+    else:
+        generate_kwargs = dict(
+            temperature=temp,
+            max_new_tokens=tokens,
+            top_p=top_p,
+            repetition_penalty=rep_p,
+            do_sample=True,
+            seed=seed,
+        )
+        #formatted_prompt=prompt   
+        formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history[0-chat_mem:])
+        print("\n######### PROMPT "+str(len(formatted_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 [(prompt,output)]
+        history.append((prompt,output))
+        memory=history
+        yield history
 
 def get_screenshot(chat: list,height=5000,width=600,chatblock=[],theme="light",wait=3000,header=True):
     print(chatblock)