Update app.py

app.py

@@ -125,6 +125,42 @@ def format_prompt(message, history):
   prompt += f"[INST] {message} [/INST]"
   return prompt
 
+def run_gpt_no_prefix(
+    prompt_template,
+    stop_tokens,
+    max_tokens,
+    seed,
+    **prompt_kwargs,
+):
+    print(seed)
+    timestamp=datetime.datetime.now()
+    
+    generate_kwargs = dict(
+        temperature=0.9,
+        max_new_tokens=max_tokens,
+        top_p=0.95,
+        repetition_penalty=1.0,
+        do_sample=True,
+        seed=seed,
+    )
+    
+    content = prompt_template.format(**prompt_kwargs)
+    #if VERBOSE:
+    print(LOG_PROMPT.format(content))
+    
+    
+    #formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
+    #formatted_prompt = format_prompt(f'{content}', history)
+
+    stream = client.text_generation(content, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    resp = ""
+    for response in stream:
+        resp += response.token.text
+        #yield resp
+
+    if VERBOSE:
+        print(LOG_RESPONSE.format(resp))
+    return resp
 
 
 def run_gpt(
@@ -266,7 +302,7 @@ def compress_data_og(c, instruct, history):
 def get_chart(inp):
     seed=random.randint(1,1000000000)
     try:
-        resp = run_gpt(
+        resp = run_gpt_no_prefix(
             GET_CHART,
             stop_tokens=["observation:", "task:", "action:", "thought:"],
             max_tokens=8192,