Update app.py

app.py

@@ -35,47 +35,47 @@ def parse_codeblock(text):
 def predict(inputs, top_p, temperature, chat_counter, chatbot=[], history=[]):  
 
     payload = {
-    "model": MODEL,
-    "messages": [{"role": "user", "content": f"{inputs}"}],
-    "temperature" : 1.0,
-    "top_p":1.0,
-    "n" : 1,
-    "stream": True,
-    "presence_penalty":0,
-    "frequency_penalty":0,
+        "model": MODEL,
+        "messages": [{"role": "user", "content": f"{inputs}"}],
+        "temperature" : 1.0,
+        "top_p":1.0,
+        "n" : 1,
+        "stream": True,
+        "presence_penalty":0,
+        "frequency_penalty":0,
     }
 
     headers = {
-    "Content-Type": "application/json",
-    "Authorization": f"Bearer {OPENAI_API_KEY}"
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {OPENAI_API_KEY}"
     }
 
     # print(f"chat_counter - {chat_counter}")
     if chat_counter != 0 :
         messages = []
         for i, data in enumerate(history):
-          if i % 2 == 0:
-              role = 'user'
-          else:
-              role = 'assistant'
-          temp = {}
-          temp["role"] = role
-          temp["content"] = data
-          messages.append(temp)
+            if i % 2 == 0:
+                role = 'user'
+            else:
+                role = 'assistant'
+            temp = {}
+            temp["role"] = role
+            temp["content"] = data
+            messages.append(temp)
         
         temp3 = {}
         temp3["role"] = "user" 
         temp3["content"] = inputs
         messages.append(temp3)
         payload = {
-        "model": MODEL,
-        "messages": messages,
-        "temperature" : temperature, #1.0,
-        "top_p": top_p, #1.0,
-        "n" : 1,
-        "stream": True,
-        "presence_penalty":0,
-        "frequency_penalty":0,
+            "model": MODEL,
+            "messages": messages,
+            "temperature" : temperature,
+            "top_p": top_p,
+            "n" : 1,
+            "stream": True,
+            "presence_penalty":0,
+            "frequency_penalty":0,
         }
 
     chat_counter+=1
@@ -85,39 +85,37 @@ def predict(inputs, top_p, temperature, chat_counter, chatbot=[], history=[]):
     response = requests.post(API_URL, headers=headers, json=payload, stream=True)
     response_code = f"{response}"
     if response_code.strip() != "<Response [200]>":
-        #print(f"response code - {response}")
         raise Exception(f"Sorry, hitting rate limit. Please try again later. {response}")
     token_counter = 0 
     partial_words = "" 
-    counter=0
+    counter = 0
     for chunk in response.iter_lines():
         #Skipping first chunk
         if counter == 0:
           counter+=1
           continue
-        #counter+=1
         # check whether each line is non-empty
         if chunk.decode() :
-          chunk = chunk.decode()
-          # decode each line as response data is in bytes
-          if len(chunk) > 12 and "content" in json.loads(chunk[6:])['choices'][0]['delta']:
-              #if len(json.loads(chunk.decode()[6:])['choices'][0]["delta"]) == 0:
-              #  break
-              partial_words = partial_words + json.loads(chunk[6:])['choices'][0]["delta"]["content"]
-              if token_counter == 0:
-                history.append(" " + partial_words)
-              else:
-                history[-1] = partial_words
-              chat = [(parse_codeblock(history[i]), parse_codeblock(history[i + 1])) for i in range(0, len(history) - 1, 2) ]  # convert to tuples of list
-              token_counter+=1
-              yield chat, history, chat_counter, response  # resembles {chatbot: chat, state: history}  
+            chunk = chunk.decode()
+            # decode each line as response data is in bytes
+            if len(chunk) > 12 and "content" in json.loads(chunk[6:])['choices'][0]['delta']:
+                #if len(json.loads(chunk.decode()[6:])['choices'][0]["delta"]) == 0:
+                #  break
+                partial_words = partial_words + json.loads(chunk[6:])['choices'][0]["delta"]["content"]
+                if token_counter == 0:
+                  history.append(" " + partial_words)
+                else:
+                  history[-1] = partial_words
+                chat = [(parse_codeblock(history[i]), parse_codeblock(history[i + 1])) for i in range(0, len(history) - 1, 2) ]  # convert to tuples of list
+                token_counter+=1
+                yield chat, history, chat_counter, response  # resembles {chatbot: chat, state: history}  
     print(json.dumps({"chat_counter": chat_counter, "payload": payload, "partial_words": partial_words, "token_counter": token_counter, "counter": counter}))
                    
 
 def reset_textbox():
     return gr.update(value='')
 
-title = """<h1 align="center">GPT3.5 Chatbot</h1>"""
+title = """<h1 align="center">GPT-3.5 Chatbot</h1>"""
 if DISABLED:
     title = """<h1 align="center" style="color:red">This app has reached OpenAI's usage limit. We are currently requesting an increase in our quota. Please check back in a few days.</h1>"""
 description = """Language models can be conditioned to act like dialogue agents through a conversational prompt that typically takes the form:
@@ -137,7 +135,7 @@ with gr.Blocks(css = """#col_container { margin-left: auto; margin-right: auto;}
                 #chatbot {height: 520px; overflow: auto;}""",
               theme=theme) as demo:
     gr.HTML(title)
-    gr.HTML("""<h3 align="center">This App provides you full access to GPT3.5 API (4096 token limit). You don't need any OPENAI API key</h1>""")
+    gr.HTML("""<h3 align="center">This App provides you full access to GPT-3.5 (4096 token limit). You don't need any OPENAI API key.</h1>""")
     gr.HTML('''<center><a href="https://huggingface.co/spaces/yuntian-deng/ChatGPT?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>Duplicate the Space and run securely with your OpenAI API Key</center>''')
     with gr.Column(elem_id = "col_container", visible=False) as main_block:
         #API Key is provided by OpenAI