Update app.py

app.py

@@ -1,8 +1,10 @@
-import openai
 import os
 import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-openai.api_key = os.environ.get("OPENAI_API_KEY")
+model_name = "huggingface_model_name"  # 将此处替换为你想使用的模型的名称
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
 class Conversation:
     def __init__(self, prompt, round):
@@ -14,39 +16,22 @@ class Conversation:
     def ask(self, question):
         try:
             self.messages.append({"role": "user", "content": question})
-            response = openai.ChatCompletion.create(
-                model="gpt-3.5-turbo",
-                messages=self.messages,
-                temperature=0.5,
-                max_tokens=2048,
-                top_p=1,
-            )
+            input_text = self._build_message(self.messages)
+            encoded_input = tokenizer.encode(input_text + tokenizer.eos_token, return_tensors='pt')
+            output = model.generate(encoded_input, max_length=200, temperature=0.5)
+            message = tokenizer.decode(output[:, encoded_input.shape[-1]:][0], skip_special_tokens=True)
         except Exception as e:
             print(e)
             return e
 
-        message = response["choices"][0]["message"]["content"]
         self.messages.append({"role": "assistant", "content": message})
 
         if len(self.messages) > self.round * 2 + 1:
             text = self._build_message(self.messages)
-            #print (text)
-            #print ("=====summarize=====")
-            summarize = self.summarize(text)
-            #print (summarize)
-            #print ("=====summarize=====")
             self.messages = []
-            self.messages.append({"role": "system", "content": summarize})
+            self.messages.append({"role": "system", "content": text})
         return message
 
-    def summarize(self, text, max_tokens=200):
-        response = openai.Completion.create(
-            model = "text-davinci-003",
-            prompt = text + "\n\n请总结一下上面User和Assistant聊了些什么，限制100字以内：\n",
-            max_tokens = max_tokens,
-        )
-        return response["choices"][0]["text"]
-
     def _build_message(self, messages):
         text = ""
         for message in messages:
@@ -56,7 +41,6 @@ class Conversation:
                 text += "Assistant : " + message["content"] + "\n\n" 
         return text
 
-
 prompt = """你是一个大数据和AI领域的专家，用中文回答大数据和AI的相关问题。你的回答需要满足以下要求:
 1. 你的回答必须是中文
 2. 回答限制在200个字以内
@@ -64,7 +48,6 @@ prompt = """你是一个大数据和AI领域的专家，用中文回答大数据
 
 conv = Conversation(prompt, 3)
 
-
 def answer(question, history=[]):
     history.append(question)
     message = conv.ask(question)