update

app.py

@@ -17,28 +17,28 @@ from langchain.schema import SystemMessage
 
 import urllib
 
-# urllib.request.urlretrieve(
-#     "https://huggingface.co/hfl/chinese-alpaca-2-7b-rlhf-gguf/resolve/main/ggml-model-q6_k.gguf?download=true", 
-#     "ggml-model-q6_k.gguf"
-#     )
+urllib.request.urlretrieve(
+    "https://huggingface.co/hfl/chinese-alpaca-2-7b-rlhf-gguf/resolve/main/ggml-model-q6_k.gguf?download=true", 
+    "ggml-model-q6_k.gguf"
+    )
 
-# template_messages = [
-#     SystemMessage(content="你是一名软件工程师，你的名字叫做贺英旭。请你以这个身份回答以下问题！"),
-#     MessagesPlaceholder(variable_name="chat_history"),
-#     HumanMessagePromptTemplate.from_template("{text}"),
-# ]
+template_messages = [
+    SystemMessage(content="你是一名软件工程师，你的名字叫做贺英旭。请你以这个身份回答以下问题！"),
+    MessagesPlaceholder(variable_name="chat_history"),
+    HumanMessagePromptTemplate.from_template("{text}"),
+]
 
-# prompt_template = ChatPromptTemplate.from_messages(template_messages)
+prompt_template = ChatPromptTemplate.from_messages(template_messages)
 
-# llm = LlamaCpp(
-#     model_path="ggml-model-q6_k.gguf",
-#     temperature=0.75,
-#     max_tokens=64
-# )
-# model = Llama2Chat(llm=llm)
+llm = LlamaCpp(
+    model_path="ggml-model-q6_k.gguf",
+    temperature=0.75,
+    max_tokens=64
+)
+model = Llama2Chat(llm=llm)
 
-# memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
-# chain = LLMChain(llm=model, prompt=prompt_template, memory=memory)
+memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+chain = LLMChain(llm=model, prompt=prompt_template, memory=memory)
 
 
 def add_text(history, text):
@@ -60,8 +60,7 @@ def bot(history):
 
 def infer(question):
     
-    # result = chain.run(text=question).strip()
-    result = "123123123123"
+    result = chain.run(text=question).strip()
     print(result)
     return result