Update app.py

app.py

@@ -1,66 +1,20 @@
 import gradio as gr
-# from langchain_community.chat_models import ChatOllama
-# from langchain_community.embeddings import GPT4AllEmbeddings
-
-# from langchain.prompts import ChatPromptTemplate
-# from langchain.schema.runnable import RunnablePassthrough
-# from langchain_community.vectorstores import FAISS
 from langchain_community.llms import LlamaCpp
 
-# import os
-# os.system("ollama pull alen_ox/llama_3_fin")
-
 vector_db_path = "vectorstores/db_faiss"
 
 llm = LlamaCpp(
-    model_path="Llama-3.1-8B-Instruct.Q3_K_L.gguf",
-    temperature=0.75,
-    max_tokens=2000,
+    model_path="Llama-3.1-8B-Instruct.Q5_K_M.gguf",
+    temperature=0,
+    max_tokens=512,
     top_p=1,
     # callback_manager=callback_manager,
     verbose=True,  # Verbose is required to pass to the callback manager
 )
-# embeddings = OllamaEmbeddings(model="nomic-embed-text", show_progress=False)
-# embeddings = GPT4AllEmbeddings(model_name = "all-MiniLM-L6-v2.gguf2.f16.gguf", gpt4all_kwargs = {'allow_download': 'True'})
-
-# db = FAISS.load_local(vector_db_path, embeddings, allow_dangerous_deserialization=True)
-
-# # # Create retriever
-# retriever = db.as_retriever(
-#     search_type="similarity",
-#     search_kwargs= {"k": 3}
-# )
-# local_llm = 'llama3.1'
-
-# llm = ChatOllama(model=local_llm,
-#                  keep_alive="3h", 
-#                  max_tokens=512,  
-#                  temperature=0)
-
-# Create prompt template
 
 def respond(message, history, system_message, path_document):
-    # print(message, history, system_message, path_document)
-    respon = ''
-    # print("Answer:\n\n", end=" ", flush=True)
-    # template = """Bạn là trợ lý ảo vì vậy bạn hãy sử dụng dữ liệu dưới đây để trả lời câu hỏi, 
-    #     nếu không có thông tin hãy đưa ra câu trả lời sát nhất với câu hỏi từ các thông tin tìm được
-    #     Content: {content}
-    #     Question: {question}
-    #     Chỉ đưa ra các câu trả lời hữu ích.
-    #     Helpful answer:
-    #     """
-    # prompt = ChatPromptTemplate.from_template(template)
 
-    # rag_chain = (
-    #     {"content": retriever, "question": RunnablePassthrough()}
-    #     | prompt
-    #     | llm
-    # )
-    # for chunk in rag_chain.stream(message):
-    #     respon += chunk.content
-    #     print(chunk.content, end="", flush=True)
-    #     yield respon
+    respon = ''
     
     for chunk in llm.stream(message):
         respon += chunk