Update app.py

app.py

@@ -81,7 +81,7 @@ def get_conversation_chain(vectorstore, tokenH):
     def generate_response(messages):
         try:
             completion = client.chat.completions.create(
-                model="HuggingFaceH4/zephyr-7b-alphat", 
+                model="Qwen/Qwen2.5-72B-Instruct", 
                 messages=messages, 
                 max_tokens=500
             )
@@ -148,516 +148,3 @@ def main():
 if __name__ == '__main__':
     main()
 
-
-
-# import streamlit as st
-# from dotenv import load_dotenv
-# from PyPDF2 import PdfReader
-# from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
-# from langchain_community.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
-# from langchain_community.vectorstores import FAISS, Chroma
-# from langchain_community.embeddings import HuggingFaceEmbeddings  # General embeddings from HuggingFace models.
-# from langchain.chat_models import ChatOpenAI
-# from langchain.memory import ConversationBufferMemory
-# from langchain.chains import ConversationalRetrievalChain
-# from htmlTemplates import css, bot_template, user_template
-# from langchain.llms import HuggingFaceHub, LlamaCpp, CTransformers  # For loading transformer models.
-# from langchain_community.document_loaders import PyPDFLoader, TextLoader, JSONLoader, CSVLoader
-# import tempfile # 임시 파일을 생성하기 위한 라이브러리입니다.
-# import os
-
-# def get_pdf_text(pdf_docs):
-#     temp_dir = tempfile.TemporaryDirectory()  # 임시 디렉토리를 생성합니다.
-#     temp_filepath = os.path.join(temp_dir.name, pdf_docs.name)  # 임시 파일 경로를 생성합니다.
-#     with open(temp_filepath, "wb") as f:  # 임시 파일을 바이너리 쓰기 모드로 엽니다.
-#         f.write(pdf_docs.getvalue())  # PDF 문서의 내용을 임시 파일에 씁니다.
-#     pdf_loader = PyPDFLoader(temp_filepath)  # PyPDFLoader를 사용해 PDF를 로드합니다.
-#     pdf_doc = pdf_loader.load()  # 텍스트를 추출합니다.
-#     return pdf_doc  # 추출한 텍스트를 반환합니다.
-
-# def get_text_file(text_docs):
-#     temp_dir = tempfile.TemporaryDirectory()
-#     temp_filepath = os.path.join(temp_dir.name, text_docs.name)
-#     with open(temp_filepath, "wb") as f:
-#         f.write(text_docs.getvalue())
-#     text_loader = TextLoader(temp_filepath)
-#     text_doc = text_loader.load()
-#     return text_doc
-
-# def get_csv_file(csv_docs):
-#     temp_dir = tempfile.TemporaryDirectory()
-#     temp_filepath = os.path.join(temp_dir.name, csv_docs.name)
-#     with open(temp_filepath, "wb") as f:
-#         f.write(csv_docs.getvalue())
-#     csv_loader = CSVLoader(temp_filepath)
-#     csv_doc = csv_loader.load()
-#     return csv_doc
-
-# def get_json_file(json_docs):
-#     temp_dir = tempfile.TemporaryDirectory()
-#     temp_filepath = os.path.join(temp_dir.name, json_docs.name)
-#     with open(temp_filepath, "wb") as f:
-#         f.write(json_docs.getvalue())
-#     json_loader = JSONLoader(temp_filepath)
-#     json_doc = json_loader.load()
-#     return json_doc
-
-# def get_text_chunks(documents):
-#     text_splitter = RecursiveCharacterTextSplitter(
-#         chunk_size=300,  # 청크의 크기를 지정합니다.
-#         chunk_overlap=100,  # 청크 사이의 중복을 지정합니다.
-#         length_function=len  # 텍스트의 길이를 측정하는 함수를 지정합니다.
-#     )
-
-#     documents = text_splitter.split_documents(documents)  # 문서들을 청크로 나눕니다
-#     return documents  # 나눈 청크를 반환합니다.
-
-# # 텍스트 청크들로부터 벡터 스토어를 생성하는 함수입니다.
-# def get_vectorstore(text_chunks):
-#     # embeddings = OpenAIEmbeddings()
-#     # embeddings = HuggingFaceEmbeddings(model_name="WhereIsAI/UAE-Large-V1")
-#     embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-#     vectorstore = FAISS.from_documents(text_chunks, embeddings)  # FAISS 벡터 스토어를 생성합니다.
-#     return vectorstore  # 생성된 벡터 스토어를 반환합니다.
-
-# # def get_conversation_chain(vectorstore, tokenH):
-# #     if not tokenH:
-# #         raise ValueError("API token is required to initialize the HuggingFaceHub model")
-
-# #     # Initialize the HuggingFaceHub model with the correct token
-# #     try:
-# #         llm = HuggingFaceHub(
-# #             repo_id="Qwen/Qwen2.5-7B-Instruct", 
-# #             token=tokenH)
-# #     except Exception as e:
-# #         raise ValueError(f"Error initializing HuggingFaceHub model: {str(e)}")
-
-# #     # Create conversational retrieval chain without memory
-# #     conversation_chain = ConversationalRetrievalChain.from_llm(
-# #         llm=llm,
-# #         retriever=vectorstore.as_retriever()
-# #     )
-    
-# #     return conversation_chain
-# from huggingface_hub import InferenceClient
-
-# def get_conversation_chain(vectorstore, tokenH):
-#     if not tokenH:
-#         raise ValueError("API token is required to initialize the HuggingFaceHub model")
-
-#     # Initialize the InferenceClient with the API key
-#     try:
-#         client = InferenceClient(api_key=tokenH)
-#     except Exception as e:
-#         raise ValueError(f"Error initializing HuggingFace InferenceClient: {str(e)}")
-
-#     # Initialize chat history
-#     chat_history = []
-
-#     # Function to generate responses from the InferenceClient
-#     def generate_response(messages):
-#         nonlocal chat_history
-#         try:
-#             completion = client.chat.completions.create(
-#                 model="microsoft/Phi-3.5-mini-instruct", 
-#                 messages=messages, 
-#                 max_tokens=500
-#             )
-#             # Add the new message and response to chat history
-#             chat_history.append({"role": "user", "content": messages[-1]["content"]})
-#             chat_history.append({"role": "assistant", "content": completion.choices[0].message['content']})
-            
-#             # Return the current assistant's response
-#             return completion.choices[0].message['content']
-#         except Exception as e:
-#             raise ValueError(f"Error generating response: {str(e)}")
-
-#     # Create conversational retrieval chain without memory
-#    def conversation_chain(user_input):
-#     # Ensure user input is a string
-#     if isinstance(user_input, dict):
-#         user_input = user_input.get('question', '')
-
-#     # Get the relevant documents from the vector store using retriever's query method
-#     retriever = vectorstore.as_retriever(search_type="similarity", search_kwargs={"k": 5})  # Adjust the search arguments
-#     documents = retriever.get_relevant_documents(user_input)
-
-#     # Extract text from the documents (ensure they are strings)
-#     documents_text = "\n".join(doc.page_content for doc in documents)  # Use doc.page_content instead of doc['text']
-
-#     # Prepare the messages for the InferenceClient
-#     messages = [{"role": "user", "content": user_input}, {"role": "system", "content": documents_text}]
-#     response = generate_response(messages)
-
-#     # Return the response
-#     return response
-
-    
-# def handle_userinput(user_question):
-#     # 대화 체인을 사용하여 사용자 질문에 대한 응답을 생성합니다.
-#     response = st.session_state.conversation({'question': user_question})
-
-#     # Ensure response contains both chat_history and the assistant's response
-#     st.session_state.chat_history = response['chat_history']
-
-#     # Display chat history
-#     for i, message in enumerate(st.session_state.chat_history):
-#         if i % 2 == 0:
-#             st.write(user_template.replace("{{MSG}}", message['content']), unsafe_allow_html=True)
-#         else:
-#             st.write(bot_template.replace("{{MSG}}", message['content']), unsafe_allow_html=True)
-
-
-# def main():
-#     st.set_page_config(page_title="Chat with multiple Files", page_icon=":books:")
-#     st.write(css, unsafe_allow_html=True)
-
-#     if "conversation" not in st.session_state:
-#         st.session_state.conversation = None
-#     if "chat_history" not in st.session_state:
-#         st.session_state.chat_history = None
-
-#     st.header("Chat with multiple Files :")
-#     st.header("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21")
-#     tokenH = st.text_input("Paste your TOKEN key (sk-...)", key="token_input_1")
-    
-#     # Validate if the token is empty
-#     if not tokenH:
-#         st.warning("Please enter a valid HuggingFace API token.")
-#         return
-
-#     user_question = st.text_input("Ask a question about your documents:")
-#     if user_question:
-#         handle_userinput(user_question)
-
-#     with st.sidebar:
-#         tokenH_sidebar = st.text_input("Paste your TOKEN key (sk-...)", key="token_input_2")
-#         tokenH = tokenH_sidebar or tokenH  # fallback to main input if sidebar is empty
-
-#         st.subheader("Your documents")
-#         docs = st.file_uploader(
-#             "Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
-#         if st.button("Process"):
-#             with st.spinner("Processing"):
-#                 # get pdf text
-#                 doc_list = []
-
-#                 for file in docs:
-#                     print('file - type : ', file.type)
-#                     if file.type == 'text/plain':
-#                         # file is .txt
-#                         doc_list.extend(get_text_file(file))
-#                     elif file.type in ['application/octet-stream', 'application/pdf']:
-#                         # file is .pdf
-#                         doc_list.extend(get_pdf_text(file))
-#                     elif file.type == 'text/csv':
-#                         # file is .csv
-#                         doc_list.extend(get_csv_file(file))
-#                     elif file.type == 'application/json':
-#                         # file is .json
-#                         doc_list.extend(get_json_file(file))
-
-#                 # get the text chunks
-#                 text_chunks = get_text_chunks(doc_list)
-
-#                 # create vector store
-#                 vectorstore = get_vectorstore(text_chunks)
-
-#                 # create conversation chain
-#                 st.session_state.conversation = get_conversation_chain(vectorstore, tokenH)
-
-# if __name__ == '__main__':
-#     main()
-
-# import streamlit as st
-# from dotenv import load_dotenv
-# from PyPDF2 import PdfReader
-# from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
-# from langchain_community.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
-# from langchain_community.vectorstores import FAISS, Chroma
-# from langchain_community.embeddings import HuggingFaceEmbeddings  # General embeddings from HuggingFace models.
-# from langchain.chat_models import ChatOpenAI
-# from langchain.memory import ConversationBufferMemory
-# from langchain.chains import ConversationalRetrievalChain
-# from htmlTemplates import css, bot_template, user_template
-# from langchain.llms import HuggingFaceHub, LlamaCpp, CTransformers  # For loading transformer models.
-# from langchain_community.document_loaders import PyPDFLoader, TextLoader, JSONLoader, CSVLoader
-# import tempfile # 임시 파일을 생성하기 위한 라이브러리입니다.
-# import os
-
-
-# def get_pdf_text(pdf_docs):
-#     temp_dir = tempfile.TemporaryDirectory() # 임시 디렉토리를 생성합니다.
-#     temp_filepath = os.path.join(temp_dir.name, pdf_docs.name) # 임시 파일 경로를 생성합니다.
-#     with open(temp_filepath, "wb") as f:  # 임시 파일을 바이너리 쓰기 모드로 엽니다.
-#         f.write(pdf_docs.getvalue()) # PDF 문서의 내용을 임시 파일에 씁니다.
-#     pdf_loader = PyPDFLoader(temp_filepath) # PyPDFLoader를 사용해 PDF를 로드합니다.
-#     pdf_doc = pdf_loader.load() # 텍스트를 추출합니다.
-#     return pdf_doc # 추출한 텍스트를 반환합니다.
-
-
-# def get_text_file(text_docs):
-#     temp_dir = tempfile.TemporaryDirectory()
-#     temp_filepath = os.path.join(temp_dir.name, text_docs.name)
-#     with open(temp_filepath, "wb") as f:
-#         f.write(text_docs.getvalue())
-#     text_loader = TextLoader(temp_filepath)
-#     text_doc = text_loader.load()
-#     return text_doc
-
-
-# def get_csv_file(csv_docs):
-#     temp_dir = tempfile.TemporaryDirectory()
-#     temp_filepath = os.path.join(temp_dir.name, csv_docs.name)
-#     with open(temp_filepath, "wb") as f:
-#         f.write(csv_docs.getvalue())
-#     csv_loader = CSVLoader(temp_filepath)
-#     csv_doc = csv_loader.load()
-#     return csv_doc
-
-
-# def get_json_file(json_docs):
-#     temp_dir = tempfile.TemporaryDirectory()
-#     temp_filepath = os.path.join(temp_dir.name, json_docs.name)
-#     with open(temp_filepath, "wb") as f:
-#         f.write(json_docs.getvalue())
-#     json_loader = JSONLoader(temp_filepath)
-#     json_doc = json_loader.load()
-#     return json_doc
-
-
-# def get_text_chunks(documents):
-#     text_splitter = RecursiveCharacterTextSplitter(
-#         chunk_size=1000, # 청크의 크기를 지정합니다.
-#         chunk_overlap=200, # 청크 사이의 중복을 지정합니다.
-#         length_function=len # 텍스트의 길이를 측정하는 함수를 지정합니다.
-#     )
-
-#     documents = text_splitter.split_documents(documents) # 문서들을 청크로 나눕니다
-#     return documents # 나눈 청크를 반환합니다.
-
-
-# from langchain_huggingface import HuggingFaceEmbeddings
-# # 텍스트 청크들로부터 벡터 스토어를 생성하는 함수입니다.
-# def get_vectorstore(text_chunks):
-#     # OpenAI 임베딩 모델을 로드합니다. (Embedding models - Ada v2)
-
-#     # embeddings = OpenAIEmbeddings()
-#     embeddings = HuggingFaceEmbeddings(model_name="WhereIsAI/UAE-Large-V1")
-#     vectorstore = FAISS.from_documents(text_chunks, embeddings) # FAISS 벡터 스토어를 생성합니다.
-
-#     return vectorstore # 생성된 벡터 스토어를 반환합니다.
-
-
-# api="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21"
-# repo_id = "HuggingFaceH4/zephyr-7b-alpha"
-# # from huggingface_hub import InferenceClient
-
-# # from langchain.llms import HuggingFaceHub
-# # from langchain.llms import HuggingFaceInferenceAPI
-# # def get_conversation_chain(vectorstore):
-# #     # gpt_model_name = 'gpt-3.5-turbo'
-# #     # llm = ChatOpenAI(model_name = gpt_model_name) #gpt-3.5 모델 로드
-# #     # llm = HuggingFaceInferenceAPI(model_name="HuggingFaceH4/zephyr-7b-alpha", token=api[:-2])
-# #     # llm = InferenceClient(
-# #     # model=repo_id,
-# #     # token=api[:-2],  # Pass the token here
-# #     # timeout=120)
-# #     # llm = HuggingFaceHub(
-# #     #     repo_id="HuggingFaceH4/zephyr-7b-alpha", 
-# #     #     token=api[:-2],
-# #     #     huggingfacehub_api_token=api[:-2]
-# #     # )
-# #     # 대화 기록을 저장하기 위한 메모리를 생성합니다.
-# #     if "HUGGINGFACEHUB_API_TOKEN" not in os.environ:
-# #         st.write(ValueError("HUGGINGFACEHUB_API_TOKEN is not set in the environment variables."))
-
-# #     llm = HuggingFaceHub(
-# #         repo_id="HuggingFaceH4/zephyr-7b-alpha", 
-# #         token=os.getenv("HUGGINGFACEHUB_API_TOKEN")
-# #     )
-# #     memory = ConversationBufferMemory(
-# #         memory_key='chat_history', return_messages=True)
-# #     # 대화 검색 체인을 생성합니다.
-# #     conversation_chain = ConversationalRetrievalChain.from_llm(
-# #         llm=llm,
-# #         retriever=vectorstore.as_retriever(),
-# #         memory=memory
-# #     )
-# #     return conversation_chain
-
-
-
-# import os
-# from langchain.llms import HuggingFaceHub
-# from langchain.memory import ConversationBufferMemory
-# from langchain.chains import ConversationalRetrievalChain
-
-# # def get_conversation_chain(vectorstore,tokenH):
-# #     # api_token = os.getenv("HUGGINGFACEHUB_API_TOKEN")
-
-# #     # if api_token is None:
-# #     #     st.header("HUGGINGFACEHUB_API_TOKEN is not set in the environment variables :")
-# #     #     raise ValueError("HUGGINGFACEHUB_API_TOKEN is not set in the environment variables.")
-    
-# #     # Initialize the HuggingFaceHub model with the correct token
-# #     # llm = HuggingFaceHub(
-# #     #     repo_id="HuggingFaceH4/zephyr-7b-alpha", 
-# #     #     token=tokenH
-# #     # )
-# #     tokenH = st.text_input("Paste your TOKENH key (sk-...)")
-
-# #     if tokenH:
-# #         llm = HuggingFaceHub(
-# #             repo_id="HuggingFaceH4/zephyr-7b-alpha", 
-# #             token=tokenH  # Token passed here directly
-# #         )
-
-    
-# #     # Set up memory for conversation history
-# #     memory = ConversationBufferMemory(
-# #         memory_key='chat_history', return_messages=True
-# #     )
-    
-# #     # Create conversational retrieval chain
-# #     conversation_chain = ConversationalRetrievalChain.from_llm(
-# #         llm=llm,
-# #         retriever=vectorstore.as_retriever(),
-# #         memory=memory
-# #     )
-    
-# #     return conversation_chain
-
-# # def get_conversation_chain(vectorstore, tokenH):
-# #     if not tokenH:
-# #         raise ValueError("API token is required to initialize the HuggingFaceHub model")
-
-# #     # Initialize the HuggingFaceHub model with the correct token
-# #     try:
-# #         llm = HuggingFaceHub(
-# #             repo_id="Qwen/Qwen2.5-7B-Instruct", 
-# #             token=tokenH,
-# #             use_auth_token=True
-# #         )
-# #     except Exception as e:
-# #         raise ValueError(f"Error initializing HuggingFaceHub model: {str(e)}")
-
-# #     # Set up memory for conversation history
-# #     memory = ConversationBufferMemory(
-# #         memory_key='chat_history', return_messages=True
-# #     )
-    
-# #     # Create conversational retrieval chain
-# #     conversation_chain = ConversationalRetrievalChain.from_llm(
-# #         llm=llm,
-# #         retriever=vectorstore.as_retriever(),
-# #         memory=memory
-# #     )
-    
-# #     return conversation_chain
-
-# def get_conversation_chain(vectorstore, tokenH):
-#     if not tokenH:
-#         raise ValueError("API token is required to initialize the HuggingFaceHub model")
-
-#     # Initialize the HuggingFaceHub model with the correct token
-#     try:
-#         llm = HuggingFaceHub(
-#             repo_id="Qwen/Qwen2.5-7B-Instruct", 
-#             token=tokenH)
-#     except Exception as e:
-#         raise ValueError(f"Error initializing HuggingFaceHub model: {str(e)}")
-
-#     # Set up memory for conversation history
-#     memory = ConversationBufferMemory(
-#         memory_key='chat_history', return_messages=True
-#     )
-    
-#     # Create conversational retrieval chain
-#     conversation_chain = ConversationalRetrievalChain.from_llm(
-#         llm=llm,
-#         retriever=vectorstore.as_retriever(),
-#         memory=memory
-#     )
-    
-#     return conversation_chain
-    
-    
-# def handle_userinput(user_question):
-#     # 대화 체인을 사용하여 사용자 질문에 대한 응답을 생성합니다.
-#     response = st.session_state.conversation({'question': user_question})
-#     # 대화 기록을 저장합니다.
-#     st.session_state.chat_history = response['chat_history']
-
-#     for i, message in enumerate(st.session_state.chat_history):
-#         if i % 2 == 0:
-#             st.write(user_template.replace(
-#                 "{{MSG}}", message.content), unsafe_allow_html=True)
-#         else:
-#             st.write(bot_template.replace(
-#                 "{{MSG}}", message.content), unsafe_allow_html=True)
-
-
-
-# def main():
-#     # load_dotenv()
-#     st.set_page_config(page_title="Chat with multiple Files",
-#                        page_icon=":books:")
-#     st.write(css, unsafe_allow_html=True)
-
-#     if "conversation" not in st.session_state:
-#         st.session_state.conversation = None
-#     if "chat_history" not in st.session_state:
-#         st.session_state.chat_history = None
-
-#     st.header("Chat with multiple Files :",)
-#     st.header("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21")
-#     tokenH = st.text_input("Paste your TOKEN key (sk-...)", key="token_input_1")
-    
-#     # Validate if the token is empty
-#     if not tokenH:
-#         st.warning("Please enter a valid HuggingFace API token.")
-#         return
-
-#     user_question = st.text_input("Ask a question about your documents:")
-#     if user_question:
-#         handle_userinput(user_question)
-
-#     with st.sidebar:
-#         tokenH_sidebar = st.text_input("Paste your TOKEN key (sk-...)", key="token_input_2")
-#         tokenH = tokenH_sidebar or tokenH  # fallback to main input if sidebar is empty
-
-#         st.subheader("Your documents")
-#         docs = st.file_uploader(
-#             "Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
-#         if st.button("Process"):
-#             with st.spinner("Processing"):
-#                 # get pdf text
-#                 doc_list = []
-
-#                 for file in docs:
-#                     print('file - type : ', file.type)
-#                     if file.type == 'text/plain':
-#                         # file is .txt
-#                         doc_list.extend(get_text_file(file))
-#                     elif file.type in ['application/octet-stream', 'application/pdf']:
-#                         # file is .pdf
-#                         doc_list.extend(get_pdf_text(file))
-#                     elif file.type == 'text/csv':
-#                         # file is .csv
-#                         doc_list.extend(get_csv_file(file))
-#                     elif file.type == 'application/json':
-#                         # file is .json
-#                         doc_list.extend(get_json_file(file))
-
-#                 # get the text chunks
-#                 text_chunks = get_text_chunks(doc_list)
-
-#                 # create vector store
-#                 vectorstore = get_vectorstore(text_chunks)
-
-#                 # create conversation chain
-#                 st.session_state.conversation = get_conversation_chain(vectorstore, tokenH)
-
-# if __name__ == '__main__':
-#     main()