Update app.py

app.py

@@ -1,21 +1,16 @@
 import streamlit as st
 from dotenv import load_dotenv
-from PyPDF2 import PdfReader
-from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
+from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
-from langchain.vectorstores import FAISS, Chroma
-from langchain.embeddings import HuggingFaceEmbeddings  # General embeddings from HuggingFace models.
+from langchain.vectorstores import FAISS
 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.document_loaders import PyPDFLoader, TextLoader, JSONLoader, CSVLoader
-import tempfile # 임시 파일을 생성하기 위한 라이브러리입니다.
+import tempfile
 import os
 
 
-# PDF 문서로부터 텍스트를 추출하는 함수입니다.
 def get_pdf_text(pdf_docs):
     temp_dir = tempfile.TemporaryDirectory()
     temp_filepath = os.path.join(temp_dir.name, pdf_docs.name)
@@ -23,72 +18,50 @@ def get_pdf_text(pdf_docs):
         f.write(pdf_docs.getvalue())
     pdf_loader = PyPDFLoader(temp_filepath)
     pdf_doc = pdf_loader.load()
+    return pdf_doc
+
+
+def get_text_file(docs):
+    text_loader = TextLoader(docs.name)
+    text = text_loader.load()
+    return [text]
+
+
+def get_csv_file(docs):
+    csv_loader = CSVLoader(docs.name)
+    csv_text = csv_loader.load()
+    return csv_text.values.tolist()
+
+
+def get_json_file(docs):
+    json_loader = JSONLoader(docs.name)
+    json_text = json_loader.load()
+    return [json_text]
+
 
-    text_list = []  # 각 페이지의 텍스트를 저장할 리스트
-
-    for page_num in range(len(pdf_doc)):
-        text_list.append(pdf_doc.get_page_text(page_num))
-
-    return text_list
-
-# 과제
-# 아래 텍스트 추출 함수를 작성
-
-def get_text_file(text_docs):
-    text_content = text_docs.getvalue().decode("utf-8")
-    return [text_content]
-
-def get_csv_file(csv_docs):
-    csv_content = csv_docs.getvalue().decode("utf-8")
-    csv_data = pd.read_csv(pd.compat.StringIO(csv_content))
-    text_list = []
-    for column in csv_data.columns:
-        text_list.extend(csv_data[column].astype(str).tolist())
-    return text_list
-
-def get_json_file(json_docs):
-    json_content = json_docs.getvalue().decode("utf-8")
-    json_data = json.loads(json_content)
-    text_list = []
-    for key, value in json_data.items():
-        if isinstance(value, str):
-            text_list.append(value)
-        elif isinstance(value, list):
-            text_list.extend(value)
-        elif isinstance(value, dict):
-            text_list.extend(value.values())
-    return text_list
-    
-# 문서들을 처리하여 텍스트 청크로 나누는 함수입니다.
 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.
+        chunk_size=1000,
+        chunk_overlap=200,
+        length_function=len
     )
 
-    documents = text_splitter.split_documents(documents) # 문서들을 청크로 나눕니다
-    return documents # 나눈 청크를 반환합니다.
+    documents = text_splitter.split_documents(documents)
+    return documents
 
 
-# 텍스트 청크들로부터 벡터 스토어를 생성하는 함수입니다.
 def get_vectorstore(text_chunks):
-    # OpenAI 임베딩 모델을 로드합니다. (Embedding models - Ada v2)
-
     embeddings = OpenAIEmbeddings()
-    vectorstore = FAISS.from_documents(text_chunks, embeddings) # FAISS 벡터 스토어를 생성합니다.
-
-    return vectorstore # 생성된 벡터 스토어를 반환합니다.
+    vectorstore = FAISS.from_documents(text_chunks, embeddings)
+    return vectorstore
 
 
 def get_conversation_chain(vectorstore):
     gpt_model_name = 'gpt-3.5-turbo'
-    llm = ChatOpenAI(model_name = gpt_model_name) #gpt-3.5 모델 로드
-    
-    # 대화 기록을 저장하기 위한 메모리를 생성합니다.
+    llm = ChatOpenAI(model_name=gpt_model_name)
+
     memory = ConversationBufferMemory(
         memory_key='chat_history', return_messages=True)
-    # 대화 검색 체인을 생성합니다.
     conversation_chain = ConversationalRetrievalChain.from_llm(
         llm=llm,
         retriever=vectorstore.as_retriever(),
@@ -96,11 +69,9 @@ def get_conversation_chain(vectorstore):
     )
     return conversation_chain
 
-# 사용자 입력을 처리하는 함수입니다.
+
 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):
@@ -135,34 +106,23 @@ def main():
 
         st.subheader("Your documents")
         docs = st.file_uploader(
-            "Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
+            "Upload your files 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)