refactor: Add Comments for explainig codes and adjust linting

app.py

@@ -1,38 +1,45 @@
+import gradio as gr
+import openai
+import os
+
 from langchain.chat_models import ChatOpenAI
 from langchain.document_loaders import PyPDFLoader
 from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.embeddings.cohere import CohereEmbeddings
 from langchain.text_splitter import CharacterTextSplitter
-from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch
 from langchain.vectorstores import Chroma
-from PyPDF2 import PdfWriter
-import gradio as gr
-import os
 from dotenv import load_dotenv
-import openai
+
+from langchain.embeddings.cohere import CohereEmbeddings
+from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch
+from PyPDF2 import PdfWriter
 
 load_dotenv()
-#비밀키 가져오기 시도중
-# api_key = os.getenv('OPENAI_API_KEY') ## .env 파일 업로드하면 숨겨지지 않음 안됨
-# api_key = os.environ['my_secret'] ## 안불러와짐
-# api_key = os.getenv('my_secret') ## 3트 .env 대신 secret키를 불러오는 형태로 도전
-os.environ["OPENAI_API_KEY"] = os.environ['my_secret']
+os.environ["OPENAI_API_KEY"] = os.getenv('my_secret')
+openai.api_key = os.getenv('my_secret')
 
-loader = PyPDFLoader("/home/user/app/docs.pdf")
+## Load PDF file
+loader = PyPDFLoader("docs.pdf")
 documents = loader.load()
 
+## Split Document
 text_splitter = CharacterTextSplitter(chunk_size=800, chunk_overlap=0)
 texts = text_splitter.split_documents(documents)
 
-#vector embedding
+## token -> Vector Embedding
 embeddings = OpenAIEmbeddings()
 vector_store = Chroma.from_documents(texts, embeddings)
 retriever = vector_store.as_retriever(search_kwargs={"k": 2})
 
 from langchain.chat_models import ChatOpenAI
 from langchain.chains import RetrievalQAWithSourcesChain
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    SystemMessagePromptTemplate,
+    HumanMessagePromptTemplate,
+)
 
-llm = ChatOpenAI(model_name="gpt-4", temperature=0)  # Modify model_name if you have access to GPT-4
+## Build LLM Chain
+llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)  # Modify model_name if you have access to GPT-4
 
 chain = RetrievalQAWithSourcesChain.from_chain_type(
     llm=llm,
@@ -40,12 +47,6 @@ chain = RetrievalQAWithSourcesChain.from_chain_type(
     retriever = retriever,
     return_source_documents=True)
 
-from langchain.prompts.chat import (
-    ChatPromptTemplate,
-    SystemMessagePromptTemplate,
-    HumanMessagePromptTemplate,
-)
-
 system_template="""Use the following pieces of context to answer the users question shortly.
 Given the following summaries of a long document and a question, create a final answer with references ("SOURCES"), use "SOURCES" in capital letters regardless of the number of sources.
 If you don't know the answer, just say that "I don't know", don't try to make up an answer.
@@ -61,12 +62,11 @@ messages = [
 
 prompt = ChatPromptTemplate.from_messages(messages)
 
-from langchain.chat_models import ChatOpenAI
-from langchain.chains import RetrievalQAWithSourcesChain
-
+############################
+## Local 에서 잘 되는지 확인
 chain_type_kwargs = {"prompt": prompt}
 
-llm = ChatOpenAI(model_name="gpt-4", temperature=0)  # Modify model_name if you have access to GPT-4
+llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)  # Modify model_name if you have access to GPT-4
 
 chain = RetrievalQAWithSourcesChain.from_chain_type(
     llm=llm,
@@ -84,21 +84,21 @@ for doc in result['source_documents']:
     print('내용 : ' + doc.page_content[0:100].replace('\n', ' '))
     print('파일 : ' + doc.metadata['source'])
     print('페이지 : ' + str(doc.metadata['page']))
+##############################
 
-
+## Define response method
 def respond(message, chat_history):  # 채팅봇의 응답을 처리하는 함수를 정의합니다.
 
     result = chain(message)
-
     bot_message = result['answer']
 
     for i, doc in enumerate(result['source_documents']):
         bot_message += '[' + str(i+1) + '] ' + doc.metadata['source'] + '(' + str(doc.metadata['page']) + ') '
-
     chat_history.append((message, bot_message))  # 채팅 기록에 사용자의 메시지와 봇의 응답을 추가합니다.
 
     return "", chat_history  # 수정된 채팅 기록을 반환합니다.
 
+## Build Gradio App
 with gr.Blocks(theme='gstaff/sketch') as demo:  # gr.Blocks()를 사용하여 인터페이스를 생성합니다.
     gr.Markdown("# 안녕하세요. 세이노와 대화해보세요.")
     chatbot = gr.Chatbot(label="채팅창")  # '채팅창'이라는 레이블을 가진 채팅봇 컴포넌트를 생성합니다.