Create app.py

app.py

@@ -0,0 +1,61 @@
+import os
+from openai import OpenAI
+from langchain_community.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import Chroma
+from langchain_openai import OpenAIEmbeddings
+from langchain_openai import ChatOpenAI
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.runnables import RunnablePassthrough
+from langchain_core.output_parsers import StrOutputParser
+from langchain.schema import AIMessage, HumanMessage
+import gradio as gr
+
+# 1. PDF 로드 및 전처리
+pdf_filepath = '3.pdf'
+loader = PyPDFLoader(pdf_filepath)
+pages = loader.load()
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=4000, chunk_overlap=400)
+splits = text_splitter.split_documents(pages)
+
+# 2. 벡터 스토어 생성 및 임베딩
+vectorstore = Chroma.from_documents(documents=splits,
+                                    embedding=OpenAIEmbeddings())
+
+# 3. RAG 체인 설정
+template = '''Answer the question based only on the following context:
+{context}
+
+Question: {question}
+'''
+prompt = ChatPromptTemplate.from_template(template)
+
+model = ChatOpenAI(model='gpt-4o-mini', temperature=0)
+
+retriever = vectorstore.as_retriever()
+
+def format_docs(docs):
+    return '\n\n'.join(doc.page_content for doc in docs)
+
+rag_chain = (
+    {'context': retriever | format_docs, 'question': RunnablePassthrough()}
+    | prompt
+    | model
+    | StrOutputParser()
+)
+
+# 4. Gradio 인터페이스 predict 함수 수정
+def predict(message, history):
+    # RAG 체인을 사용하여 답변 생성
+    response = rag_chain.invoke(message)
+    return response
+
+# 5. Gradio 인터페이스 설정 및 실행
+demo = gr.ChatInterface(
+    predict,
+    title="영어 학습 챗봇 (Powered by RAG & LangChain)",
+    description="영어 교재(1.pdf) 내용을 기반으로 질문에 답변합니다."
+)
+
+demo.launch()