Update app.py

app.py

@@ -28,15 +28,33 @@ def get_pdf_text(pdf_docs):
 # 과제
 # 아래 텍스트 추출 함수를 작성
 
-def get_text_file(docs):
-    pass
-
-
-def get_csv_file(docs):
-    pass
-
-def get_json_file(docs):
-    pass
+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
 
     
 # 문서들을 처리하여 텍스트 청크로 나누는 함수입니다.
@@ -147,5 +165,87 @@ def main():
                     vectorstore)
 
 
+if __name__ == '__main__':
+    main()
+e)
+    # 대화 검색 체인을 생성합니다.
+    conversation_chain = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        retriever=vectorstore.as_retriever(),
+        memory=memory
+    )
+    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):
+        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 :")
+    user_question = st.text_input("Ask a question about your documents:")
+    if user_question:
+        handle_userinput(user_question)
+
+    with st.sidebar:
+        openai_key = st.text_input("Paste your OpenAI API key (sk-...)")
+        if openai_key:
+            os.environ["OPENAI_API_KEY"] = openai_key
+
+        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)
+
+
 if __name__ == '__main__':
     main()