Create app.py

app.py

@@ -0,0 +1,196 @@
+import streamlit as st
+import tiktoken
+from loguru import logger
+
+from langchain.chains import ConversationalRetrievalChain
+from langchain.chat_models import ChatOpenAI
+
+from langchain.document_loaders.pdf import (PyPDFLoader, PyMuPDFLoader)
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+
+from langchain.memory import ConversationBufferMemory
+from langchain.vectorstores import FAISS
+
+# from streamlit_chat import message
+from langchain.callbacks import get_openai_callback
+from langchain.memory import StreamlitChatMessageHistory
+from gtts import gTTS
+from IPython.display import Audio, display
+
+from io import BytesIO
+import speech_recognition as sr
+
+from langchain.callbacks import get_openai_callback
+from langchain.memory import StreamlitChatMessageHistory
+
+def main():
+    st.set_page_config(
+        page_title="차량용 Q&A 챗봇",
+        page_icon=":car:"
+    )
+
+    st.title("차량용 Q&A 챗봇 :car:")
+
+    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
+
+    if "processComplete" not in st.session_state:
+        st.session_state.processComplete = None
+
+    with st.sidebar:
+        uploaded_files = st.file_uploader("차량 메뉴얼 PDF 파일을 넣어주세요.", type=['pdf'], accept_multiple_files=True)
+        openai_api_key = st.text_input("OpenAI API Key", key="chatbot_api_key", type="password")
+        process = st.button("실행")
+
+    if process:
+        if not openai_api_key:
+            st.info("Open AI키를 입력해주세요.")
+            st.stop()
+        files_text = get_text(uploaded_files)
+        text_chunks = get_text_chunks(files_text)
+        vector_store = get_vectorstore(text_chunks)
+
+        st.session_state.conversation = get_conversation_chain(vector_store, openai_api_key)
+
+        st.session_state.processComplete = True
+
+    if 'messages' not in st.session_state:
+        st.session_state['messages'] = [{"role": "assistant",
+                                         "content": "안녕하세요! 주어진 문서에 대해 궁금하신 것이 있으면 언제든 물어봐주세요!"}]
+
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+
+    history = StreamlitChatMessageHistory(key="chat_messages")
+
+    # Chat logic
+    if query := st.chat_input("질문을 입력해주세요."):
+        st.session_state.messages.append({"role": "user", "content": query})
+
+        with st.chat_message("user"):
+            st.markdown(query)
+
+        with st.chat_message("assistant"):
+            # STT 코드 추가
+            user_voice_input = stt()
+            if user_voice_input:
+                # Add user's voice input to chat history
+                st.session_state.messages.append({"role": "user", "content": user_voice_input})
+
+                # Continue with the rest of the conversation logic...
+                chain = st.session_state.conversation
+
+                with st.spinner("Thinking..."):
+                    result = chain({"question": query})
+                    with get_openai_callback() as cb:
+                        st.session_state.chat_history = result['chat_history']
+                    response = result['answer']
+                    source_documents = result['source_documents']
+
+                    st.markdown(response)
+                    with st.expander("참고 문서 확인"):
+                        st.markdown(source_documents[0].metadata['source'], help=source_documents[0].page_content)
+                        st.markdown(source_documents[1].metadata['source'], help=source_documents[1].page_content)
+                        st.markdown(source_documents[2].metadata['source'], help=source_documents[2].page_content)
+
+                # TTS 코드 추가
+                tts("이것은 음성으로 변환된 답변입니다.")
+
+                # Add assistant message to chat history
+                st.session_state.messages.append({"role": "assistant", "content": response})
+
+# ...
+
+# STT 함수 추가
+def stt():
+    recognizer = sr.Recognizer()
+
+    with sr.Microphone() as source:
+        st.write("말해보세요...")
+        recognizer.adjust_for_ambient_noise(source)
+        audio = recognizer.listen(source, timeout=5)
+
+    try:
+        text = recognizer.recognize_google(audio, language="ko-KR")
+        st.write("인식된 텍스트: {}".format(text))
+        return text
+    except sr.UnknownValueError:
+        st.write("음성을 인식할 수 없습니다.")
+        return None
+    except sr.RequestError as e:
+        st.write("Google Speech Recognition 서비스에 접근할 수 없습니다; {0}".format(e))
+        return None
+
+# TTS 함수 추가
+def tts(text):
+    st.write("음성으로 변환 중...")
+    tts = gTTS(text=text, lang='ko')
+    audio_stream = BytesIO()
+    tts.save(audio_stream)
+    st.audio(audio_stream, format='audio/wav')
+
+def tiktoken_len(text):
+    tokenizer = tiktoken.get_encoding("cl100k_base")
+    tokens = tokenizer.encode(text)
+    return len(tokens)
+
+
+def get_text(docs):
+    doc_list = []
+
+    for doc in docs:
+        file_name = doc.name  # doc 객체의 이름을 파일 이름으로 사용
+        with open(file_name, "wb") as file:  # 파일을 doc.name으로 저장
+            file.write(doc.getvalue())
+            logger.info(f"Uploaded {file_name}")
+        if '.pdf' in doc.name:
+            loader = PyMuPDFLoader(file_name)
+            documents = loader.load_and_split()
+
+        doc_list.extend(documents)
+    return doc_list
+
+
+def get_text_chunks(text):
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,
+        chunk_overlap=100,
+        length_function=tiktoken_len
+    )
+    chunks = text_splitter.split_documents(text)
+    return chunks
+
+
+def get_vectorstore(text_chunks):
+    embeddings = HuggingFaceEmbeddings(
+        model_name="jhgan/ko-sroberta-multitask",
+        model_kwargs={'device': 'cpu'},
+        encode_kwargs={'normalize_embeddings': True}
+    )
+    vectordb = FAISS.from_documents(text_chunks, embeddings)
+    return vectordb
+
+
+def get_conversation_chain(vetorestore, openai_api_key):
+    llm = ChatOpenAI(openai_api_key=openai_api_key, model_name='gpt-3.5-turbo', temperature=0)
+    conversation_chain = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        chain_type="stuff",
+        retriever=vetorestore.as_retriever(search_type='mmr', vervose=True),
+        memory=ConversationBufferMemory(memory_key='chat_history', return_messages=True, output_key='answer'),
+        get_chat_history=lambda h: h,
+        return_source_documents=True,
+        verbose=True
+    )
+
+    return conversation_chain
+
+
+if __name__ == '__main__':
+    main()