Update app.py

app.py

@@ -19,17 +19,11 @@ 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
-
+#사이트 관련 함수
 def main():
     st.set_page_config(
         page_title="차량용 Q&A 챗봇",
-        page_icon=":car:"
-    )
+        page_icon=":car:")
 
     st.title("차량용 Q&A 챗봇 :car:")
 
@@ -53,9 +47,9 @@ def main():
             st.stop()
         files_text = get_text(uploaded_files)
         text_chunks = get_text_chunks(files_text)
-        vector_store = get_vectorstore(text_chunks)
+        vetorestore = get_vectorstore(text_chunks)
 
-        st.session_state.conversation = get_conversation_chain(vector_store, openai_api_key)
+        st.session_state.conversation = get_conversation_chain(vetorestore, openai_api_key)
 
         st.session_state.processComplete = True
 
@@ -77,70 +71,32 @@ def main():
             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')
+            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)
 
+        # Add assistant message to chat history
+        st.session_state.messages.append({"role": "assistant", "content": response})
+
+
+#토큰화 시키는 곳
 def tiktoken_len(text):
     tokenizer = tiktoken.get_encoding("cl100k_base")
     tokens = tokenizer.encode(text)
     return len(tokens)
 
-
+#pdfload코드
 def get_text(docs):
     doc_list = []
 
@@ -156,7 +112,7 @@ def get_text(docs):
         doc_list.extend(documents)
     return doc_list
 
-
+#textsplitter 코드
 def get_text_chunks(text):
     text_splitter = RecursiveCharacterTextSplitter(
         chunk_size=1000,
@@ -166,7 +122,7 @@ def get_text_chunks(text):
     chunks = text_splitter.split_documents(text)
     return chunks
 
-
+#임베딩 및 벡터저장 코드
 def get_vectorstore(text_chunks):
     embeddings = HuggingFaceEmbeddings(
         model_name="jhgan/ko-sroberta-multitask",
@@ -176,7 +132,7 @@ def get_vectorstore(text_chunks):
     vectordb = FAISS.from_documents(text_chunks, embeddings)
     return vectordb
 
-
+#리트리버 및 llm코드
 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(