Update app.py

app.py

@@ -8,90 +8,134 @@ from langchain.chains import ConversationalRetrievalChain
 from langchain_g4f import G4FLLM
 from g4f import Provider, models
 
-# Define the path for generated embeddings
+# Configuration
 DB_FAISS_PATH = 'vectorstore/db_faiss'
+EMBEDDING_MODEL = 'sentence-transformers/all-MiniLM-L6-v2'
+LLM_MODEL = models.gpt_35_turbo
+LLM_PROVIDER = Provider.Aichat
+
+# UI Configuration
+def configure_ui():
+    """Configure Streamlit UI settings"""
+    st.set_page_config(page_title="Zendo AI Assistant", page_icon="📄")
+    hide_streamlit_style = """
+    <style>
+    #MainMenu {visibility: hidden;}
+    footer {visibility: hidden;}
+    .stTextInput input {font-size: 16px;}
+    </style>
+    """
+    st.markdown(hide_streamlit_style, unsafe_allow_html=True)
+
+# Initialize session state
+def init_session_state():
+    """Initialize session state variables"""
+    if 'history' not in st.session_state:
+        st.session_state['history'] = []
+    if 'generated' not in st.session_state:
+        st.session_state['generated'] = ["こんにちは！Zendoアシスタントです。PDFの内容について何でも聞いてください 🤗"]
+    if 'past' not in st.session_state:
+        st.session_state['past'] = ["ようこそ！"]
 
-# Load LLM using G4F (supports GPT-3.5, etc.)
+# Load LLM model
 def load_llm():
-    llm = G4FLLM(
-        model=models.gpt_35_turbo,
-        provider=Provider.Aichat,
+    """Load the language model"""
+    return G4FLLM(
+        model=LLM_MODEL,
+        provider=LLM_PROVIDER,
     )
-   
-    return llm
-
-# Hide default Streamlit style
-hide_streamlit_style = """
-        <style>
-        #MainMenu {visibility: hidden;}
-        footer {visibility: hidden;}
-        </style>
-        """
-st.markdown(hide_streamlit_style, unsafe_allow_html=True)
-
-# Set the title for the Streamlit app
-st.title("📄 PDF Chatbot - Zendo美女チャットボックス")
-
-# Upload PDF file
-uploaded_file = st.file_uploader("Tải lên tệp PDF của bạn", type="pdf")
 
-if uploaded_file is not None:
-    # Save temporary file
+# Process uploaded PDF
+def process_pdf(uploaded_file):
+    """Process the uploaded PDF file"""
     with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmpfile:
         tmpfile.write(uploaded_file.getvalue())
         tmpfile_path = tmpfile.name
-
-    # Load PDF using PyPDFLoader
+    
     loader = PyPDFLoader(tmpfile_path)
     pdf_data = loader.load()
-
-    # Create embeddings and save to FAISS
-    embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2', model_kwargs={'device': 'cpu'})
+    
+    embeddings = HuggingFaceEmbeddings(
+        model_name=EMBEDDING_MODEL,
+        model_kwargs={'device': 'cpu'}
+    )
+    
     db = FAISS.from_documents(pdf_data, embeddings)
     db.save_local(DB_FAISS_PATH)
-
-    # Reload LLM and update retrieval chain
-    llm = load_llm()
-    chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=db.as_retriever())
-
-    st.success("PDF đã được tải lên và xử lý thành công!")
-
-    # Function for conversational chat
-    def conversational_chat(query):
-        result = chain({"question": query, "chat_history": st.session_state['history']})
-        st.session_state['history'].append((query, result["answer"]))
-        return result["answer"]
-
-    # Initialize session state for chat history and messages
-    if 'history' not in st.session_state:
-        st.session_state['history'] = []
-
-    if 'generated' not in st.session_state:
-        st.session_state['generated'] = ["こんにちは！zendo美女です。PDFの内容についてご質問ください... 🤗"]
-
-    if 'past' not in st.session_state:
-        st.session_state['past'] = ["チャットはここから"]
-
-    # UI Form for user input
-    response_container = st.container()
-    container = st.container()
-
-    with container:
-        with st.form(key='my_form', clear_on_submit=True):
-            user_input = st.text_input("ChatBox", placeholder="質問をご記入ください...", key='input')
-            submit_button = st.form_submit_button(label='Send')
-
-        if submit_button and user_input:
-            output = conversational_chat(user_input)
-            st.session_state['past'].append(user_input)
-            st.session_state['generated'].append(output)
-
-    # Display chat history
-    if st.session_state['generated']:
-        with response_container:
-            for i in range(len(st.session_state['generated'])):
-                message(st.session_state["past"][i], is_user=True, key=str(i) + '_user', avatar_style="big-smile")
-                message(st.session_state["generated"][i], key=str(i), avatar_style="thumbs")
-
-else:
-    st.info("Vui lòng tải lên một tệp PDF để bắt đầu trò chuyện.")
+    return db
+
+# Chat function
+def conversational_chat(query, chain):
+    """Handle conversational chat with memory"""
+    result = chain({
+        "question": query, 
+        "chat_history": st.session_state['history']
+    })
+    st.session_state['history'].append((query, result["answer"]))
+    return result["answer"]
+
+# Main application
+def main():
+    configure_ui()
+    init_session_state()
+    
+    st.title("📄 Zendo AI Assistant - PDFチャットボット")
+    
+    # Language selection
+    col1, col2 = st.columns([1, 3])
+    with col1:
+        language = st.selectbox("言語/Language", ["日本語", "English", "Tiếng Việt"])
+    
+    # Upload PDF
+    uploaded_file = st.file_uploader(
+        "PDFファイルをアップロードしてください (Upload PDF file)", 
+        type="pdf",
+        help="PDFをアップロードすると、その内容について質問できます"
+    )
+    
+    if uploaded_file:
+        with st.spinner("PDFを処理中...少々お待ちください"):
+            db = process_pdf(uploaded_file)
+            llm = load_llm()
+            chain = ConversationalRetrievalChain.from_llm(
+                llm=llm, 
+                retriever=db.as_retriever()
+            )
+            st.success("PDFの処理が完了しました！質問をどうぞ")
+        
+        # Chat interface
+        response_container = st.container()
+        
+        with st.form(key='chat_form', clear_on_submit=True):
+            user_input = st.text_input(
+                "メッセージを入力...", 
+                key='input',
+                placeholder="PDFについて質問してください"
+            )
+            submit_button = st.form_submit_button(label='送信')
+            
+            if submit_button and user_input:
+                output = conversational_chat(user_input, chain)
+                st.session_state['past'].append(user_input)
+                st.session_state['generated'].append(output)
+        
+        # Display chat history
+        if st.session_state['generated']:
+            with response_container:
+                for i in range(len(st.session_state['generated'])):
+                    message(
+                        st.session_state["past"][i], 
+                        is_user=True, 
+                        key=str(i) + '_user', 
+                        avatar_style="big-smile"
+                    )
+                    message(
+                        st.session_state["generated"][i], 
+                        key=str(i), 
+                        avatar_style="thumbs"
+                    )
+    else:
+        st.info("PDFファイルをアップロードしてチャットを開始してください")
+
+if __name__ == "__main__":
+    main()