Create app.py

app.py

@@ -0,0 +1,123 @@
+import streamlit as st
+from config.globals import SPEAKER_TYPES, initial_prompt
+from langchain.prompts import PromptTemplate
+from langchain.chains.question_answering import load_qa_chain
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import Chroma
+from langchain_google_genai import GoogleGenerativeAIEmbeddings, ChatGoogleGenerativeAI
+from dotenv import load_dotenv
+import PyPDF2
+import os
+import io
+from langchain.document_loaders import PyPDFDirectoryLoader
+from langchain.embeddings import SentenceTransformerEmbeddings
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
+
+# --- Your RAG chatbot logic ---
+source_data_folder = "MyData"
+text_splitter = RecursiveCharacterTextSplitter(
+    separators=["\n\n", "\n", ". ", " ", ""],
+    chunk_size=2000,
+    chunk_overlap=200
+)
+embeddings_model = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+path_db = "/content/VectorDB"
+llm = ChatGoogleGenerativeAI(model="gemini-1.5-pro", google_api_key="AIzaSyAnsIVS4x_7lJLe9AYXGLV8FRwUTQkB-1w")
+
+# --- Streamlit app starts here ---
+# Set up the Streamlit app configuration
+st.set_page_config(
+    page_title="Gemini Pro RAG App",
+    page_icon="🔍",
+    layout="wide",
+    initial_sidebar_state="expanded",
+)
+
+# Initialize session state for chat history and vectorstore (PDF context)
+if 'chat_history' not in st.session_state:
+    st.session_state.chat_history = [initial_prompt]
+if 'vectorstore' not in st.session_state:
+    st.session_state.vectorstore = None
+
+# Function to clear chat history
+def clear_chat_history():
+    st.session_state.chat_history = [initial_prompt]
+
+# Extract text from PDF
+def extract_text_from_pdf(pdf_bytes):
+    pdf_reader = PyPDF2.PdfReader(io.BytesIO(pdf_bytes))
+    text = ""
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+    return text
+
+# Initialize vectorstore
+def initialize_vector_index(text):
+    docs = [{'page_content': text}]
+    splits = text_splitter.split_documents(docs)
+    vectorstore = Chroma.from_documents(documents=splits, embedding=embeddings_model, persist_directory=path_db)
+    return vectorstore
+
+# Sidebar configuration
+with st.sidebar:
+    st.title('🔍 Gemini RAG Chatbot')
+    st.write('This chatbot uses the Gemini Pro API with RAG capabilities.')
+    st.button('Clear Chat History', on_click=clear_chat_history, type='primary')
+    uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"], help="Upload your PDF file here to start the analysis.")
+    if uploaded_file is not None:
+        st.success("PDF File Uploaded Successfully!")
+        text = extract_text_from_pdf(uploaded_file.read())
+        vectorstore = initialize_vector_index(text)
+        st.session_state.vectorstore = vectorstore
+
+# Main interface
+st.header('Gemini Pro RAG Chatbot')
+st.subheader('Upload a PDF and ask questions about its content!')
+
+# Display the welcome prompt if chat history is only the initial prompt
+if len(st.session_state.chat_history) == 1:
+    with st.chat_message(SPEAKER_TYPES.BOT, avatar="🔍"):
+        st.write(initial_prompt['content'])
+
+# Get user input
+prompt = st.chat_input("Ask a question about the PDF content:", key="user_input")
+
+# Function to get a response from RAG chain
+def get_rag_response(prompt):
+    retriever = st.session_state.vectorstore.as_retriever()  # Use the stored vectorstore retriever
+    rag_chain = (
+        {"context": retriever | format_docs, "question": RunnablePassthrough()}
+        | prompt
+        | llm
+        | StrOutputParser()
+    )
+    response = rag_chain.invoke(prompt)
+    return response
+
+# Handle the user prompt and generate response
+if prompt:
+    # Add user prompt to chat history
+    st.session_state.chat_history.append({'role': SPEAKER_TYPES.USER, 'content': prompt})
+    
+    # Display chat messages from the chat history
+    for message in st.session_state.chat_history[1:]:
+        with st.chat_message(message["role"], avatar="👤" if message['role'] == SPEAKER_TYPES.USER else "🔍"):
+            st.write(message["content"])
+    
+    # Get the response using the RAG chain
+    with st.spinner(text='Generating response...'):
+        response_text = get_rag_response(prompt)
+        st.session_state.chat_history.append({'role': SPEAKER_TYPES.BOT, 'content': response_text})
+    
+    # Display the bot response
+    with st.chat_message(SPEAKER_TYPES.BOT, avatar="🔍"):
+        st.write(response_text)
+
+# Add footer for additional information or credits
+st.markdown("""
+<hr>
+<div style="text-align: center;">
+    <small>Powered by Gemini Pro API | Developed by Christian Thomas BADOLO</small>
+</div>
+""", unsafe_allow_html=True)