Update app.py

app.py

@@ -10,142 +10,149 @@ import os
 import google.generativeai as genai
 from dotenv import load_dotenv
 
-load_dotenv() # Load all env variables 
+# Load environment variables
+load_dotenv()
 genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
 
 
-def get_pdf_text(pdf_docs):
-    text=""
-    for pdf in pdf_docs:
-        pdf_reader= PdfReader(pdf)
-        for page in pdf_reader.pages:
-            text+= page.extract_text()
-    return  text
+def process_pdfs(pdf_files):
+  """
+  Extracts text from uploaded PDFs and splits them into chunks.
+  """
+  text = ""
+  for pdf in pdf_files:
+    reader = PdfReader(pdf)
+    for page in reader.pages:
+      text += page.extract_text()
+  return get_text_chunks(text)
 
 
 def get_text_chunks(text):
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
-    chunks = text_splitter.split_text(text)
-    return chunks
+  """
+  Splits the text into manageable chunks for processing.
+  """
+  splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
+  return splitter.split_text(text)
+
+
+def create_vector_store(text_chunks):
+  """
+  Creates a vector store for efficient text retrieval.
+  """
+  embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+  return FAISS.from_texts(text_chunks, embedding=embeddings).save_local("faiss_index")
+
+
+def build_qa_chain():
+  """
+  Defines the prompt template and loads the question-answering chain.
+  """
+  prompt_template = """
+  Answer the question in detail, considering the provided context. 
+  If the answer is not available, state "answer unavailable".\n\n
+  Context: {context}?\n
+  Question: {question}\n
+
+  Answer:
+  """
+  model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3)
+  prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
+  return load_qa_chain(model, chain_type="stuff", prompt=prompt)
+
+
+def answer_question(question, embeddings, vector_store):
+  """
+  Searches the vector store and retrieves relevant documents for answering.
+  """
+  docs = vector_store.similarity_search(question)
+  qa_chain = get_conversational_chain()
+  response = qa_chain({"input_documents": docs, "question": question}, return_only_outputs=True)
+  return response["output_text"]
+
+
+def get_gemini_response(input_text, image=None):
+  """
+  Generates a response using the Gemini Pro model, potentially with an image.
+  """
+  model = genai.GenerativeModel("gemini-pro-vision")
+  if image is not None and model.is_image_model:
+    response = model.generate_content([input_text, image])
+  else:
+    response = model.generate_content(input_text)
+  return response.text
+
+
+def pdf_chat_app():
+  """
+  Handles the PDF chat functionality.
+  """
+  st.header("PDF Chat Application")
+  user_question = st.text_input("Ask a Question from the PDF Files")
+  uploaded_files = st.file_uploader("Upload PDF Files", accept_multiple_files=True)
+
+  if uploaded_files:
+    with st.spinner("Processing..."):
+      text_chunks = process_pdfs(uploaded_files)
+      create_vector_store(text_chunks)
+      embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+      vector_store = FAISS.load_local("faiss_index", embeddings)
+      st.success("Done!")
+
+  if user_question and uploaded_files:
+    answer = answer_question(user_question, embeddings, vector_store)
+    st.write("Reply:", answer)
+
+def image_chat_app():
+  """
+  Handles the image chat functionality.
+  """
+  st.header("Image Chat Application")
+  input_text = st.text_input("Input for Gemini Pro:")
+  uploaded_image = st.file_uploader("Choose an image...", type="jpg")
+  if uploaded_image is not None:
+    image = Image.open(uploaded_image)
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+
+  submit_gemini = st.button("Ask Gemini Pro")
+
+  if submit_gemini:
+    response_gemini = get_gemini_response(input_text, image)
+    st.subheader("Gemini Pro Response:")
+    st.write(response_gemini)
+
+
+def qa_chat_app():
+  """
+  Handles the Q&A chat functionality.
+  """
+  st.header("Q&A Chat Application")
+  # Initialize session state for chat history if it doesn't exist
+  if 'chat_history' not in st.session_state:
+    st.session_state['chat_history'] = []
+
+  input_qa = st.text_area("Input for Q&A:", key="input_qa")
+  submit_qa = st.button("Ask the question")
+
+  if submit_qa and input_qa:
+    response_qa = get_gemini_response(input_qa)
+    # Add user query and response to session state chat history
+    st.session_state['chat_history'].append(("You", input_qa))
+    st.subheader("Q&A Response:")
+    for chunk in response_qa:
+      st.write(chunk.text)
+    st.session_state['chat_history'].append(("Gemini Pro", chunk.text))
+
+  st.subheader("Q&A Chat History:")
+  for role, text in st.session_state['chat_history']:
+    st.write(f"{role}: {text}")
 
 
-def get_vector_store(text_chunks):
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
-    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
-    vector_store.save_local("faiss_index")
-
-
-def get_conversational_chain():
-    prompt_template = """
-    Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
-    provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
-    Context:\n {context}?\n
-    Question: \n{question}\n
-
-    Answer:
-    """
-
-    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3)
-    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
-    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
-
-    return chain
-
-
-def user_input(user_question):
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
-    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
-    docs = new_db.similarity_search(user_question)
-    chain = get_conversational_chain()
-    response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
-    st.write("Reply: ", response["output_text"])
-
-
-## function to load Gemini Pro model and get responses
-model = genai.GenerativeModel("gemini-pro-vision")
-def get_gemini_response(input, image=None):
-    if image is not None and model.is_image_model:
-        response = model.generate_content([input, image])
-    else:
-        response = model.generate_content(input)
-    return response.text
-
-
-## Initialize our Streamlit app
-
-st.set_page_config(page_title='Combined Streamlit Application')
-st.header("Streamlit Application")
-
-# Define the different applications
-applications = {
-    "PDF Chat": "pdf_chat",
-    "Image Chat": "image_chat",
-    "Q&A Chat": "qa_chat"
-}
-
-# Render the dropdown menu
-selected_app = st.sidebar.selectbox("Select Application", list(applications.keys()))
-
-# Function to display PDF Chat application
-def pdf_chat():
-    st.header("PDF Chat Application")
-    user_question = st.text_input("Ask a Question from the PDF Files")
-    if user_question:
-        user_input(user_question)
-
-    pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True)
-    if st.button("Submit & Process"):
-        with st.spinner("Processing..."):
-            raw_text = get_pdf_text(pdf_docs)
-            text_chunks = get_text_chunks(raw_text)
-            get_vector_store(text_chunks)
-            st.success("Done")
-
-# Function to display Image Chat application
-def image_chat():
-    st.header("Image Chat Application")
-    input_text = st.text_input("Input for Gemini Pro:", key="input_gemini")
-    uploaded_file = st.file_uploader("Choose an image...", type="jpg")
-    if uploaded_file is not None:
-        image = Image.open(uploaded_file)
-        st.image(image, caption="Uploaded Image", use_column_width=True)
-
-    submit_gemini = st.button("Ask Gemini Pro")
-
-    if submit_gemini:
-        response_gemini = get_gemini_response(input_text, image)
-        st.subheader("Gemini Pro Response:")
-        st.write(response_gemini)
-
-# Function to display Q&A Chat application
-def qa_chat():
-    st.header("Q&A Chat Application")
-    # Initialize session state for chat history if it doesn't exist
-    if 'chat_history' not in st.session_state:
-        st.session_state['chat_history'] = []
-
-    input_qa = st.text_area("Input for Q&A:", key="input_qa")
-    submit_qa = st.button("Ask the question")
-
-    if submit_qa and input_qa:
-        response_qa = get_gemini_response(input_qa)
-        # Add user query and response to session state chat history
-        st.session_state['chat_history'].append(("You", input_qa))
-        st.subheader("Q&A Response:")
-        for chunk in response_qa:
-            st.write(chunk.text)
-            st.session_state['chat_history'].append(("Gemini Pro", chunk.text))
-
-    st.subheader("Q&A Chat History:")
-    for role, text in st.session_state['chat_history']:
-        st.write(f"{role}: {text}")
-
 # Map selected application to corresponding function
 selected_app_func = {
-    "PDF Chat": pdf_chat,
-    "Image Chat": image_chat,
-    "Q&A Chat": qa_chat
+  "PDF Chat": pdf_chat,
+  "Image Chat": image_chat,
+  "Q&A Chat": qa_chat
 }
 
 # Run the selected application function
-selected_app_func[selected_app]()
+selected_app_func[selected_app]()