Upload 13 files

.env

@@ -0,0 +1 @@
+GOOGLE_API_KEY="AIzaSyCH8lnRWjJe5vABq_uI0yIsXJz9dUhRK2A"

.gitattributes

@@ -1,35 +1,2 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Auto detect text files and perform LF normalization
+* text=auto

app.py

@@ -0,0 +1,46 @@
+import streamlit as st
+from streamlit_option_menu import option_menu
+
+st.set_page_config(
+    page_title="PawSome-AI", 
+    page_icon="🐾", 
+    layout="centered", 
+    initial_sidebar_state="auto"
+)
+
+# Display your logo at the top of the main page
+# Adjust the path to your logo image
+
+# st.header("Welcome to PawSome AI")
+
+with st.sidebar:
+    selected = option_menu(
+        'PawSome AI',
+        ['Welcome', 'Disease & Breed Detection', 'Petcare ChatBot', 'Prescription-Analyzer', 'Team Details', 'Feedback'],
+        icons=['house-door-fill', 'search', 'chat-right-fill', 'file-earmark-break-fill', 'info', 'star'],
+        menu_icon="🐶",
+        default_index=0
+    )
+
+if selected == 'Welcome':
+    import welcome
+    welcome.welcome()
+
+if selected == 'Disease & Breed Detection':
+    import model
+    model.model()
+
+if selected == 'Petcare ChatBot':
+    import chatbot
+    chatbot.chatbot()
+
+if selected == 'Prescription-Analyzer':
+    import prescription
+    prescription.presc_analyze()
+
+if selected == 'Feedback':
+    import feedback
+    feedback.feedback()
+if selected == 'Team Details':
+    import team
+    team.team_details()

chatbot.py

@@ -0,0 +1,111 @@
+def chatbot():
+    # Importing all the modules
+    import streamlit as st
+    from PyPDF2 import PdfReader
+    from langchain.text_splitter import RecursiveCharacterTextSplitter
+    import os
+    from langchain_google_genai import GoogleGenerativeAIEmbeddings
+    import google.generativeai as genai
+    from langchain.vectorstores import FAISS
+    from langchain_google_genai import ChatGoogleGenerativeAI
+    from langchain.chains.question_answering import load_qa_chain
+    from langchain.prompts import PromptTemplate
+    from dotenv import load_dotenv
+    import pyttsx3
+
+    def speak_response(response_content):
+        engine = pyttsx3.init()
+        engine.say(response_content)
+        engine.runAndWait()
+
+    # Load environment variables
+    load_dotenv()
+    api_key = os.getenv("GOOGLE_API_KEY")
+    genai.configure(api_key=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 get_text_chunks(text):
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
+        chunks = text_splitter.split_text(text)
+        return chunks
+
+    def get_vector_store(text_chunks):
+        embedding_function = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+        vector_store = FAISS.from_texts(text_chunks, embedding=embedding_function)
+        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 then go and find and provide the answer don't provide the wrong answer and your a expert in pet-care so make sure all your responses are within that.\n\n
+        Context:\n {context}?\n
+        Question: \n{question}\n
+
+        Answer:
+        """
+        model = ChatGoogleGenerativeAI(model="gemini-1.5-pro-latest", 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)
+        return response["output_text"]
+
+    # Main function for the chatbot
+    st.title("Pet Care ChatBot 🐾")
+    st.subheader("Your AI-Powered Pet Care Assistant")
+    st.markdown("""
+    Welcome to the Pet Care ChatBot! Ask any question related to pet care, and our AI-powered assistant will provide you with detailed and accurate answers.
+    """)
+    voice_response = st.checkbox("Click for Voice Response")
+
+    if "messages" not in st.session_state:
+        st.session_state.messages = []
+
+# Uncomment if you want to add your own-custom pdf:
+    # with st.form(key="uploader_form"):
+    #     pdf_docs = st.file_uploader("Upload your PDF Files", accept_multiple_files=True)
+    #     submit_button = st.form_submit_button(label="Submit & Process")
+    # if submit_button:
+    #     if pdf_docs:
+    #         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("Processing completed successfully.")
+    #     else:
+    #         st.warning("Please upload at least one PDF file.")
+
+    # Display chat messages from history on app rerun
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+
+    # React to user input
+    if prompt := st.chat_input("Ask a question from the PDF files"):
+        # Display user message in chat message container
+        st.chat_message("user").markdown(prompt)
+        # Add user message to chat history
+        st.session_state.messages.append({"role": "user", "content": prompt})
+
+        response = user_input(prompt)
+        # Display assistant response in chat message container
+        with st.chat_message("assistant"):
+            st.markdown(response)
+            if voice_response:
+                speak_response(response)
+
+        # Add assistant response to chat history
+        st.session_state.messages.append({"role": "assistant", "content": response})

feedback.csv

@@ -0,0 +1,3 @@
+name,email,feedback_type,message,timestamp
+Boss,habii,Suggestion,great job guys,2024-06-20 22:26:46.126194
+Boss,habii,Issue,great job guys cool,2024-06-20 22:27:24.377924

feedback.py

@@ -0,0 +1,40 @@
+import streamlit as st
+import pandas as pd
+from datetime import datetime
+
+def feedback():
+    st.title("Feedback")
+    st.write("We value your feedback to help us improve PawSome-AI!")
+
+    # Feedback form
+    with st.form(key='feedback_form'):
+        name = st.text_input("Your Name")
+        email = st.text_input("Your Email")
+        feedback_type = st.selectbox("Type of Feedback", ["Suggestion", "Issue", "Other"])
+        message = st.text_area("Your Feedback")
+        submit_button = st.form_submit_button(label="Submit")
+
+    # After the user clicks the submit button
+    if submit_button:
+        feedback_data = {
+            "name": [name],
+            "email": [email],
+            "feedback_type": [feedback_type],
+            "message": [message],
+            "timestamp": [datetime.now()]
+        }
+        feedback_df = pd.DataFrame(feedback_data)
+
+        # Save the feedback to a CSV file
+        try:
+            existing_feedback_df = pd.read_csv("feedback.csv")
+            feedback_df = pd.concat([existing_feedback_df, feedback_df], ignore_index=True)
+        except FileNotFoundError:
+            pass
+
+        feedback_df.to_csv("feedback.csv", index=False)
+
+        st.success("Thank you for your feedback! We'll get back to you shortly.")
+
+    st.write("If you need immediate assistance, please contact us at: ")
+    st.markdown("[contact.pawsomeai@gmail.com](mailto:contact.pawsomeai@gmail.com)")

model.py

@@ -0,0 +1,96 @@
+def model():
+    # Importing All the modules
+    import streamlit as st
+    import os
+    from PIL import Image
+    import google.generativeai as genai
+    from dotenv import load_dotenv
+
+    # Load all environment Variables
+    load_dotenv()
+
+    # Configuring the api key
+    genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+
+    # Function to load Gemini Vison Pro Vision Model and Get response
+    def get_gemini_response(image, prompt):
+        # Loading the desired Model
+        model = genai.GenerativeModel("gemini-pro-vision")
+        response = model.generate_content([image[0], prompt])
+        return response.text
+
+    # Function to extract data from Image Uploaded
+    def input_image_setup(uploaded_file):
+        # Check if a file has been uploaded
+        if uploaded_file is not None:
+            # Read the file into bytes
+            bytes_data = uploaded_file.getvalue()
+            image_parts = [
+                {
+                    "mime_type": uploaded_file.type,  # Get the mime type of the uploaded file
+                    "data": bytes_data
+                }
+            ]
+            return image_parts
+        else:
+            raise FileNotFoundError("No file uploaded")
+
+    # Initializing our Streamlit Prompt
+    st.title("Pet Image Analyzer")
+    st.write(
+        """
+        Welcome to the Pet Image Analyzer! This tool uses advanced AI technology to analyze images of your pets 
+        and provide insights into their breed, potential health issues, and more. Please upload an image of your pet 
+        to get started.
+        """
+    )
+
+    # File uploader for image input
+    uploaded_file = st.file_uploader("Choose a pet image...", type=["jpg", "jpeg", "png", "webp"])
+    image = None
+
+    if uploaded_file is not None:
+        image = Image.open(uploaded_file)
+        st.image(image, caption="Uploaded Image.", use_column_width=True)
+
+        # Defining a System Prompt (pre-defined)
+        input_prompt = f"""Image: (content of the uploaded image)
+
+        Text: Analyze the image and provide the following information:
+
+        * Breed: Identify the breed of the animal in the image (if possible).
+        * Disease Detection: If the image shows a diseased area, identify the specific disease (if possible).
+        * Severity: If a disease is detected, assess the severity of the disease.
+        * Symptoms: Describe the common symptoms associated with the detected disease.
+        * Precautions: Recommend preventative measures to avoid the disease.
+
+        Give response with headings,
+        Inform the user if the image is not related to pet care.
+        """
+
+        submit = st.button("Analyze Image")
+        Disclaimer = (
+            "**Disclaimer:** This application uses image analysis to provide potential information about your pet's health. "
+            "The results are for informational purposes only and should not be considered a replacement for professional veterinary diagnosis. "
+            "For any concerns about your pet's health, please consult a licensed veterinarian. They can conduct a thorough examination and provide personalized recommendations for your pet's well-being."
+        )
+
+        if submit:
+            if image:
+                with st.spinner("Analyzing Image..."):
+                    image_data = input_image_setup(uploaded_file)
+                    response = get_gemini_response(image_data, input_prompt)
+                st.subheader("Analysis Result:")
+                st.write(response)
+                st.warning(Disclaimer)
+                st.balloons()
+            else:
+                st.error("Please upload an image to proceed.")
+    else:
+        st.info("Upload an image of your pet to get started!")
+        st.write(
+            """
+            To analyze your pet's image, click on the 'Choose a pet image...' button above and select an image file from your device. 
+            Once the image is uploaded, click on 'Analyze Image' to receive detailed information about your pet.
+            """
+        )

mysrap.py

@@ -0,0 +1,83 @@
+import streamlit as st
+import pandas as pd
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+from selenium.webdriver.chrome.options import Options
+from webdriver_manager.chrome import ChromeDriverManager
+import time
+
+def search_medicine_supertails(medicine_name):
+    url = f'https://supertails.com/search?q={medicine_name}&page=1'
+    
+    options = Options()
+    options.headless = True
+    driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=options)
+    
+    try:
+        driver.get(url)
+        time.sleep(5)  # Wait for the page to load completely
+
+        # Get the page source and parse it with BeautifulSoup
+        page_source = driver.page_source
+        soup_obj = BeautifulSoup(page_source, 'html.parser')
+
+        # Find all product elements
+        products = soup_obj.find_all('li', class_='findify-components-common--grid__column findify-components-common--grid__column-3 product-item')
+
+        product_name = []
+        product_price = []
+        product_link = []
+
+        for product in products:
+            # Find the first <a> tag directly after the <li> tag
+            link_tag = product.find_next('a', href=True)
+            if link_tag:
+                product_link.append('https://supertails.com' + link_tag['href'])
+            else:
+                product_link.append('N/A')  # Append placeholder if link is missing
+
+            name_tag = product.find('h2', class_='findify-components--cards--product__title')
+            if name_tag:
+                product_name.append(name_tag.text.strip())
+            else:
+                product_name.append('N/A')  # Append placeholder if name is missing
+
+            price_tag = product.find('div', class_='findify-components--cards--product--price__price findify-components--cards--product--price__sale-price')
+            if price_tag:
+                product_price.append(price_tag.text.strip())
+            else:
+                product_price.append('N/A')  # Append placeholder if price is missing
+
+        df = pd.DataFrame({
+            'Product Name': product_name,
+            'Price': product_price,
+            'Link': product_link
+        })
+
+        return df
+
+    except Exception as e:
+        st.error(f'Error occurred: {e}')
+        return None
+    finally:
+        driver.quit()
+
+def main():
+    st.title('Medicine Finder')
+
+    # Input field for medicine name
+    medicine_name = st.text_input('Enter the name of the medicine:')
+
+    if st.button('Search'):
+        # Call the scraper function
+        results_df = search_medicine_supertails(medicine_name)
+
+        # Display results
+        if results_df is not None and not results_df.empty:
+            st.dataframe(results_df)
+        elif results_df is not None:
+            st.write("No results found")
+            
+if __name__ == '__main__':
+    main()

prescription.py

@@ -0,0 +1,106 @@
+import streamlit as st
+import os
+from PIL import Image
+import google.generativeai as genai
+from dotenv import load_dotenv
+from mysrap import search_medicine_supertails
+from google.generativeai.types import HarmCategory, HarmBlockThreshold
+
+def presc_analyze():
+    # Load environment variables
+    load_dotenv()
+
+    # Configure the API key
+    genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+
+    # Function to load Gemini Vision Pro model and get response
+    def get_gemini_response(input_prompt, image_data, user_prompt):
+        # model = genai.GenerativeModel("gemini-pro-vision")
+        safety_settings={
+        HarmCategory.HARM_CATEGORY_HATE_SPEECH: HarmBlockThreshold.BLOCK_LOW_AND_ABOVE,
+        HarmCategory.HARM_CATEGORY_HARASSMENT: HarmBlockThreshold.BLOCK_LOW_AND_ABOVE,
+        # HarmCategory.HARM_CATEGORY_DANGEROUS: HarmBlockThreshold.BLOCK_LOW_AND_ABOVE,
+        HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: HarmBlockThreshold.BLOCK_NONE,
+    }
+        model = genai.GenerativeModel("gemini-pro-vision",safety_settings=safety_settings)
+        response = model.generate_content([input_prompt, image_data[0], user_prompt])
+        return response.text
+
+    # Function to extract data from uploaded image
+    def input_image_setup(uploaded_file):
+        if uploaded_file is not None:
+            bytes_data = uploaded_file.getvalue()
+            image_parts = [
+                {
+                    "mime_type": uploaded_file.type,
+                    "data": bytes_data,
+                }
+            ]
+            return image_parts
+        else:
+            raise FileNotFoundError("No file uploaded")
+
+    def extract_medicine_names_heuristic(text):
+        import re
+        # Split based on common delimiters, numbers, or new lines
+        potential_medicines = re.split(r'\d+\.\s*|\n|\r|,', text)
+        # Clean up and filter out non-medicines
+        potential_medicines = [med.strip() for med in potential_medicines if med.strip() and med.lower() not in ["the", "to", "of", "and", "is"]]
+        return potential_medicines
+
+    # Streamlit app configuration
+    # st.set_page_config(page_title="Prescription & Medicine Information Extractor")
+    st.header("Prescription & Medicine Information Extractor")
+
+    user_prompt = "Give me the details about the Prescription and along with basic personal details and tell about medications and frequency in a proper tabular form"
+    uploaded_file = st.file_uploader("Choose a Prescription Image...", type=["jpg", "jpeg", "png"])
+    image = ""
+    if uploaded_file is not None:
+        image = Image.open(uploaded_file)
+        st.image(image, caption="Uploaded Image", use_column_width=True)
+
+    submit = st.button("Extract Information")
+
+    # System prompt for understanding prescriptions
+    info_prompt = """You are an expert in understanding prescriptions. 
+    You will receive prescription images and answer questions based on them. 
+    Please consider the following information: {user_prompt}"""
+
+    # System prompt for extracting medicine names (heuristic)
+    medicine_prompt = "Please list all the medications mentioned in the prescription.Make sure that you just give medicine name with strength."
+
+    if submit:
+        image_data = input_image_setup(uploaded_file)
+
+        # Extract information based on user prompt
+        info_response = get_gemini_response(info_prompt.format(user_prompt=user_prompt), image_data, "")
+        st.subheader("Extracted Information:")
+        st.write(info_response)
+
+        # Extract medicine names using a separate query
+        medicine_response = get_gemini_response(medicine_prompt, image_data, "")
+        medicine_names = extract_medicine_names_heuristic(medicine_response)
+
+        if medicine_names:
+            st.subheader("Medicine Names:")
+            # Store medicine names in a list
+            medicine_list = ", ".join(medicine_names)
+            st.write(medicine_list)
+
+            # Display at least 6-7 medicines with clickable links for each extracted medicine name
+            st.subheader("Medicines with Links:")
+            for medicine in medicine_names:
+                st.markdown(f"### {medicine}")
+                results_df = search_medicine_supertails(medicine)
+                if results_df is not None and not results_df.empty:
+                    for index, row in results_df.head(7).iterrows():
+                        st.markdown(f"[{row['Product Name']}]({row['Link']}) - {row['Price']} ₹")
+                else:
+                    st.write(f"No results found for {medicine}")
+        else:
+            st.write("No medicine names found using the heuristic approach.")
+
+        st.balloons()
+
+if __name__ == '__main__':
+    presc_analyze()

requirements.txt

@@ -0,0 +1,17 @@
+streamlit
+streamlit-option-menu
+google-generativeai
+python-dotenv
+langchain
+PyPDF2
+chromadb
+faiss-cpu
+langchain_google_genai
+streamlit
+pandas
+beautifulsoup4
+selenium
+webdriver-manager
+pyttsx3
+langchain-community
+requests

team.py

@@ -0,0 +1,47 @@
+import streamlit as st
+import webbrowser
+
+def team_details():
+    st.title("Our Team")
+
+    team_members = [
+        {
+            "name": "Mohammadi Shifa",
+            "role": "Lead Developer",
+            "description": "Shifa is passionate about building innovative solutions and has a strong background in web development and AI.",
+            "gmail": "shifamohammadi07@gmail.com",
+            "usn": "USN: A1234567"
+        },
+        {
+            "name": "Harsha",
+            "role": "Data Scientist",
+            "description": "Harsha specializes in machine learning algorithms and data analysis. She enjoys tackling complex problems.",
+            "gmail": "harshasmith@gmail.com",
+            "usn": "USN: B2345678"
+        },
+        {
+            "name": "Kishitj",
+            "role": "UI/UX Designer",
+            "description": "Kishitj brings creativity to our team with a focus on user experience and interface design.",
+            "gmail": "kishitj@gmail.com",
+            "usn": "USN: C3456789"
+        },
+        {
+            "name": "Emily Brown",
+            "role": "Marketing Specialist",
+            "description": "Emily excels in digital marketing strategies and customer engagement, ensuring our app reaches a wide audience.",
+            "gmail": "emilybrown@gmail.com",
+            "usn": "USN: D4567890"
+        }
+    ]
+
+    for member in team_members:
+        st.header(member["name"])
+        st.subheader(member["role"])
+        st.write(member["description"])
+        st.write(member["usn"])
+        if st.button(f"Contact {member['name']} via Gmail"):
+            webbrowser.open_new_tab(f"mailto:{member['gmail']}?subject=Regarding%20PawSome-AI%20App")
+
+if __name__ == "__main__":
+    team_details()

welcome.py

@@ -0,0 +1,61 @@
+import streamlit as st
+
+def welcome():
+    # Logo and main heading
+    st.image("logo-hd.png", width=200)
+    st.title("Welcome to PawSome-AI 🐾")
+    st.write("Your AI-Powered Pet Care Assistant")
+    st.markdown("---")  # Horizontal line
+
+    # Main layout with two columns
+    col1, col2 = st.columns(2)
+
+    # Key Features section centered (Column 1)
+    with col1:
+        st.markdown("""
+        <div style="background-color:#e5f7fa; padding:20px; border-radius:10px; text-align:center;">
+        <h3 style="color:#007a87;">Key Features</h3>
+        <p style="color:#333333;">Explore the capabilities that PawSome-AI offers to enhance your pet care experience:</p>
+        <ul style="text-align:left;">
+        <li><strong>Dog Breed Identification and Disease Detection</strong><br>
+        Upload images to identify your dog's breed and detect diseases. Get detailed information on symptoms, precautions, and treatments.</li><br>
+
+        <li><strong>Pet Care Chatbot</strong><br>
+        Interactive chatbot for pet-care-related queries and advice. Receive personalized recommendations on nutrition, grooming, behavior, and more.</li><br>
+        </ul>
+        </div>
+        """, unsafe_allow_html=True)
+
+    # Additional Key Features (Column 2)
+    with col2:
+        st.markdown("""
+        <div style="background-color:#e5f7fa; padding:20px; border-radius:10px;">
+        <h3 style="color:#007a87;">Additional Key Features</h3>
+        <ul style="text-align:left;">
+        <li><strong>Prescription Analyzer</strong><br>
+         Upload veterinary prescriptions to manage your pet's medications effectively
+         Get detailed information about medications listed in the prescription. 
+         <br>
+                  
+         
+        <li><strong>Contact and Feedback</strong><br>
+        Contact form for inquiries and feedback collection. Reach out to us for any questions or suggestions.</li><br>
+
+        <li><strong>Future Features</strong><br>
+        Planned enhancements to further assist pet owners. Suggestions are welcomed. </li><br>
+        </ul>
+        </div>
+        """, unsafe_allow_html=True)
+
+    # How to Use section centered (Spanning both columns)
+    st.markdown("""
+    <div style="background-color:#f9f9f9; padding:20px; border-radius:10px; text-align:center;">
+    <h3 style="color:#4d4d4d;">How to Use</h3>
+    <ul style="text-align:left;">
+    <li>Navigate through the app using the sidebar menu on the left.</li>
+    <li>Upload an image to detect dog breeds and diseases.</li>
+    <li>Interact with the chatbot for personalized pet care advice.</li>
+    <li>Use the Prescription Analyzer to manage your pet's medications.</li>
+    </ul>
+    </div>
+    """, unsafe_allow_html=True)