app.py

import streamlit as st

# Define appliance options
appliance_options = ["Refrigerator", "Dish Washer", "Coffee Maker", "Air Conditioner", 
                     "Washing Machine", "Laptop", "Oven", "TV", "Soundbar", "Vacuum Cleaner", 
                     "Iron", "Mixer", "Food Processor", "Tooth Brush", "Electric Toaster", 
                     "Citrus Press", "Air Dryer", "Juicer", "Heater", "Ceiling Fan"]

# Define brand dictionaries for each appliance (key: appliance name, value: list of brands)
brand_options = {
    "Refrigerator": ["Haier", "Samsung", "Dawlance", "Hitachi", "PEL"],
    "Dish Washer": ["Samsung", "Bosch", "Baumeatic"],
    "Coffee Maker": ["Black & Decker"],
    "Air Conditioner": ["Samsung", "Haier", "GREE"],
    "Washing Machine": ["Samsung", "Haier"],
    "Laptop": ["Haier"],
    "Oven": ["La Vita", "Samsung", "Kenwood", "Haier", "Phillips"],
    "TV": ["Samsung", "Haier", "Hisense", "Phillips", "Google"],
    "Soundbar": ["Samsung", "Phillips"],
    "Vacuum Cleaner": ["Samsung"],
    "Iron": ["Phillips"],
    "Mixer": ["Phillips"],
    "Food Processor": ["Phillips"],
    "Tooth Brush": ["Phillips"],
    "Electric Toaster": ["Phillips"],
    "Citrus Press": ["Phillips"],
    "Air Dryer": ["Phillips"],
    "Juicer": ["Phillips"],
    "Heater": ["Phillips"],
    "Ceiling Fan": ["GFC", "Hunter"]
}

# Get user selections for appliance and brand
selected_appliance = st.selectbox("Select Appliance", appliance_options)
selected_brand = None

if selected_appliance:
    selected_brand = st.selectbox(f"Select Brand for {selected_appliance}", brand_options[selected_appliance])

# Display user selection
if selected_appliance and selected_brand:
    st.write(f"You selected {selected_brand} {selected_appliance}")

    import os
from groq import Groq
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.text_splitter import RecursiveCharacterTextSplitter
from PyPDF2 import PdfReader

from tempfile import NamedTemporaryFile

# Initialize Groq client
client = Groq(api_key="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")

#client = Groq("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")

# Function to extract text from a PDF
def extract_text_from_pdf(pdf_file_path):
    pdf_reader = PdfReader(pdf_file_path)
    text = ""
    for page in pdf_reader.pages:
        text += page.extract_text()
    return text

# Function to split text into chunks
def chunk_text(text, chunk_size=500, chunk_overlap=50):
    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=chunk_size, chunk_overlap=chunk_overlap
    )
    return text_splitter.split_text(text)

# Function to create embeddings and store them in FAISS
def create_embeddings_and_store(chunks):
    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
    vector_db = FAISS.from_texts(chunks, embedding=embeddings)
    return vector_db

# Function to query the vector database and interact with Groq
def query_vector_db(query, vector_db):
    # Retrieve relevant documents
    docs = vector_db.similarity_search(query, k=3)
    context = "\n".join([doc.page_content for doc in docs])

    # Interact with Groq API
    chat_completion = client.chat.completions.create(
        messages=[
            {"role": "system", "content": f"Use the following context:\n{context}"},
            {"role": "user", "content": query},
        ],
        model="llama3-8b-8192",
    )
    return chat_completion.choices[0].message.content

# Streamlit app
st.title("RAG-Based Application")

# Upload PDF
uploaded_file = st.file_uploader("Upload the troubleshooting guide of appliance ", type=["pdf"]) 

if uploaded_file:
    with NamedTemporaryFile(delete=False, suffix=".pdf") as temp_file:
        temp_file.write(uploaded_file.read())
        pdf_path = temp_file.name

    # Extract text
    text = extract_text_from_pdf(pdf_path)
    #st.write("PDF Text Extracted Successfully!")

    # Chunk text
    chunks = chunk_text(text)
    #st.write("Text Chunked Successfully!")

    # Generate embeddings and store in FAISS
    vector_db = create_embeddings_and_store(chunks)
    #st.write("Embeddings Generated and Stored Successfully!")

    # User query input
    user_query = st.text_input("Enter your query:")
    if user_query:
        response = query_vector_db(user_query, vector_db)
        st.write(f"Possible solutions for {selected_brand} {selected_appliance} would be") 
        st.write(response)