app.py

import os
import streamlit as st
import PyPDF2
from sentence_transformers import SentenceTransformer
import faiss
from groq import Groq

# Initialize Groq client
client = Groq(api_key=os.environ.get("GROQ_API_KEY"))

# Load embedding model
embedding_model = SentenceTransformer('all-MiniLM-L6-v2')

# Initialize FAISS Index
dimension = 384  # Dimension of embeddings
index = faiss.IndexFlatL2(dimension)

# Streamlit App
st.title("RAG Application with Groq and FAISS")

# PDF Upload
uploaded_file = st.file_uploader("Upload a PDF Document", type=["pdf"])
if uploaded_file:
    # Extract text from PDF
    pdf_reader = PyPDF2.PdfReader(uploaded_file)
    text = ""
    for page in pdf_reader.pages:
        text += page.extract_text()

    # Split text into chunks
    chunks = [text[i:i+500] for i in range(0, len(text), 500)]
    st.write(f"Document split into {len(chunks)} chunks.")

    # Generate embeddings and store in FAISS
    embeddings = embedding_model.encode(chunks)
    index.add(embeddings)
    st.success("Embeddings created and stored in FAISS.")

    # Query and Response
    user_query = st.text_input("Enter your query:")
    if user_query:
        query_embedding = embedding_model.encode([user_query])
        _, indices = index.search(query_embedding, k=1)
        retrieved_chunk = chunks[indices[0][0]]
        
        # Use Groq API for completion
        chat_completion = client.chat.completions.create(
            messages=[{"role": "user", "content": retrieved_chunk}],
            model="llama3-8b-8192",
        )
        response = chat_completion.choices[0].message.content
        st.write("**Response:**")
        st.write(response)