File size: 2,062 Bytes
b22814b 798069a b22814b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
import os
import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from groq import Groq
# Set up Groq client
client = Groq(
api_key="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")
# Streamlit app
st.title("RAG-based PDF QA Application")
# Step 1: Upload PDF document
uploaded_file = st.file_uploader("Upload a PDF document", type="pdf")
if uploaded_file:
# Step 2: Extract text from PDF
pdf_reader = PdfReader(uploaded_file)
text = "\n".join(page.extract_text() for page in pdf_reader.pages if page.extract_text())
# Step 3: Split text into chunks
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=1000, chunk_overlap=200
)
chunks = text_splitter.split_text(text)
# Step 4: Generate embeddings
st.text("Generating embeddings...")
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
vector_db = FAISS.from_texts(chunks, embeddings)
st.success("Embeddings generated and stored in vector database.")
# Step 5: User interaction
query = st.text_input("Ask a question based on the uploaded document:")
if query:
# Retrieve relevant chunks from vector DB
docs = vector_db.similarity_search(query, k=3)
context = "\n".join(doc.page_content for doc in docs)
# Use Groq API for response generation
chat_completion = client.chat.completions.create(
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": query},
{"role": "assistant", "content": context},
],
model="llama3-8b-8192",
stream=False,
)
answer = chat_completion.choices[0].message.content
st.text_area("Answer:", value=answer, height=200)
# Footer
st.caption("Powered by Open Source Models and Groq API.")
|