Spaces:
Build error
Build error
File size: 2,215 Bytes
3895252 74d77a0 3895252 |
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 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
import os
import streamlit as st
from PyPDF2 import PdfReader
from sentence_transformers import SentenceTransformer
import faiss
import numpy as np
from groq import Groq
# Initialize Groq Client
client = Groq(api_key=os.getenv("groq_api_key"))
# Load embedding model
embedding_model = SentenceTransformer("all-MiniLM-L6-v2")
# Initialize FAISS vector store
dimension = 384 # Embedding dimension of the model
index = faiss.IndexFlatL2(dimension)
# Function to extract text from PDF
def extract_text_from_pdf(pdf_file):
reader = PdfReader(pdf_file)
text = ""
for page in reader.pages:
text += page.extract_text()
return text
# Function to split text into chunks
def chunk_text(text, chunk_size=500):
words = text.split()
return [" ".join(words[i:i+chunk_size]) for i in range(0, len(words), chunk_size)]
# Function to add embeddings to vector database
def add_to_vector_db(chunks):
embeddings = embedding_model.encode(chunks)
index.add(np.array(embeddings, dtype="float32"))
return embeddings
# Streamlit frontend
st.title("RAG-based PDF Query Application")
# PDF upload
uploaded_file = st.file_uploader("Upload your PDF file", type=["pdf"])
if uploaded_file:
st.write("Processing your PDF...")
text = extract_text_from_pdf(uploaded_file)
chunks = chunk_text(text)
add_to_vector_db(chunks)
st.success("PDF processed and embeddings stored in the vector database!")
# Query input
query = st.text_input("Enter your query:")
if query:
# Generate embedding for query
query_embedding = embedding_model.encode([query])
# Retrieve relevant chunks from FAISS
distances, indices = index.search(np.array(query_embedding, dtype="float32"), k=5)
context = "\n".join([chunks[i] for i in indices[0]])
# Interact with Groq API
chat_completion = client.chat.completions.create(
messages=[
{
"role": "user",
"content": f"Context: {context}\n\nQuery: {query}"
}
],
model="llama3-8b-8192",
stream=False,
)
response = chat_completion.choices[0].message.content
# Display response
st.write("Response:")
st.write(response)
|