Spaces:
Sleeping
Sleeping
File size: 2,669 Bytes
bc0ffe5 43089b4 bc0ffe5 |
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 77 78 79 |
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
import streamlit as st
from tempfile import NamedTemporaryFile
# Initialize Groq client
client = Groq(api_key="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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 a PDF document", type=["pdf"], accept_multiple_files=True)
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("Response from LLM:")
st.write(response)
|