File size: 3,578 Bytes
3342df5 bf9af3e 73fe663 3342df5 |
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 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 |
import os
import requests
from io import BytesIO
from PyPDF2 import PdfReader
from tempfile import NamedTemporaryFile
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from groq import Groq
import streamlit as st
# Initialize Groq client
GROQ_API_KEY= os.environ.get('GroqApi')
client = Groq(api_key=GROQ_API_KEY)
# if client:
# st.write(f"API KEY FOUND!!!{client}")
# else:
# st.write("API KEY NOT FOUND")
# Predefined list of Google Drive links
drive_links = [
"https://drive.google.com/file/d/1JPf0XvDhn8QoDOlZDrxCOpu4WzKFESNz/view?usp=sharing"
]
# Function to download PDF from Google Drive
def download_pdf_from_drive(drive_link):
file_id = drive_link.split('/d/')[1].split('/')[0]
download_url = f"https://drive.google.com/uc?id={file_id}&export=download"
response = requests.get(download_url)
if response.status_code == 200:
return BytesIO(response.content)
else:
raise Exception("Failed to download the PDF file from Google Drive.")
# Function to extract text from a PDF
def extract_text_from_pdf(pdf_stream):
pdf_reader = PdfReader(pdf_stream)
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 ChatBot (Already having Document)")
st.write("Processing the Data links...")
all_chunks = []
# Process each predefined Google Drive link
for link in drive_links:
try:
# st.write(f"Processing link: {link}")
# Download PDF
pdf_stream = download_pdf_from_drive(link)
# st.write("PDF Downloaded Successfully!")
# Extract text
text = extract_text_from_pdf(pdf_stream)
# st.write("PDF Text Extracted Successfully!")
# Chunk text
chunks = chunk_text(text)
# st.write(f"Created {len(chunks)} text chunks.")
all_chunks.extend(chunks)
except Exception as e:
st.write(f"Error processing link {link}: {e}")
if all_chunks:
# Generate embeddings and store in FAISS
vector_db = create_embeddings_and_store(all_chunks)
st.write("Data is Ready 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)
|