File size: 2,970 Bytes
3477355 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 | import streamlit as st
from pypdf import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_google_genai import GoogleGenerativeAIEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.chains.question_answering import load_qa_chain
import google.generativeai as genai
# Configure Gemini API
api_key = st.secrets["GOOGLE_API_KEY"]
genai.configure(api_key=api_key)
# Streamlit page config
st.set_page_config(page_title="PDF RAG Chatbot")
st.header("📄 Chat with PDF using Gemini AI")
# Extract text from PDFs
def get_pdf_text(pdf_docs):
text = ""
for pdf in pdf_docs:
pdf_reader = PdfReader(pdf)
for page in pdf_reader.pages:
extracted = page.extract_text()
if extracted:
text += extracted
return text
# Split text into chunks
def get_text_chunks(text):
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=1000,
chunk_overlap=200
)
chunks = text_splitter.split_text(text)
return chunks
# Create vector store
def get_vector_store(text_chunks):
embeddings = GoogleGenerativeAIEmbeddings(
model="models/embedding-001",
google_api_key=api_key
)
vector_store = FAISS.from_texts(
text_chunks,
embedding=embeddings
)
vector_store.save_local("faiss_index")
# Create QA chain
def get_conversational_chain():
model = ChatGoogleGenerativeAI(
model="gemini-1.5-flash",
temperature=0.3,
google_api_key=api_key
)
chain = load_qa_chain(
model,
chain_type="stuff"
)
return chain
# Handle user question
def user_input(user_question):
embeddings = GoogleGenerativeAIEmbeddings(
model="models/embedding-001",
google_api_key=api_key
)
new_db = FAISS.load_local(
"faiss_index",
embeddings,
allow_dangerous_deserialization=True
)
docs = new_db.similarity_search(user_question)
chain = get_conversational_chain()
response = chain(
{
"input_documents": docs,
"question": user_question
},
return_only_outputs=True
)
st.subheader("🤖 Answer")
st.write(response["output_text"])
# Sidebar for PDF upload
with st.sidebar:
st.title("📚 Upload Your PDF Files")
pdf_docs = st.file_uploader(
"Upload PDF Files",
accept_multiple_files=True
)
if st.button("Submit & Process"):
with st.spinner("Processing PDFs..."):
raw_text = get_pdf_text(pdf_docs)
text_chunks = get_text_chunks(raw_text)
get_vector_store(text_chunks)
st.success("PDF Processing Complete!")
# User question input
user_question = st.text_input(
"Ask a Question from the Uploaded PDF Files"
)
if user_question:
user_input(user_question)
|