File size: 5,200 Bytes
c78f1ff 139f1ef c78f1ff 139f1ef 61ec34a 61c8cc7 139f1ef 61c8cc7 c78f1ff dc6e9a7 139f1ef 2d8b66e 139f1ef 2d8b66e 139f1ef 61ec34a e054530 61ec34a 139f1ef 61ec34a 139f1ef 61ec34a 2d8b66e 61ec34a dc6e9a7 61ec34a 2d8b66e 61ec34a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 |
import os
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_google_genai import GoogleGenerativeAIEmbeddings
import streamlit as st
import google.generativeai as genai
from langchain.vectorstores import FAISS
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.chains.question_answering import load_qa_chain
from langchain.prompts import PromptTemplate
from dotenv import load_dotenv
load_dotenv()
os.getenv("GOOGLE_API_KEY")
genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
DEFAULT_PDF_FILES = ["2024_25_Annex_Budget.pdf", "2024_25_Budget_Speech.pdf"] # Define default PDFs
# read all pdf files and return text
def get_pdf_text(pdf_docs):
text = ""
for pdf in pdf_docs:
pdf_reader = PdfReader(pdf)
for page in pdf_reader.pages:
text += page.extract_text()
return text
# split text into chunks
def get_text_chunks(text):
splitter = RecursiveCharacterTextSplitter(
chunk_size=10000, chunk_overlap=1000)
chunks = splitter.split_text(text)
return chunks # list of strings
# get embeddings for each chunk
def get_vector_store(chunks):
embeddings = GoogleGenerativeAIEmbeddings(
model="models/embedding-001") # type: ignore
vector_store = FAISS.from_texts(chunks, embedding=embeddings)
vector_store.save_local("faiss_index")
def get_conversational_chain():
prompt_template = """
You an economist.Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
Context:\n {context}?\n
Question: \n{question}\n
Answer:
"""
model = ChatGoogleGenerativeAI(model="gemini-1.5-flash",
client=genai,
temperature=0.3,
)
prompt = PromptTemplate(template=prompt_template,
input_variables=["context", "question"])
chain = load_qa_chain(llm=model, chain_type="stuff", prompt=prompt)
return chain
def clear_chat_history():
st.session_state.messages = [
{"role": "assistant", "content": "upload some pdfs and ask me a question"}]
def user_input(user_question):
embeddings = GoogleGenerativeAIEmbeddings(
model="models/embedding-001") # type: ignore
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, )
print(response)
return response
def main():
st.set_page_config(
page_title="Gemini PDF Chatbot",
page_icon="🤖"
)
# Sidebar for uploading PDF files
with st.sidebar:
st.title("Menu:")
pdf_docs = st.file_uploader(
"Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True)
if st.button("Submit & Process"):
with st.spinner("Processing..."):
for file_name in pdf_docs:
if not os.path.exists(file_name):
st.error(f"Default file '{file_name}' not found!")
return # Exit if a default file is missing
raw_text = get_pdf_text(pdf_docs)
text_chunks = get_text_chunks(raw_text)
get_vector_store(text_chunks)
st.success("Done")
# Main content area for displaying chat messages
st.title("Chat with the Budget 2024-2025 using Gemini🤖")
st.write("Welcome to the Budget 2024-2025 chatbot!")
st.sidebar.button('Clear Chat History', on_click=clear_chat_history)
# Chat input
# Placeholder for chat messages
if "messages" not in st.session_state.keys():
st.session_state.messages = [
{"role": "assistant", "content": "upload some pdfs and ask me a question"}]
for message in st.session_state.messages:
with st.chat_message(message["role"]):
st.write(message["content"])
if prompt := st.chat_input():
st.session_state.messages.append({"role": "user", "content": prompt})
with st.chat_message("user"):
st.write(prompt)
# Display chat messages and bot response
if st.session_state.messages[-1]["role"] != "assistant":
with st.chat_message("assistant"):
with st.spinner("Thinking..."):
response = user_input(prompt)
placeholder = st.empty()
full_response = ''
for item in response['output_text']:
full_response += item
placeholder.markdown(full_response)
placeholder.markdown(full_response)
if response is not None:
message = {"role": "assistant", "content": full_response}
st.session_state.messages.append(message)
if __name__ == "__main__":
main() |