File size: 4,228 Bytes
030bc4f 4f4392b 030bc4f 29d0fc0 030bc4f 4f4392b 030bc4f 4f4392b 030bc4f 4f4392b 29d0fc0 030bc4f 29d0fc0 030bc4f 29d0fc0 030bc4f 29d0fc0 030bc4f 29d0fc0 030bc4f 29d0fc0 4f4392b 29d0fc0 4f4392b 29d0fc0 4f4392b 29d0fc0 4f4392b |
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 |
import os
import streamlit as st
from typing import List
from dotenv import load_dotenv
from langchain_community.embeddings import OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import FAISS
from langchain_community.document_loaders import PyPDFLoader
from langchain.chains import RetrievalQA
from langchain_openai import ChatOpenAI
from langchain_openai import OpenAIEmbeddings
import tempfile
# Load environment variables
load_dotenv()
# Initialize OpenAI API key
openai_api_key = os.getenv('OPENAI_API_KEY')
# Initialize embedding model using OpenAI
embeddings = OpenAIEmbeddings(openai_api_key=openai_api_key, model="text-embedding-3-small")
# Initialize vector store
vector_store = None
# Store PDF file paths
pdf_files = {}
# Define the path for the FAISS index
FAISS_INDEX_PATH = "faiss_index"
FAISS_INDEX_FILE = os.path.join(FAISS_INDEX_PATH, "index.faiss")
@st.cache_resource
def process_pdf(uploaded_file):
"""Process the uploaded PDF and add it to the vector store."""
global vector_store, pdf_files
# Create a temporary file to store the uploaded PDF
with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
tmp_file.write(uploaded_file.getvalue())
tmp_file_path = tmp_file.name
loader = PyPDFLoader(tmp_file_path)
documents = loader.load()
pdf_files[uploaded_file.name] = tmp_file_path
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
texts = text_splitter.split_documents(documents)
if vector_store is None:
vector_store = FAISS.from_documents(texts, embeddings)
else:
vector_store.add_documents(texts)
# Save the updated vector store
if not os.path.exists(FAISS_INDEX_PATH):
os.makedirs(FAISS_INDEX_PATH)
vector_store.save_local(FAISS_INDEX_PATH)
# Clean up the temporary file
os.unlink(tmp_file_path)
def main():
st.title("PDF Question Answering System")
# File uploader
uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")
if uploaded_file is not None:
process_pdf(uploaded_file)
st.success(f"PDF '{uploaded_file.name}' processed. You can now ask questions!")
# User input
user_question = st.text_input("Ask a question about the PDFs:")
if user_question:
if vector_store is None:
st.error("Error: No PDFs have been uploaded yet.")
return
retriever = vector_store.as_retriever(search_kwargs={"k": 3})
# Initialize the OpenAI language model
llm = ChatOpenAI(openai_api_key=openai_api_key, model="gpt-4o-mini", temperature=0)
qa_chain = RetrievalQA.from_chain_type(
llm=llm,
chain_type="stuff",
retriever=retriever,
return_source_documents=True
)
result = qa_chain(user_question)
answer = result['result']
source_docs = result['source_documents']
st.write("Answer:", answer)
if source_docs:
st.subheader("Sources:")
unique_sources = set()
for doc in source_docs:
file_name = os.path.basename(doc.metadata['source'])
if file_name in pdf_files and file_name not in unique_sources:
unique_sources.add(file_name)
file_path = pdf_files[file_name]
st.write(f"Source: {file_name}")
with open(file_path, "rb") as file:
st.download_button(
label=f"Download {file_name}",
data=file,
file_name=file_name,
mime="application/pdf"
)
other_sources = [doc.metadata['source'] for doc in source_docs if os.path.basename(doc.metadata['source']) not in pdf_files]
unique_other_sources = set(other_sources)
if unique_other_sources:
st.subheader("Other Sources:")
for source in unique_other_sources:
st.write(f"- {source}")
if __name__ == "__main__":
main() |