Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
from dotenv import load_dotenv
|
| 3 |
+
import pickle
|
| 4 |
+
from PyPDF2 import PdfReader
|
| 5 |
+
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
| 6 |
+
from langchain.embeddings.openai import OpenAIEmbeddings
|
| 7 |
+
from langchain.vectorstores import FAISS
|
| 8 |
+
from langchain.llms import OpenAI
|
| 9 |
+
from langchain.chains.question_answering import load_qa_chain
|
| 10 |
+
from langchain.callbacks import get_openai_callback
|
| 11 |
+
import os
|
| 12 |
+
|
| 13 |
+
load_dotenv()
|
| 14 |
+
|
| 15 |
+
def main():
|
| 16 |
+
st.header("LLM-powered PDF Chatbot 💬")
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
# upload a PDF file
|
| 20 |
+
pdf = st.file_uploader("Upload your PDF", type='pdf')
|
| 21 |
+
|
| 22 |
+
# st.write(pdf)
|
| 23 |
+
if pdf is not None:
|
| 24 |
+
pdf_reader = PdfReader(pdf)
|
| 25 |
+
|
| 26 |
+
text = ""
|
| 27 |
+
for page in pdf_reader.pages:
|
| 28 |
+
text += page.extract_text()
|
| 29 |
+
|
| 30 |
+
text_splitter = RecursiveCharacterTextSplitter(
|
| 31 |
+
chunk_size=1000,
|
| 32 |
+
chunk_overlap=200,
|
| 33 |
+
length_function=len
|
| 34 |
+
)
|
| 35 |
+
chunks = text_splitter.split_text(text=text)
|
| 36 |
+
|
| 37 |
+
# # embeddings
|
| 38 |
+
store_name = pdf.name[:-4]
|
| 39 |
+
st.write(f'{store_name}')
|
| 40 |
+
# st.write(chunks)
|
| 41 |
+
|
| 42 |
+
if os.path.exists(f"{store_name}.pkl"):
|
| 43 |
+
with open(f"{store_name}.pkl", "rb") as f:
|
| 44 |
+
VectorStore = pickle.load(f)
|
| 45 |
+
# st.write('Embeddings Loaded from the Disk')s
|
| 46 |
+
else:
|
| 47 |
+
embeddings = OpenAIEmbeddings()
|
| 48 |
+
VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
|
| 49 |
+
with open(f"{store_name}.pkl", "wb") as f:
|
| 50 |
+
pickle.dump(VectorStore, f)
|
| 51 |
+
|
| 52 |
+
# embeddings = OpenAIEmbeddings()
|
| 53 |
+
# VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
|
| 54 |
+
|
| 55 |
+
# Accept user questions/query
|
| 56 |
+
query = st.text_input("Ask questions about your PDF file:")
|
| 57 |
+
# st.write(query)
|
| 58 |
+
|
| 59 |
+
if query:
|
| 60 |
+
docs = VectorStore.similarity_search(query=query, k=3)
|
| 61 |
+
|
| 62 |
+
llm = OpenAI()
|
| 63 |
+
chain = load_qa_chain(llm=llm, chain_type="stuff")
|
| 64 |
+
with get_openai_callback() as cb:
|
| 65 |
+
response = chain.run(input_documents=docs, question=query)
|
| 66 |
+
print(cb)
|
| 67 |
+
st.write(response)
|
| 68 |
+
|
| 69 |
+
if __name__ == '__main__':
|
| 70 |
+
main()
|
| 71 |
+
|
| 72 |
+
def set_bg_from_url(url, opacity=1):
|
| 73 |
+
|
| 74 |
+
footer = """
|
| 75 |
+
<link href="https://cdn.jsdelivr.net/npm/bootstrap@5.2.0/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha384-gH2yIJqKdNHPEq0n4Mqa/HGKIhSkIHeL5AyhkYV8i59U5AR6csBvApHHNl/vI1Bx" crossorigin="anonymous">
|
| 76 |
+
<footer>
|
| 77 |
+
<div style='visibility: visible;margin-top:7rem;justify-content:center;display:flex;'>
|
| 78 |
+
<p style="font-size:1.1rem;">
|
| 79 |
+
Made by Mohamed Shaad
|
| 80 |
+
|
| 81 |
+
<a href="https://www.linkedin.com/in/mohamedshaad">
|
| 82 |
+
<svg xmlns="http://www.w3.org/2000/svg" width="23" height="23" fill="white" class="bi bi-linkedin" viewBox="0 0 16 16">
|
| 83 |
+
<path d="M0 1.146C0 .513.526 0 1.175 0h13.65C15.474 0 16 .513 16 1.146v13.708c0 .633-.526 1.146-1.175 1.146H1.175C.526 16 0 15.487 0 14.854V1.146zm4.943 12.248V6.169H2.542v7.225h2.401zm-1.2-8.212c.837 0 1.358-.554 1.358-1.248-.015-.709-.52-1.248-1.342-1.248-.822 0-1.359.54-1.359 1.248 0 .694.521 1.248 1.327 1.248h.016zm4.908 8.212V9.359c0-.216.016-.432.08-.586.173-.431.568-.878 1.232-.878.869 0 1.216.662 1.216 1.634v3.865h2.401V9.25c0-2.22-1.184-3.252-2.764-3.252-1.274 0-1.845.7-2.165 1.193v.025h-.016a5.54 5.54 0 0 1 .016-.025V6.169h-2.4c.03.678 0 7.225 0 7.225h2.4z"/>
|
| 84 |
+
</svg>
|
| 85 |
+
</a>
|
| 86 |
+
|
| 87 |
+
<a href="https://github.com/shaadclt">
|
| 88 |
+
<svg xmlns="http://www.w3.org/2000/svg" width="23" height="23" fill="white" class="bi bi-github" viewBox="0 0 16 16">
|
| 89 |
+
<path d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.012 8.012 0 0 0 16 8c0-4.42-3.58-8-8-8z"/>
|
| 90 |
+
</svg>
|
| 91 |
+
</a>
|
| 92 |
+
</p>
|
| 93 |
+
</div>
|
| 94 |
+
</footer>
|
| 95 |
+
"""
|
| 96 |
+
st.markdown(footer, unsafe_allow_html=True)
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
# Set background image using HTML and CSS
|
| 100 |
+
st.markdown(
|
| 101 |
+
f"""
|
| 102 |
+
<style>
|
| 103 |
+
body {{
|
| 104 |
+
background: url('{url}') no-repeat center center fixed;
|
| 105 |
+
background-size: cover;
|
| 106 |
+
opacity: {opacity};
|
| 107 |
+
}}
|
| 108 |
+
</style>
|
| 109 |
+
""",
|
| 110 |
+
unsafe_allow_html=True
|
| 111 |
+
)
|
| 112 |
+
|
| 113 |
+
# Set background image from URL
|
| 114 |
+
set_bg_from_url("https://www.1access.com/wp-content/uploads/2019/10/GettyImages-1180389186.jpg", opacity=0.875)
|