Spaces:
Sleeping
Sleeping
File size: 3,618 Bytes
1c7a288 e6bfac3 24ba781 2f15a0b 6648f74 2f15a0b e6bfac3 24ba781 2f15a0b 24ba781 |
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 |
import streamlit as st
from langchain_community.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.chains import ConversationalRetrievalChain
from langchain.llms import HuggingFaceHub
from langchain.memory import ConversationBufferMemory
import os
# App title and color theme
st.set_page_config(page_title="📘 PDF Q&A Agent", layout="centered", page_icon="📘")
st.markdown(
\"\"\"
<div style="background-color:#E3E8FF;padding:10px;border-radius:10px">
<h2 style="color:#3C3C88;text-align:center">📘 Student PDF Assistant</h2>
<p style="color:#444;text-align:center">Ask questions from your uploaded PDF and generate Q&A for chapters!</p>
</div>
\"\"\", unsafe_allow_html=True
)
# Upload PDF
uploaded_file = st.file_uploader("📎 Upload your PDF file", type=["pdf"])
if uploaded_file:
# Save PDF temporarily
with open("uploaded.pdf", "wb") as f:
f.write(uploaded_file.read())
st.success("✅ PDF uploaded successfully!")
# Load and split PDF
loader = PyPDFLoader("uploaded.pdf")
pages = loader.load_and_split()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=800, chunk_overlap=150)
chunks = text_splitter.split_documents(pages)
# Embedding
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
vectordb = FAISS.from_documents(chunks, embeddings)
# Load Open Source LLM from Hugging Face (Mistral or any lightweight LLM)
repo_id = "mistralai/Mistral-7B-Instruct-v0.1"
llm = HuggingFaceHub(repo_id=repo_id, model_kwargs={"temperature":0.5, "max_new_tokens":500})
# Memory and Chain
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
qa_chain = ConversationalRetrievalChain.from_llm(
llm, retriever=vectordb.as_retriever(), memory=memory
)
# Chat Interface
st.markdown("---")
st.markdown("💬 **Ask a question from the PDF:**")
if "chat_history" not in st.session_state:
st.session_state.chat_history = []
question = st.text_input("Type your question here...", key="user_input")
if question:
result = qa_chain.run(question)
st.session_state.chat_history.append(("You", question))
st.session_state.chat_history.append(("Bot", result))
# Show chat history
for sender, msg in st.session_state.chat_history[::-1]:
st.markdown(f"**{sender}:** {msg}")
# Question Generation Button
st.markdown("---")
if st.button("📚 Generate Q&A from all chapters"):
st.info("Generating questions and answers from the content...")
questions = [
"What is the main idea of this chapter?",
"What are the key points discussed?",
"Can you summarize this section?",
"Are there any definitions or terms introduced?"
]
for i, chunk in enumerate(chunks[:3]): # Limit to first 3 chunks for demo
st.markdown(f"**Chapter Section {i+1}:**")
for q in questions:
answer = llm.invoke(q + "\\n" + chunk.page_content[:1000])
st.markdown(f"**Q:** {q}")
st.markdown(f"**A:** {answer}")
st.markdown("---")
"""
# Save both files to /mnt/data for user download or deployment
with open("/mnt/data/requirements.txt", "w") as f:
f.write(requirements_txt.strip())
with open("/mnt/data/app.py", "w") as f:
f.write(app_py.strip())
|