Spaces:
Sleeping
Sleeping
File size: 6,052 Bytes
318577c 7afc98c 6ccfd34 82d3171 7afc98c 6ccfd34 7afc98c 45b170d 7afc98c 45b170d 7afc98c 82d3171 7afc98c 82d3171 7afc98c 82d3171 7afc98c 318577c 7afc98c 82d3171 7afc98c 318577c 7afc98c 82d3171 7afc98c 318577c 7afc98c 318577c 7afc98c 318577c 7afc98c 318577c 7afc98c | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 | # 1. Mandatory SQLite fix for ChromaDB in Docker (MUST BE AT THE VERY TOP)
try:
__import__('pysqlite3')
import sys
sys.modules['sqlite3'] = sys.modules.pop('pysqlite3')
except ImportError:
pass
import re
import os
import shutil
import streamlit as st
import chromadb # Added for EphemeralClient
from langchain_huggingface import HuggingFaceEndpoint, HuggingFaceEmbeddings, ChatHuggingFace
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import Chroma
from langchain_community.document_loaders import PyPDFLoader
from langchain_core.messages import HumanMessage, SystemMessage
# -----------------------------
# 1. Page Configuration + UI Styling
# -----------------------------
st.set_page_config(
page_title="AI Study Assistant for University Lecture Notes",
page_icon="🎓",
layout="wide",
)
st.markdown("""
<style>
.block-container {
padding-top: 2rem;
padding-bottom: 2rem;
}
.main-title {
text-align: center;
font-size: 42px;
font-weight: 700;
}
.subtitle {
text-align: center;
font-size: 18px;
color: #555;
margin-bottom: 30px;
}
.stButton>button {
width: 100%;
border-radius: 12px;
height: 3em;
font-weight: 600;
}
.section-card {
padding: 20px;
border-radius: 15px;
background-color: #f8f9fb;
box-shadow: 0 4px 10px rgba(0,0,0,0.05);
margin-bottom: 20px;
}
</style>
""", unsafe_allow_html=True)
st.markdown("<div class='main-title'>🎓 AI Study Assistant for University Lecture Notest</div>", unsafe_allow_html=True)
st.markdown("<div class='subtitle'></div>", unsafe_allow_html=True)
st.markdown("---")
token = os.environ.get("HUGGINGFACEHUB_API_TOKEN2")
# -----------------------------
# 2. RAG Logic
# -----------------------------
def process_lecture_pdf(uploaded_file):
# Save the uploaded file temporarily
temp_path = os.path.join("/tmp", uploaded_file.name)
with open(temp_path, "wb") as f:
f.write(uploaded_file.getbuffer())
try:
# Load and split PDF
loader = PyPDFLoader(temp_path)
docs = loader.load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=700, chunk_overlap=100)
chunks = text_splitter.split_documents(docs)
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
# --- FIX: Use In-Memory Client ---
# This prevents the "readonly database" error (Code 1032) by not using the disk
client = chromadb.EphemeralClient()
vectorstore = Chroma.from_documents(
documents=chunks,
embedding=embeddings,
client=client
)
return vectorstore.as_retriever(search_kwargs={"k": 3}), docs
finally:
# Cleanup: Remove the temp PDF file after processing
if os.path.exists(temp_path):
os.remove(temp_path)
# -----------------------------
# 3. Model Setup
# -----------------------------
# Ensure the token exists before initializing
if not token:
st.error("HUGGINGFACEHUB_API_TOKEN2 is not set in environment variables.")
st.stop()
llm_endpoint = HuggingFaceEndpoint(
repo_id="meta-llama/Meta-Llama-3-8B-Instruct",
task="conversational",
huggingfacehub_api_token=token,
max_new_tokens=1024,
temperature=0.6
)
chat_llm = ChatHuggingFace(llm=llm_endpoint)
# -----------------------------
# 4. User Interface
# -----------------------------
col1, col2 = st.columns([1, 2])
with col1:
st.header("📂 Upload Notes")
uploaded_file = st.file_uploader("Upload Lecture PDF", type="pdf")
if uploaded_file:
# Only process if it's a new file
if 'last_file' not in st.session_state or st.session_state.last_file != uploaded_file.name:
with st.spinner("Analyzing PDF with Llama 3..."):
retriever, full_docs = process_lecture_pdf(uploaded_file)
st.session_state.retriever = retriever
st.session_state.full_text = "\n".join([d.page_content for d in full_docs])
st.session_state.last_file = uploaded_file.name
st.success("Ready to study!")
st.header("📝 Summarize")
if st.button("Generate Summary"):
if 'full_text' in st.session_state:
with st.spinner("Llama 3 is summarizing..."):
messages = [
SystemMessage(content="You are a helpful university teaching assistant. Summarize the following text clearly."),
HumanMessage(content=f"Notes: {st.session_state.full_text[:4000]}")
]
response = chat_llm.invoke(messages)
st.write(response.content)
else:
st.warning("Please upload a PDF first.")
with col2:
st.header("💬 Ask Questions")
with st.form("qa_form"):
user_query = st.text_input("What would you like to know about your lecture?")
submit_button = st.form_submit_button("Ask Question")
if submit_button:
if not user_query:
st.error("Please enter a question.")
elif 'retriever' in st.session_state:
with st.spinner("Llama 3 is searching for the answer..."):
context_docs = st.session_state.retriever.invoke(user_query)
context_text = "\n\n".join([doc.page_content for doc in context_docs])
messages = [
SystemMessage(content="Use the provided context to answer the student's question accurately."),
HumanMessage(content=f"Context: {context_text}\n\nQuestion: {user_query}")
]
response = chat_llm.invoke(messages)
st.markdown("### Answer")
st.info(response.content)
with st.expander("View Source Context"):
st.write(context_text)
else:
st.warning("Upload a PDF to start.") |