Spaces:
Sleeping
Sleeping
File size: 4,991 Bytes
3a8d617 0fe6232 |
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 |
import streamlit as st
import os
import tempfile
# from src.RAG_builder import ProjectRAGGraph # Ensure your graph class is in your_filename.py
from src.rag_graph import ProjectRAGGraph
# from src.graph.rag_graph import ProjectRAGGraph
# --- Page Config ---
st.set_page_config(page_title="Project Report Analyzer", layout="wide")
st.title("📄 Project Report Analyzer")
# --- Initialize Session State ---
if "rag_graph" not in st.session_state:
st.session_state.rag_graph = ProjectRAGGraph()
if "messages" not in st.session_state:
st.session_state.messages = []
if "thread_id" not in st.session_state:
st.session_state.thread_id = "default_user_1" # Hardcoded for demo, could be unique per session
# --- Sidebar: File Upload ---
with st.sidebar:
st.header("Upload Documents")
uploaded_files = st.file_uploader(
"Upload Project PDFs",
type="pdf",
accept_multiple_files=True
)
process_button = st.button("Process Documents")
if process_button and uploaded_files:
with st.spinner("Processing PDFs..."):
pdf_paths = []
original_names = [] # <--- Add this
for uploaded_file in uploaded_files:
original_names.append(uploaded_file.name) # <--- Capture real name
with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
tmp.write(uploaded_file.getvalue())
pdf_paths.append(tmp.name)
# Pass BOTH the paths and the original names
st.session_state.rag_graph.process_documents(
pdf_paths,
original_names=original_names
)
for path in pdf_paths:
os.remove(path)
st.success("Documents Indexed Successfully!")
# if process_button and uploaded_files:
# with st.spinner("Processing PDFs..."):
# # Create temporary file paths to pass to your PDF Loader
# pdf_paths = []
# for uploaded_file in uploaded_files:
# with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
# tmp.write(uploaded_file.getvalue())
# pdf_paths.append(tmp.name)
# # Use your existing process_documents method
# st.session_state.rag_graph.process_documents(pdf_paths)
# # Clean up temp files
# for path in pdf_paths:
# os.remove(path)
# st.success("Documents Indexed Successfully!")
# --- Chat Interface ---
# Display existing messages
for message in st.session_state.messages:
with st.chat_message(message["role"]):
st.markdown(message["content"])
if "citations" in message and message["citations"]:
with st.expander("View Sources"):
for doc in message["citations"]:
st.caption(f"Source: {doc.metadata.get('source', 'Unknown')} - Page: {doc.metadata.get('page', 'N/A')}")
st.write(f"_{doc.page_content[:200]}..._")
# User Input
if prompt := st.chat_input("Ask a question about your projects..."):
# Check if vector store is ready
if st.session_state.rag_graph.vector_store is None:
st.error("Please upload and process documents first!")
else:
# Add user message to state
st.session_state.messages.append({"role": "user", "content": prompt})
with st.chat_message("user"):
st.markdown(prompt)
# Generate Response using the Graph
with st.chat_message("assistant"):
with st.spinner("Analyzing..."):
# We need to call the graph. We'll modify the query return slightly to get citations
config = {"configurable": {"thread_id": st.session_state.thread_id}}
inputs = {"question": prompt}
# Execute graph
result = st.session_state.rag_graph.workflow.invoke(inputs, config=config)
answer = result["answer"]
context = result["context"] # These are the retrieved Document objects
st.markdown(answer)
# Citations section
if context:
with st.expander("View Sources"):
for doc in context:
source_name = os.path.basename(doc.metadata.get('source', 'Unknown'))
page_num = doc.metadata.get('page', 0) + 1
st.caption(f"📄 {source_name} (Page {page_num})")
st.write(f"_{doc.page_content[:300]}..._")
# Add assistant response to state
st.session_state.messages.append({
"role": "assistant",
"content": answer,
"citations": context
}) |