Spaces:
Runtime error
Runtime error
File size: 14,981 Bytes
7b43396 913af42 7b43396 913af42 7b43396 913af42 7b43396 913af42 7b43396 cb6ce27 7b43396 cb6ce27 7b43396 913af42 7b43396 db0b8ce 7b43396 913af42 db0b8ce 7b43396 db0b8ce 7b43396 db0b8ce 7b43396 0293829 7b43396 db0b8ce 7b43396 913af42 7b43396 cb6ce27 7b43396 913af42 7b43396 cb6ce27 7b43396 913af42 7b43396 cb6ce27 7b43396 913af42 7b43396 913af42 7b43396 cb6ce27 7b43396 cb6ce27 7b43396 cb6ce27 7b43396 913af42 7b43396 cb6ce27 7b43396 913af42 cb6ce27 913af42 7b43396 cb6ce27 7b43396 913af42 7b43396 f259155 7b43396 f259155 7b43396 f259155 7b43396 f259155 7b43396 913af42 7b43396 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 | import streamlit as st
from datetime import datetime
from hybrid_processor import HybridProcessor
import logging
# Configure Streamlit page settings
st.set_page_config(layout="wide")
# Set up logging for debugging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)
# Initialize the HybridProcessor
try:
processor = HybridProcessor()
except Exception as e:
logger.error(f"Failed to initialize HybridProcessor: {str(e)}")
raise
# Function to compare approaches and return results
def compare_approaches(question, processor):
try:
vector_result = processor.vector_processor.query(question)
logger.info(f"Vector result: {vector_result}")
graph_result = processor.graph_processor.query(question)
logger.info(f"Graph result: {graph_result}")
hybrid_result = processor.query(question)
logger.info(f"Hybrid result: {hybrid_result}")
vector_chunks_str = '\n\n'.join(
[f'Chunk {i + 1}: {chunk}' for i, chunk in enumerate(hybrid_result['chunks']['vector'])])
graph_chunks_str = '\n\n'.join(
[f'Record {i + 1}: {chunk}' for i, chunk in enumerate(hybrid_result['chunks']['graph'])])
hybrid_chunks_formatted = f"Vector Chunks:\n{vector_chunks_str}\n\nGraph Records:\n{graph_chunks_str}"
return {
"vector_answer": vector_result["answer"],
"vector_chunks": "\n\n".join(
[f"Chunk {i + 1}: {chunk}" for i, chunk in enumerate(vector_result["chunks"])]),
"graph_answer": graph_result["answer"],
"graph_chunks": "\n\n".join([f"Record {i + 1}: {chunk}" for i, chunk in enumerate(graph_result["chunks"])]),
"hybrid_answer": hybrid_result["answer"],
"hybrid_chunks": hybrid_chunks_formatted
}
except Exception as e:
logger.error(f"Error in compare_approaches: {str(e)}")
st.error(f"Error processing query: {str(e)}")
return {
"vector_answer": "Error processing query.",
"vector_chunks": "",
"graph_answer": "Error processing query.",
"graph_chunks": "",
"hybrid_answer": "Error processing query.",
"hybrid_chunks": ""
}
# Custom CSS for a modern dark theme UI
# Custom CSS for a modern dark theme UI with reduced font sizes
st.markdown("""
<style>
@import url('https://fonts.googleapis.com/css2?family=Poppins:wght@300;400;500;600;700&display=swap');
@import url('https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0-beta3/css/all.min.css');
* {
font-family: 'Poppins', sans-serif !important;
box-sizing: border-box;
font-size: 13px !important; /* Reduced base font size from 16px (implicit default) to 13px */
}
body, .stApp {
background: #1A1B26 !important;
color: #E0E0E0 !important;
margin: 0 !important;
padding: 0 !important;
}
.main {
background: #1A1B26 !important;
padding: 24px !important;
}
.header h1 {
font-size: 32px !important; /* Reduced from 24px to 20px */
font-weight: 600 !important;
color: #60A5FA !important;
margin-bottom: 4px !important;
text-align: center !important;
}
.header-text {
color: #A0AEC0 !important;
font-size: 12px !important; /* Reduced from 16px to 13px */
text-align: center !important;
margin-bottom: 4px !important;
}
.warning-text {
color: #F87171 !important;
font-size: 10px !important; /* Reduced from 14px to 11px */
font-weight: 500 !important;
text-align: center !important;
margin-bottom: 10px !important;
}
.stTextInput > div > div > input {
background-color: #2A2B37 !important;
color: #E0E0E0 !important;
border: 1px solid #3B82F6 !important;
border-radius: 12px !important;
padding: 14px !important;
font-size: 13px !important; /* Reduced from 16px to 13px */
box-shadow: 0 2px 4px rgba(0, 0, 0, 0.2) !important;
transition: all 0.3s ease !important;
}
.stTextInput > div > div > input:focus {
border-color: #60A5FA !important;
box-shadow: 0 0 0 3px rgba(59, 130, 246, 0.2) !important;
}
.stButton > button {
background: linear-gradient(90deg, #3B82F6 0%, #A855F7 100%) !important;
color: white !important;
border: none !important;
border-radius: 12px !important;
padding: 12px 24px !important;
font-size: 13px !important; /* Reduced from 16px to 13px */
font-weight: 500 !important;
box-shadow: 0 2px 4px rgba(0, 0, 0, 0.2) !important;
transition: all 0.3s ease !important;
}
.stButton > button:hover {
background: linear-gradient(90deg, #60A5FA 0%, #C084FC 100%) !important;
box-shadow: 0 4px 8px rgba(0, 0, 0, 0.3) !important;
transform: scale(1.05) !important;
}
.clear-button > button {
background: linear-gradient(90deg, #F87171 0%, #EF4444 100%) !important;
color: white !important;
border: none !important;
border-radius: 12px !important;
padding: 12px 24px !important;
font-size: 13px !important; /* Reduced from 16px to 13px */
font-weight: 500 !important;
box-shadow: 0 2px 4px rgba(0, 0, 0, 0.2) !important;
transition: all 0.3s ease !important;
}
.clear-button > button:hover {
background: linear-gradient(90deg, #EF4444 0%, #F87171 100%) !important;
box-shadow: 0 4px 8px rgba(0, 0, 0, 0.3) !important;
transform: scale(1.05) !important;
}
.chat-container, .info-box {
background: rgba(42, 43, 55, 0.8) !important;
backdrop-filter: blur(10px) !important;
border: 1px solid rgba(255, 255, 255, 0.1) !important;
border-radius: 16px !important;
padding: 20px !important;
color: #E0E0E0 !important;
box-shadow: 0 4px 12px rgba(0, 0, 0, 0.2) !important;
}
.chat-container {
height: 400px !important;
overflow-y: auto !important;
margin-bottom: 20px !important;
scroll-behavior: smooth !important;
}
.stChatMessage {
background: #3A3B47 !important;
color: #E0E0E0 !important;
border-radius: 12px !important;
padding: 14px 18px !important;
font-size: 13px !important; /* Reduced from 16px to 13px */
line-height: 1.6 !important;
white-space: pre-wrap !important;
margin: 12px 0 !important;
opacity: 1 !important;
}
.info-box {
font-size: 13px !important; /* Reduced from 16px to 13px */
line-height: 1.6 !important;
margin-bottom: 20px !important;
padding: 20px !important;
white-space: pre-wrap !important;
}
.chunks-container {
background: rgba(42, 43, 55, 0.8) !important;
backdrop-filter: blur(10px) !important;
border: 1px solid rgba(255, 255, 255, 0.1) !important;
border-radius: 16px !important;
padding: 20px !important;
color: #E0E0E0 !important;
box-shadow: 0 4px 12px rgba(0, 0, 0, 0.2) !important;
margin-top: 24px !important;
width: 100% !important;
}
.footer {
text-align: center !important;
color: #A0AEC0 !important;
font-size: 11px !important; /* Reduced from 14px to 11px */
padding: 24px 0 !important;
}
.stColumns {
gap: 24px !important;
}
.stColumns > div {
flex: 1 !important;
}
.stExpander {
background: #2A2B37 !important;
border: 1px solid rgba(255, 255, 255, 0.1) !important;
border-radius: 12px !important;
margin-bottom: 12px !important;
}
.stExpander > div > div > div > p {
color: #E0E0E0 !important;
font-size: 13px !important; /* Reduced from 16px to 13px */
font-weight: 500 !important;
}
</style>
""", unsafe_allow_html=True)
# Streamlit App Layout
st.markdown('<div class="header">', unsafe_allow_html=True)
st.title("RAG vs GraphRAG")
st.markdown('<p class="header-text">Compare Vector DB, Graph DB, and Hybrid approaches for document querying</p>', unsafe_allow_html=True)
st.markdown('<p class="warning-text"><b>Do not upload personal or private data</b></p>', unsafe_allow_html=True)
st.markdown('</div>', unsafe_allow_html=True)
# Initialize session state
if "chat_history" not in st.session_state:
st.session_state.chat_history = []
if "vector_chunks" not in st.session_state:
st.session_state.vector_chunks = "Vector DB results will appear here"
if "graph_chunks" not in st.session_state:
st.session_state.graph_chunks = "Graph DB results will appear here"
if "hybrid_chunks" not in st.session_state:
st.session_state.hybrid_chunks = "Hybrid results will appear here"
# Create two columns for the split layout
col1, col2 = st.columns(2)
# Left Column: Chat Interface
# Left Column: Chat Interface
with col1:
# Chat display area using st.chat_message
with st.container():
# Placeholder if chat history is empty
if not st.session_state.chat_history:
st.markdown(
'<div style="text-align: center; color: #A0AEC0; font-size: 16px; margin-top: 20px;">Start the conversation by asking a question!</div>',
unsafe_allow_html=True
)
# Render chat history using st.chat_message
for message in st.session_state.chat_history:
with st.chat_message(message["role"], avatar="user" if message["role"] == "user" else "assistant"):
st.markdown(message["content"])
logger.info(f"Rendering chat message: {message}")
# Input area with Send and Clear buttons
with st.container():
query = st.text_input(
label="Ask a question",
placeholder="Ask in the format: 'What is the relationship between [Entity1] and [Entity2]?' (e.g., 'What is the relationship between Alice and TechCorp?')",
label_visibility="collapsed"
)
btn_col1, btn_col2 = st.columns([1, 1])
with btn_col1:
send_button = st.button("Send", key="send")
with btn_col2:
clear_button = st.button("Clear Chat", key="clear", help="Reset the conversation", type="secondary")
# Right Column: Single plain box with source text and use case questions
with col2:
st.markdown("""
<div class="info-box">
<b>Questions to Try:</b><br>
- What are the key achievements of TechCorp?<br>
- Who works for TechCorp?
<br><b>**** Below source document has already been loaded for testing**** </b>
<b>TechCorp Annual Report Summary</b>
<i>April 27, 2025</i><br>
TechCorp, a leading AI company headquartered in San Francisco, achieved significant milestones in 2024. Founded by Alice Johnson, TechCorp employs 500 people and specializes in machine learning solutions. Alice, the CEO, collaborated with Bob Smith, CTO of InnovateAI, on a joint project to develop a new AI model. This partnership strengthened TechCorp's presence in New York, where InnovateAI is based.<br><br>
The company expanded its operations to London, appointing Claire Brown as the regional director. Claire previously worked with Alice at Quantum Dynamics, a Boston-based firm. TechCorp's revenue grew by 20%, driven by contracts with GlobalTech in Seattle and DataSolutions in Chicago.<br><br>
<b>Key Achievements:</b>
- Launched AI platform "NeuraNet" in San Francisco.<br>
- Partnered with InnovateAI in New York.<br>
- Opened a new office in London led by Claire Brown.<br>
</div>
""", unsafe_allow_html=True)
# Handle the Send button click
if send_button and query:
# Add user message to chat history
st.session_state.chat_history.append({"role": "user", "content": query})
logger.info(f"User query added to chat history: {query}")
# Get responses from the processor
response = compare_approaches(query, processor)
logger.info(f"Compare approaches response: {response}")
# Add assistant response to chat history (only the answers)
assistant_response = (
f"**Vector DB Answer**: {response['vector_answer']}\n\n"
f"**Graph DB Answer**: {response['graph_answer']}\n\n"
f"**Hybrid Answer**: {response['hybrid_answer']}"
)
logger.info(f"Assistant response: {assistant_response}")
st.session_state.chat_history.append({"role": "assistant", "content": assistant_response})
logger.info(f"Chat history after update: {st.session_state.chat_history}")
# Update the result displays (only chunks/records)
st.session_state.vector_chunks = response["vector_chunks"]
st.session_state.graph_chunks = response["graph_chunks"]
st.session_state.hybrid_chunks = response["hybrid_chunks"]
# Rerender the page
st.rerun()
# Handle the Clear Chat button
if clear_button:
st.session_state.chat_history = []
st.session_state.vector_chunks = "Vector DB results will appear here"
st.session_state.graph_chunks = "Graph DB results will appear here"
st.session_state.hybrid_chunks = "Hybrid results will appear here"
st.rerun()
# Chunks display at the bottom in accordion style
with st.container():
st.markdown('<div class="chunks-container">', unsafe_allow_html=True)
st.markdown("### Chunks and Records", unsafe_allow_html=True)
with st.expander("Vector DB Chunks"):
st.markdown(st.session_state.vector_chunks)
with st.expander("Graph DB Records"):
st.markdown(st.session_state.graph_chunks)
with st.expander("Hybrid Chunks/Records"):
st.markdown(st.session_state.hybrid_chunks)
st.markdown('</div>', unsafe_allow_html=True)
# Footer
st.markdown("""
<div class="footer">
Interested in more of my thoughts and projects? <a href="https://dipenvekaria.com" target="_blank">Click here</a> to visit my website!
</div>
""", unsafe_allow_html=True)
if __name__ == "__main__":
logger.info(f"===== Application Startup at {datetime.now().strftime('%Y-%m-%d %H:%M:%S')} =====") |