Spaces:
Sleeping
Sleeping
File size: 5,682 Bytes
1641f21 86b54f8 1641f21 86b54f8 | 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 | import streamlit as st
from sentence_transformers import SentenceTransformer
import chromadb
import time
# 1. System Configurations
st.set_page_config(page_title="InsightStream AI", page_icon="⚡", layout="wide")
# Custom CSS to force a high-end dark theme aesthetic
st.markdown("""
<style>
.main .block-container {padding-top: 2rem;}
.metric-card {background-color: #1e222b; padding: 15px; border-radius: 8px; border: 1px solid #2d3139;}
</style>
""", unsafe_allow_html=True)
# 2. Optimized Resource Initializations
@st.cache_resource
def load_analytics_engine():
return SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
@st.cache_resource
def init_vector_vault():
client = chromadb.Client()
return client.get_or_create_collection(
name="stream_intelligence_vault",
metadata={"hnsw:space": "cosine"}
)
engine = load_analytics_engine()
vault = init_vector_vault()
# Curated high-value corporate intel data
FEED_PRESETS = [
"Market Alert: High structural inflation signals aggressive interest rate hikes next quarter.",
"R&D Update: Quantum entanglement framework successfully processing multi-dimensional data arrays.",
"Operations Briefing: Deep learning algorithms integrated into production pipelines to automate code audits.",
"Infrastructure Notice: Storage systems transitioning entirely to vectorized database mathematical modeling.",
"Wellness Policy: New corporate initiatives mandate daily physical breaks and bio-balanced nutrition tracking.",
"Logistics Report: Autonomous supply chain mechanisms deployed across regional fulfillment hubs.",
"Biotech News: Synthetic neural networks showing unprecedented mastery over biochemical sequencing tasks."
]
# 3. Main Dashboard Header Layout
t1, t2 = st.columns([7, 3])
with t1:
st.title("⚡ INSIGHTSTREAM")
st.markdown("### *Real-Time Neural Text Processing & Stream Auditing Hub*")
with t2:
st.write("")
st.write("")
# Dynamic KPI metric cards
st.markdown(
f'<div class="metric-card">'
f'📶 <b>SYSTEM STATUS:</b> <span style="color:#00ffcc;">ACTIVE</span><br>'
f'📦 <b>INDEXED DATA STREAMS:</b> {vault.count()}'
f'</div>',
unsafe_allow_html=True
)
st.divider()
# 4. Tabbed Workplace Navigation (Eliminating the traditional sidebar)
tab_monitor, tab_ingest = st.tabs(["📊 INTELLIGENCE STREAM MONITOR", "📥 DATA INGESTION ENGINE"])
# --- TAB 1: SEARCH & MONITOR ---
with tab_monitor:
if vault.count() == 0:
st.error("🚨 Neural Index Empty: No data feeds detected in the pipeline.")
if st.button("⚡ Trigger Auto-Seed Pipeline"):
with st.spinner("Processing framework initialization vectors..."):
embeddings = engine.encode(FEED_PRESETS).tolist()
ids = [f"feed_id_{i}" for i in range(len(FEED_PRESETS))]
vault.add(embeddings=embeddings, documents=FEED_PRESETS, ids=ids)
st.success("System auto-seeded successfully!")
st.rerun()
else:
# Search controls integrated horizontally into the main screen layout
ctrl1, ctrl2 = st.columns([3, 1])
with ctrl1:
intel_query = st.text_input("🎯 Filter streams via conceptual query:", placeholder="Type a concept, e.g., corporate financial stress or machine learning automation...")
with ctrl2:
max_nodes = st.select_slider("Max Nodes to Map:", options=[1, 2, 3, 4, 5], value=3)
if intel_query:
with st.spinner("Executing high-dimensional vector search..."):
t_start = time.time()
query_vec = engine.encode([intel_query]).tolist()
payload = vault.query(query_embeddings=query_vec, n_results=max_nodes)
latency = (time.time() - t_start) * 1000
st.markdown(f"##### 🛰️ Stream Analysis Complete (`{latency:.2f}ms latency`)")
if payload and payload['documents']:
feeds = payload['documents'][0]
metrics = payload['distances'][0]
node_ids = payload['ids'][0]
# Render clean metric-driven grid modules
for i in range(len(feeds)):
confidence = (1 - metrics[i]) * 100
with st.expander(f"🔴 STREAM NODE {node_ids[i]} — Match Confidence: {confidence:.2f}%", expanded=True):
st.write(f"**Data Payload:**")
st.code(feeds[i], language="markdown")
else:
st.warning("No nodes matched the conceptual threshold.")
# --- TAB 2: DATA INGESTION ---
with tab_ingest:
st.subheader("📥 Raw Text Ingestion Port")
st.markdown("Manually inject unstructured text blocks into the vector analytics cluster.")
stream_payload = st.text_area("Raw Document Payload:", placeholder="Paste text logs, reports, or data streams here...")
if st.button("🚀 Commit Payload to Cluster"):
if stream_payload.strip():
with st.spinner("Vectorizing input stream..."):
assigned_id = f"feed_user_{vault.count() + 1}"
payload_vec = engine.encode([stream_payload]).tolist()
vault.add(
embeddings=payload_vec,
documents=[stream_payload],
ids=[assigned_id]
)
st.success(f"Success: Nodes updated. Assigned ID: {assigned_id}")
st.rerun()
else:
st.error("Aborted: Ingestion payload cannot be empty.")
|