Update src/streamlit_app.py

import os

os.environ["TOKENIZERS_PARALLELISM"] = "false"

# Sekarang baru import streamlit
import streamlit as st
import faiss
import pickle
from sentence_transformers import SentenceTransformer
import pandas as pd

# Konfigurasi
MODEL_NAME = "Qwen/Qwen3-Embedding-0.6B"

# Get absolute path for data directory (independent from maintenance_web)
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
INDEX_DIR = os.path.join(SCRIPT_DIR, "data")



@st
.cache_resource(show_spinner=True)
def load_model():
"""Load embedding model"""
# Model akan di-cache otomatis
model = SentenceTransformer(MODEL_NAME)
return model



@st
.cache_resource
def load_index():
"""Load FAISS index and metadata"""
index_path = os.path.join(INDEX_DIR, "skripsi.faiss")
metadata_path = os.path.join(INDEX_DIR, "metadata.pkl")

if not os.path.exists(index_path):
st.error(f"Index not found: {index_path}")
return None, None

if not os.path.exists(metadata_path):
st.error(f"Metadata not found: {metadata_path}")
return None, None

index = faiss.read_index(index_path)

with open(metadata_path, 'rb') as f:
metadata = pickle.load(f)

return index, metadata

def search(query, model, index, metadata, top_k=10):
"""Perform semantic search"""
# Generate query embedding
query_embedding = model.encode([query])

# Search
distances, indices = index.search(query_embedding, top_k)

# Get data list from metadata
data_list = metadata.get('data', [])

# Format results
results = []
for i, (dist, idx) in enumerate(zip(distances[0], indices[0])):
if idx < len(data_list):
meta = data_list[idx]
# Combine pembimbing info
pembimbing = meta.get('nama_pembimbing', 'N/A')
gelar_depan = meta.get('gelar_depan_pembimbing', '')
gelar_belakang = meta.get('gelar_belakang_pembimbing', '')
if gelar_depan or gelar_belakang:
pembimbing = f"{gelar_depan} {pembimbing}, {gelar_belakang}".strip(', ')

results.append({
'Rank': i + 1,
'Score': f"{dist:.4f}",
'Judul': meta.get('judul', 'N/A'),
'NIM': meta.get('nim', 'N/A'),
'Nama': meta.get('nama', 'N/A'),
'Pembimbing': pembimbing,
'Tahun': meta.get('tahun', 'N/A'),
'Semester': meta.get('semester', 'N/A')
})

return results

# Streamlit UI
st.set_page_config(page_title="Semantic Search - Skripsi UNIKOM", layout="wide")

st.title("🔍 Semantic Search - Database Skripsi Prodi Teknik Informatika UNIKOM")
st.markdown("*Pencarian semantik berdasarkan kemiripan makna judul skripsi*")
st.markdown("---")

# Sidebar
with st.sidebar:
st.header("⚙️ Settings")
top_k = st.slider("Number of results", min_value=5, max_value=50, value=10, step=5)

st.markdown("---")
st.markdown("### 📊 Model Info")
st.info(f"""
**Model**: {MODEL_NAME}
**Index**: {INDEX_DIR}
""")

# Load resources
try:
model = load_model()
index, metadata = load_index()

if index is None or metadata is None:
st.error("Failed to load index or metadata")
st.stop()

st.success(f"✅ Model loaded | Index: {index.ntotal} vectors | Dimension: {index.d}")

except Exception as e:
st.error(f"Error loading resources: {e}")
st.stop()

# Search interface
st.markdown("### 💬 Enter your search query")
query = st.text_input("Search Query", placeholder="e.g., machine learning, web application, sistem informasi...", label_visibility="collapsed")

if st.button("🔍 Search", type="primary") or query:
if query.strip():
with st.spinner("Searching..."):
results = search(query, model, index, metadata, top_k)

st.markdown(f"### 📋 Found {len(results)} results")

# Display as dataframe
if results:
df = pd.DataFrame(results)
st.dataframe(df, use_container_width=True, hide_index=True)

# Detailed view
st.markdown("---")
st.markdown("### 📖 Detailed Results")
for result in results:
with st.expander(f"#{result['Rank']} - {result['Judul'][:100]}... (Score: {result['Score']})"):
col1, col2 = st.columns(2)
with col1:
st.markdown(f"**NIM**: {result['NIM']}")
st.markdown(f"**Nama**: {result['Nama']}")
st.markdown(f"**Pembimbing**: {result['Pembimbing']}")
with col2:
st.markdown(f"**Tahun**: {result['Tahun']}")
st.markdown(f"**Semester**: {result['Semester']}")
st.markdown(f"**Judul Lengkap**: {result['Judul']}")
else:
st.warning("No results found")
else:
st.warning("Please enter a search query")

# Footer
st.markdown("---")
st.markdown("""
<div style='text-align: center;'>
<p><a href='https://galih.eu'>Galih Hermawan</a> | Akabot Research Group</p>
<p>Prodi Teknik Informatika | Universitas Komputer Indonesia</p>
<p>Powered by Qwen3 Embedding Model</p>
</div>
""", unsafe_allow_html=True)

src/streamlit_app.py

@@ -1,40 +1,170 @@
-import altair as alt
-import numpy as np
-import pandas as pd
+import os
+from pathlib import Path
+
+# FIX: Set cache ke /tmp (writable di HF Spaces)
+os.environ["HOME"] = "/tmp"
+os.environ["HF_HOME"] = "/tmp/.cache/huggingface"
+os.environ["TRANSFORMERS_CACHE"] = "/tmp/.cache/huggingface/transformers"
+os.environ["SENTENCE_TRANSFORMERS_HOME"] = "/tmp/.cache/sentence-transformers"
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
+
+# Buat folder cache
+Path("/tmp/.cache/huggingface").mkdir(parents=True, exist_ok=True)
+Path("/tmp/.cache/sentence-transformers").mkdir(parents=True, exist_ok=True)
+
+# Sekarang baru import streamlit
 import streamlit as st
+import faiss
+import pickle
+from sentence_transformers import SentenceTransformer
+import pandas as pd
+
+# Konfigurasi
+MODEL_NAME = "Qwen/Qwen3-Embedding-0.6B"
+
+# Get absolute path for data directory (independent from maintenance_web)
+SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
+INDEX_DIR = os.path.join(SCRIPT_DIR, "data")
+
+@st.cache_resource(show_spinner=True)
+def load_model():
+    """Load embedding model"""
+    # Model akan di-cache otomatis
+    model = SentenceTransformer(MODEL_NAME)
+    return model
+
+@st.cache_resource
+def load_index():
+    """Load FAISS index and metadata"""
+    index_path = os.path.join(INDEX_DIR, "skripsi.faiss")
+    metadata_path = os.path.join(INDEX_DIR, "metadata.pkl")
+    
+    if not os.path.exists(index_path):
+        st.error(f"Index not found: {index_path}")
+        return None, None
+    
+    if not os.path.exists(metadata_path):
+        st.error(f"Metadata not found: {metadata_path}")
+        return None, None
+    
+    index = faiss.read_index(index_path)
+    
+    with open(metadata_path, 'rb') as f:
+        metadata = pickle.load(f)
+    
+    return index, metadata
+
+def search(query, model, index, metadata, top_k=10):
+    """Perform semantic search"""
+    # Generate query embedding
+    query_embedding = model.encode([query])
+    
+    # Search
+    distances, indices = index.search(query_embedding, top_k)
+    
+    # Get data list from metadata
+    data_list = metadata.get('data', [])
+    
+    # Format results
+    results = []
+    for i, (dist, idx) in enumerate(zip(distances[0], indices[0])):
+        if idx < len(data_list):
+            meta = data_list[idx]
+            # Combine pembimbing info
+            pembimbing = meta.get('nama_pembimbing', 'N/A')
+            gelar_depan = meta.get('gelar_depan_pembimbing', '')
+            gelar_belakang = meta.get('gelar_belakang_pembimbing', '')
+            if gelar_depan or gelar_belakang:
+                pembimbing = f"{gelar_depan} {pembimbing}, {gelar_belakang}".strip(', ')
+            
+            results.append({
+                'Rank': i + 1,
+                'Score': f"{dist:.4f}",
+                'Judul': meta.get('judul', 'N/A'),
+                'NIM': meta.get('nim', 'N/A'),
+                'Nama': meta.get('nama', 'N/A'),
+                'Pembimbing': pembimbing,
+                'Tahun': meta.get('tahun', 'N/A'),
+                'Semester': meta.get('semester', 'N/A')
+            })
+    
+    return results
+
+# Streamlit UI
+st.set_page_config(page_title="Semantic Search - Skripsi UNIKOM", layout="wide")
+
+st.title("🔍 Semantic Search - Database Skripsi Prodi Teknik Informatika UNIKOM")
+st.markdown("*Pencarian semantik berdasarkan kemiripan makna judul skripsi*")
+st.markdown("---")
+
+# Sidebar
+with st.sidebar:
+    st.header("⚙️ Settings")
+    top_k = st.slider("Number of results", min_value=5, max_value=50, value=10, step=5)
+    
+    st.markdown("---")
+    st.markdown("### 📊 Model Info")
+    st.info(f"""
+    **Model**: {MODEL_NAME}
+    **Index**: {INDEX_DIR}
+    """)
+
+# Load resources
+try:
+    model = load_model()
+    index, metadata = load_index()
+    
+    if index is None or metadata is None:
+        st.error("Failed to load index or metadata")
+        st.stop()
+    
+    st.success(f"✅ Model loaded | Index: {index.ntotal} vectors | Dimension: {index.d}")
+    
+except Exception as e:
+    st.error(f"Error loading resources: {e}")
+    st.stop()
+
+# Search interface
+st.markdown("### 💬 Enter your search query")
+query = st.text_input("Search Query", placeholder="e.g., machine learning, web application, sistem informasi...", label_visibility="collapsed")
+
+if st.button("🔍 Search", type="primary") or query:
+    if query.strip():
+        with st.spinner("Searching..."):
+            results = search(query, model, index, metadata, top_k)
+        
+        st.markdown(f"### 📋 Found {len(results)} results")
+        
+        # Display as dataframe
+        if results:
+            df = pd.DataFrame(results)
+            st.dataframe(df, use_container_width=True, hide_index=True)
+            
+            # Detailed view
+            st.markdown("---")
+            st.markdown("### 📖 Detailed Results")
+            for result in results:
+                with st.expander(f"#{result['Rank']} - {result['Judul'][:100]}... (Score: {result['Score']})"):
+                    col1, col2 = st.columns(2)
+                    with col1:
+                        st.markdown(f"**NIM**: {result['NIM']}")
+                        st.markdown(f"**Nama**: {result['Nama']}")
+                        st.markdown(f"**Pembimbing**: {result['Pembimbing']}")
+                    with col2:
+                        st.markdown(f"**Tahun**: {result['Tahun']}")
+                        st.markdown(f"**Semester**: {result['Semester']}")
+                    st.markdown(f"**Judul Lengkap**: {result['Judul']}")
+        else:
+            st.warning("No results found")
+    else:
+        st.warning("Please enter a search query")
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+# Footer
+st.markdown("---")
+st.markdown("""
+<div style='text-align: center;'>
+    <p><a href='https://galih.eu'>Galih Hermawan</a> | Akabot Research Group</p>
+    <p>Prodi Teknik Informatika | Universitas Komputer Indonesia</p>
+    <p>Powered by Qwen3 Embedding Model</p>
+</div>
+""", unsafe_allow_html=True)