"""Streamlit semantic search app for SemanticSearchApp."""
from __future__ import annotations
import sys
import subprocess
from pathlib import Path
from typing import List
import streamlit as st
from sentence_transformers import SentenceTransformer
from search_engine import SemanticSearchEngine
# ================= CONFIG =================
DATASET_PATH = Path("data/stackoverflow_sample_3000.json")
# ================= STYLES =================
def inject_styles():
st.markdown(
"""
""",
unsafe_allow_html=True,
)
# ================= DATASET SETUP =================
def ensure_dataset():
if not DATASET_PATH.exists():
with st.spinner("Preparing dataset (first run only)..."):
script = Path(__file__).parent / "prepare_stackoverflow_sample.py"
result = subprocess.run(
[sys.executable, str(script)],
capture_output=True,
text=True,
)
if result.returncode != 0:
st.error(f"Dataset preparation failed:\n\n{result.stderr}")
st.stop()
# ================= ENGINE =================
@st.cache_resource(show_spinner=False)
def load_engine() -> SemanticSearchEngine:
return SemanticSearchEngine(DATASET_PATH)
# ================= EMBEDDING =================
@st.cache_resource(show_spinner=False)
def load_embedder() -> SentenceTransformer:
return SentenceTransformer("all-MiniLM-L6-v2")
def get_query_embedding(query: str) -> List[float]:
model = load_embedder()
return model.encode(query).tolist()
# ================= MAIN APP =================
def main():
st.set_page_config(
page_title="SemanticSearchApp",
page_icon="⬡",
layout="centered",
)
inject_styles()
# ── Brand header ──
st.markdown(
"""
""",
unsafe_allow_html=True,
)
ensure_dataset()
# ── Query input ──
query = st.text_area(
"Query",
placeholder="e.g. How do I reverse a list in Python?",
height=110,
)
run = st.button("Search")
if not run or not query.strip():
if run and not query.strip():
st.info("Please enter a query before searching.")
elif not run:
st.markdown(
''
"Type a programming question above and hit Search.
",
unsafe_allow_html=True,
)
return
# ── Run search ──
try:
with st.spinner("Running semantic search…"):
engine = load_engine()
query_embedding = get_query_embedding(query.strip())
results = engine.search(query_embedding, top_k=5)
except Exception as e:
st.error(f"Search failed: {e}")
return
# ── Results ──
st.markdown(
f'Top {len(results)} results
',
unsafe_allow_html=True,
)
for i, item in enumerate(results, start=1):
score_pct = f"{item['score'] * 100:.1f}% match"
st.markdown(
f"""
Result #{i}
{item['question']}
{item['answer']}
⬡ {score_pct}
""",
unsafe_allow_html=True,
)
if __name__ == "__main__":
main()