File size: 5,376 Bytes
7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 eba760d 7ce6975 | 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 | import streamlit as st
import chromadb
from sentence_transformers import SentenceTransformer
import uuid
# ==========================================
# PAGE CONFIG
# ==========================================
st.set_page_config(
page_title="Semantic Search Engine",
page_icon="🔍",
layout="wide"
)
# ==========================================
# CUSTOM CSS
# ==========================================
st.markdown("""
<style>
.main {
padding-top: 1rem;
}
.block-container {
padding-top: 2rem;
}
.result-box {
padding: 1rem;
border-radius: 12px;
border: 1px solid #333;
margin-bottom: 10px;
}
</style>
""", unsafe_allow_html=True)
# ==========================================
# TITLE
# ==========================================
st.title("🔍 Semantic Search Engine")
st.caption(
"Search documents using semantic similarity powered by Hugging Face embeddings."
)
# ==========================================
# LOAD MODEL
# ==========================================
@st.cache_resource
def load_model():
return SentenceTransformer(
"sentence-transformers/all-MiniLM-L6-v2"
)
model = load_model()
# ==========================================
# CHROMADB
# ==========================================
client = chromadb.PersistentClient(
path="./chroma_db"
)
collection = client.get_or_create_collection(
name="documents"
)
# ==========================================
# SIDEBAR
# ==========================================
with st.sidebar:
st.header("⚙️ Settings")
top_k = st.slider(
"Number of Results",
min_value=1,
max_value=10,
value=5
)
st.markdown("---")
st.info(
"Semantic Search compares meanings instead of matching exact keywords."
)
# ==========================================
# DATABASE STATS
# ==========================================
st.markdown("## 📊 Database Statistics")
col1, col2 = st.columns(2)
with col1:
st.metric(
"Documents Stored",
collection.count()
)
with col2:
st.metric(
"Embedding Model",
"MiniLM-L6-v2"
)
# ==========================================
# DOCUMENT INPUT
# ==========================================
st.markdown("---")
st.markdown("## 📥 Add Documents")
documents = st.text_area(
"Enter documents (one document per line)",
height=220,
placeholder="""
Python is a programming language.
FastAPI is used to build APIs.
Machine learning learns patterns from data.
ChromaDB stores embeddings.
"""
)
if st.button("💾 Store Documents"):
docs = [
doc.strip()
for doc in documents.split("\n")
if doc.strip()
]
if len(docs) == 0:
st.warning("Please enter at least one document.")
else:
with st.spinner("Generating embeddings..."):
embeddings = model.encode(
docs
).tolist()
collection.add(
ids=[
str(uuid.uuid4())
for _ in docs
],
documents=docs,
embeddings=embeddings
)
st.success(
f"{len(docs)} document(s) stored successfully."
)
st.rerun()
# ==========================================
# SEARCH SECTION
# ==========================================
st.markdown("---")
st.markdown("## 🔎 Search")
query = st.text_input(
"Enter your search query",
placeholder="How can I build an API?"
)
if st.button(
"🚀 Search",
use_container_width=True
):
if collection.count() == 0:
st.error(
"No documents available. Add documents first."
)
elif not query.strip():
st.warning(
"Please enter a search query."
)
else:
with st.spinner(
"Searching similar documents..."
):
query_embedding = model.encode(
query
).tolist()
results = collection.query(
query_embeddings=[
query_embedding
],
n_results=min(
top_k,
collection.count()
)
)
docs = results["documents"][0]
distances = results["distances"][0]
st.markdown("---")
st.markdown("## 📄 Search Results")
for rank, (doc, distance) in enumerate(
zip(docs, distances),
start=1
):
# Relevance Label
if distance < 0.7:
relevance = "🟢 Highly Relevant"
elif distance < 1.2:
relevance = "🟡 Relevant"
else:
relevance = "🔴 Weak Match"
with st.expander(
f"#{rank} | {relevance}"
):
st.write(doc)
st.caption(
f"Distance Score: {distance:.4f}"
)
# ==========================================
# FOOTER
# ==========================================
st.markdown("---")
|