Spaces:
Sleeping
Sleeping
File size: 16,216 Bytes
614f1e2 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 |
# main.py - FastAPI Backend
from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from fastapi.staticfiles import StaticFiles
from fastapi.responses import HTMLResponse
from pydantic import BaseModel
import nltk
from nltk.tokenize import sent_tokenize
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity
import numpy as np
# Download required NLTK data
nltk.download('punkt', quiet=True)
nltk.download('punkt_tab')
# Initialize FastAPI app
app = FastAPI(title="Simple Search Engine")
# Add CORS middleware
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
# Define the document database
documents = {
"doc1": """
A new AI analytics tool has been released by TechCorp.
This tool uses advanced machine learning algorithms to process large datasets.
It can provide real-time insights and predictive analytics for businesses.
The tool integrates seamlessly with existing data infrastructure.
Companies can now make data-driven decisions faster than ever before.
The AI engine continuously learns from new data to improve accuracy.
""",
"doc2": """
The quarterly finance report shows strong revenue growth.
Operating expenses have decreased by 15% compared to last quarter.
Net profit margins have improved significantly across all divisions.
The company's cash flow remains healthy with substantial reserves.
Investment in new projects is expected to yield returns next year.
Shareholders can expect increased dividends this quarter.
""",
"doc3": """
Cloud infrastructure services from AWS and Azure are becoming essential.
Companies are migrating their legacy systems to the cloud for better scalability.
AWS offers a wide range of compute and storage options.
Azure provides excellent integration with Microsoft enterprise products.
Both platforms support hybrid cloud deployments for flexibility.
Security and compliance features are continuously being enhanced.
""",
"doc4": """
Our new marketing campaign focuses on SEO optimization strategies.
We are targeting high-value keywords to increase organic traffic.
Social media engagement has improved by 40% this month.
Content marketing efforts are driving more qualified leads.
The campaign includes email marketing and paid search ads.
We expect to see ROI improvements within the next quarter.
""",
"doc5": """
The AI tool leverages machine learning for predictive maintenance.
Machine learning models can detect patterns in equipment behavior.
This AI-powered solution reduces downtime and operational costs.
Deep learning techniques are applied to analyze sensor data.
The system continuously learns and adapts to new scenarios.
AI and machine learning are transforming industrial operations.
"""
}
# Function to chunk documents
def chunk_documents(documents, sentences_per_chunk=3):
chunks = []
chunk_metadata = []
for doc_id, text in documents.items():
sentences = sent_tokenize(text.strip())
for i in range(0, len(sentences), sentences_per_chunk):
chunk = ' '.join(sentences[i:i+sentences_per_chunk])
chunks.append(chunk)
chunk_metadata.append({
'doc_id': doc_id,
'chunk_index': i // sentences_per_chunk,
'text': chunk
})
return chunks, chunk_metadata
# Initialize model and process documents at startup
print("Initializing search engine...")
model = SentenceTransformer('all-MiniLM-L6-v2')
chunks, chunk_metadata = chunk_documents(documents)
chunk_embeddings = model.encode(chunks)
print(f"Search engine ready! {len(chunks)} chunks indexed.")
# Pydantic models
class SearchQuery(BaseModel):
query: str
class SearchResult(BaseModel):
rank: int
doc_id: str
similarity_score: float
text: str
# API Endpoints
@app.get("/")
async def read_root():
html_content = """
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Simple Search Engine</title>
<style>
* {
margin: 0;
padding: 0;
box-sizing: border-box;
}
body {
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
min-height: 100vh;
padding: 20px;
}
.container {
max-width: 900px;
margin: 0 auto;
}
.header {
text-align: center;
color: white;
margin-bottom: 40px;
padding-top: 60px;
}
.header h1 {
font-size: 3em;
margin-bottom: 10px;
text-shadow: 2px 2px 4px rgba(0,0,0,0.3);
}
.header p {
font-size: 1.2em;
opacity: 0.9;
}
.search-box {
background: white;
border-radius: 50px;
padding: 10px 20px;
box-shadow: 0 8px 30px rgba(0,0,0,0.3);
display: flex;
align-items: center;
margin-bottom: 40px;
}
.search-box input {
flex: 1;
border: none;
outline: none;
font-size: 1.1em;
padding: 10px;
}
.search-box button {
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
border: none;
color: white;
padding: 12px 30px;
border-radius: 25px;
font-size: 1em;
cursor: pointer;
transition: transform 0.2s;
font-weight: bold;
}
.search-box button:hover {
transform: scale(1.05);
}
.search-box button:active {
transform: scale(0.95);
}
.loading {
text-align: center;
color: white;
font-size: 1.2em;
margin: 20px 0;
display: none;
}
.loading.show {
display: block;
}
.results {
display: none;
}
.results.show {
display: block;
}
.result-card {
background: white;
border-radius: 15px;
padding: 25px;
margin-bottom: 20px;
box-shadow: 0 4px 15px rgba(0,0,0,0.2);
transition: transform 0.2s, box-shadow 0.2s;
animation: slideIn 0.5s ease-out;
}
@keyframes slideIn {
from {
opacity: 0;
transform: translateY(20px);
}
to {
opacity: 1;
transform: translateY(0);
}
}
.result-card:hover {
transform: translateY(-5px);
box-shadow: 0 6px 25px rgba(0,0,0,0.3);
}
.result-header {
display: flex;
justify-content: space-between;
align-items: center;
margin-bottom: 15px;
}
.result-rank {
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
color: white;
padding: 5px 15px;
border-radius: 20px;
font-weight: bold;
font-size: 0.9em;
}
.result-doc {
color: #666;
font-size: 0.9em;
font-weight: 600;
}
.result-score {
background: #e8f5e9;
color: #2e7d32;
padding: 5px 12px;
border-radius: 15px;
font-size: 0.85em;
font-weight: bold;
}
.result-text {
color: #333;
line-height: 1.6;
font-size: 1em;
}
.no-results {
text-align: center;
color: white;
font-size: 1.2em;
margin-top: 40px;
display: none;
}
.no-results.show {
display: block;
}
.stats {
text-align: center;
color: white;
margin-bottom: 30px;
font-size: 1.1em;
opacity: 0.9;
}
</style>
</head>
<body>
<div class="container">
<div class="header">
<h1>🔍 SimpleSearch</h1>
<p>Your intelligent document search engine</p>
</div>
<div class="search-box">
<input type="text" id="searchInput" placeholder="Search for documents..." />
<button onclick="performSearch()">Search</button>
</div>
<div class="loading" id="loading">
<p>🔄 Searching...</p>
</div>
<div class="stats" id="stats"></div>
<div class="results" id="results"></div>
<div class="no-results" id="noResults">
<p>No results found. Try a different query!</p>
</div>
</div>
<script>
// Allow Enter key to trigger search
document.getElementById('searchInput').addEventListener('keypress', function(e) {
if (e.key === 'Enter') {
performSearch();
}
});
async function performSearch() {
const query = document.getElementById('searchInput').value.trim();
if (!query) {
alert('Please enter a search query!');
return;
}
// Show loading, hide results
document.getElementById('loading').classList.add('show');
document.getElementById('results').classList.remove('show');
document.getElementById('noResults').classList.remove('show');
document.getElementById('stats').innerHTML = '';
try {
const response = await fetch('/search', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
},
body: JSON.stringify({ query: query })
});
if (!response.ok) {
throw new Error('Search failed');
}
const data = await response.json();
displayResults(data, query);
} catch (error) {
console.error('Error:', error);
alert('Search failed. Please try again.');
} finally {
document.getElementById('loading').classList.remove('show');
}
}
function displayResults(results, query) {
const resultsDiv = document.getElementById('results');
const noResultsDiv = document.getElementById('noResults');
const statsDiv = document.getElementById('stats');
if (results.length === 0) {
noResultsDiv.classList.add('show');
return;
}
statsDiv.innerHTML = `Found <strong>${results.length}</strong> results for "<strong>${query}</strong>"`;
resultsDiv.innerHTML = '';
results.forEach(result => {
const card = document.createElement('div');
card.className = 'result-card';
card.style.animationDelay = `${(result.rank - 1) * 0.1}s`;
card.innerHTML = `
<div class="result-header">
<div style="display: flex; gap: 10px; align-items: center;">
<span class="result-rank">Rank ${result.rank}</span>
<span class="result-doc">${result.doc_id.toUpperCase()}</span>
</div>
<span class="result-score">Score: ${result.similarity_score.toFixed(4)}</span>
</div>
<div class="result-text">${result.text}</div>
`;
resultsDiv.appendChild(card);
});
resultsDiv.classList.add('show');
}
</script>
</body>
</html>
"""
return HTMLResponse(content=html_content)
@app.post("/search", response_model=list[SearchResult])
async def search(search_query: SearchQuery):
"""
Search endpoint that takes a query and returns top 5 relevant chunks
"""
if not search_query.query.strip():
raise HTTPException(status_code=400, detail="Query cannot be empty")
try:
# Encode the query
query_embedding = model.encode([search_query.query])
# Calculate cosine similarity
similarities = cosine_similarity(query_embedding, chunk_embeddings)[0]
# Create results
results = []
for idx, score in enumerate(similarities):
results.append({
'chunk_index': idx,
'doc_id': chunk_metadata[idx]['doc_id'],
'similarity_score': float(score),
'text': chunk_metadata[idx]['text']
})
# Sort by similarity score
results_sorted = sorted(results, key=lambda x: x['similarity_score'], reverse=True)
# Return top 5 results
top_results = []
for rank, result in enumerate(results_sorted[:5], 1):
top_results.append(SearchResult(
rank=rank,
doc_id=result['doc_id'],
similarity_score=result['similarity_score'],
text=result['text']
))
return top_results
except Exception as e:
raise HTTPException(status_code=500, detail=f"Search error: {str(e)}")
@app.get("/health")
async def health_check():
"""Health check endpoint"""
return {"status": "healthy", "total_chunks": len(chunks)}
if __name__ == "__main__":
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=8000) |