gitea-admin/gh-christianlouis-docuelevate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(similarity): add document similarity detection with embeddings and cosine similarity

Browse Source 
Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-03-01 20:38:52 +00:00
parent 2842b4ac46
commit 9748103782
7 changed files with 858 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
frontend/templates/file_detail.html
+87
View File
@@ -951,7 +951,76 @@
{% if processed_file_exists %}
loadPDF('processed', fileId);
{% endif %}
// Load similar documents
loadSimilarDocuments(fileId);
});
// Similar documents loading
async function loadSimilarDocuments(fileId) {
const loadingDiv = document.getElementById('similar-documents-loading');
const contentDiv = document.getElementById('similar-documents-content');
const emptyDiv = document.getElementById('similar-documents-empty');
const errorDiv = document.getElementById('similar-documents-error');
try {
const response = await fetch(`/api/files/${fileId}/similar?limit=5&threshold=0.3`);
if (!response.ok) {
throw new Error(response.statusText || 'Request failed');
}
const data = await response.json();
loadingDiv.style.display = 'none';
if (!data.similar_documents || data.similar_documents.length === 0) {
emptyDiv.style.display = 'block';
if (data.message) {
emptyDiv.querySelector('p').textContent = data.message;
}
return;
}
// Build the results HTML
let html = '<div style="display: grid; gap: 0.75rem;">';
for (const doc of data.similar_documents) {
const scorePercent = Math.round(doc.similarity_score * 100);
const title = doc.document_title || doc.original_filename || 'Untitled';
const filename = doc.original_filename || 'Unknown';
const createdAt = doc.created_at ? new Date(doc.created_at).toLocaleDateString() : '';
html += `
<a href="/files/${doc.file_id}/detail" style="text-decoration: none; color: inherit;">
<div style="display: flex; align-items: center; gap: 1rem; padding: 0.75rem 1rem; background-color: #f7fafc; border-radius: 0.5rem; border: 1px solid #e2e8f0; transition: border-color 0.2s;">
<div style="flex-shrink: 0; width: 48px; height: 48px; border-radius: 50%; display: flex; align-items: center; justify-content: center; font-weight: 700; font-size: 0.875rem; color: white; background-color: ${scorePercent >= 80 ? '#48bb78' : scorePercent >= 50 ? '#ecc94b' : '#a0aec0'};">
${scorePercent}%
</div>
<div style="flex: 1; min-width: 0;">
<div style="font-weight: 600; color: #2d3748; white-space: nowrap; overflow: hidden; text-overflow: ellipsis;" title="${title}">
${title}
</div>
<div style="font-size: 0.75rem; color: #718096; white-space: nowrap; overflow: hidden; text-overflow: ellipsis;">
${filename}${createdAt ? ' · ' + createdAt : ''}
</div>
</div>
<div style="flex-shrink: 0; color: #a0aec0;">
<i class="fas fa-chevron-right" aria-hidden="true"></i>
</div>
</div>
</a>
`;
}
html += '</div>';
contentDiv.innerHTML = html;
contentDiv.style.display = 'block';
} catch (error) {
console.error('Error loading similar documents:', error);
loadingDiv.style.display = 'none';
errorDiv.style.display = 'block';
document.getElementById('similar-documents-error-msg').textContent =
'Failed to load similar documents: ' + error.message;
}
}
</script>
{% endif %}
{% endblock %}
@@ -1527,6 +1596,24 @@
</div>
{% endif %}
<!-- Similar Documents Card -->
<div class="detail-card" id="similar-documents-card">
<h3><i class="fas fa-copy" aria-hidden="true"></i> Similar Documents</h3>
<div id="similar-documents-loading" style="text-align: center; padding: 2rem; color: #718096;">
<i class="fas fa-spinner fa-spin" aria-hidden="true" style="font-size: 1.5rem; margin-bottom: 0.5rem;"></i>
<p>Searching for similar documents…</p>
</div>
<div id="similar-documents-content" style="display: none;"></div>
<div id="similar-documents-empty" style="display: none; text-align: center; padding: 2rem; color: #718096;">
<i class="fas fa-search" aria-hidden="true" style="font-size: 2rem; margin-bottom: 0.5rem; opacity: 0.5;"></i>
<p>No similar documents found.</p>
</div>
<div id="similar-documents-error" style="display: none; text-align: center; padding: 2rem; color: #991B1B;">
<i class="fas fa-exclamation-triangle" aria-hidden="true" style="font-size: 2rem; margin-bottom: 0.5rem;"></i>
<p id="similar-documents-error-msg">Failed to load similar documents.</p>
</div>
</div>
<!-- File Preview Card -->
{% if original_file_exists or processed_file_exists %}
<div class="detail-card">