Files
momentry_core/docs_v1.0/doc/06_search.html

288 lines
13 KiB
HTML

<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>06 Search - Momentry API Docs</title>
<style>
* { margin: 0; padding: 0; box-sizing: border-box; }
body { font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif; background: #f5f5f5; color: #333; padding: 40px; }
.container { max-width: 960px; margin: 0 auto; background: white; border-radius: 12px; box-shadow: 0 2px 12px rgba(0,0,0,0.08); padding: 40px; }
h1 { font-size: 24px; margin: 24px 0 12px; }
h2 { font-size: 20px; margin: 20px 0 10px; color: #222; }
h3 { font-size: 16px; margin: 16px 0 8px; color: #444; }
p { line-height: 1.6; margin: 8px 0; }
table { border-collapse: collapse; width: 100%; margin: 12px 0; font-size: 14px; }
th, td { border: 1px solid #ddd; padding: 8px 12px; text-align: left; }
th { background: #f0f0f0; font-weight: 600; }
code { background: #f0f0f0; padding: 2px 6px; border-radius: 3px; font-size: 13px; }
pre { background: #f8f8f8; border: 1px solid #ddd; border-radius: 6px; padding: 12px; overflow-x: auto; margin: 12px 0; }
pre code { background: none; padding: 0; }
a { color: #0066cc; }
.back { display: inline-block; margin-bottom: 20px; color: #666; }
.back:hover { color: #333; }
.topbar { display: flex; justify-content: space-between; align-items: center; margin-bottom: 20px; }
.logout-btn { font-size: 13px; color: #999; text-decoration: none; }
.logout-btn:hover { color: #cc0000; }
</style>
</head>
<body>
<div class="container">
<div class="topbar">
<a class="back" href="index.html">&larr; Back to index</a>
<a class="logout-btn" href="#" onclick="fetch('/api/v1/auth/logout',{method:'POST'}).then(()=>window.location.reload());return false">Logout</a>
</div>
<!-- module: search -->
<!-- description: Vector search, BM25, smart search, universal search, visual search -->
<!-- depends: 01_auth -->
<h2>Search APIs</h2>
<h3><code>POST /api/v1/search/smart</code></h3>
<p><strong>Auth</strong>: Required
<strong>Scope</strong>: file-level</p>
<p>Semantic vector search using EmbeddingGemma-300m. Generates a query embedding via EmbeddingGemma (port 11436), then searches pgvector <code>story_parent</code> and <code>llm_parent</code> chunks by cosine similarity.</p>
<h4>Request Parameters</h4>
<table class="table">
<thead>
<tr>
<th>Field</th>
<th>Type</th>
<th>Required</th>
<th>Default</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>file_uuid</code></td>
<td>string</td>
<td>Yes</td>
<td></td>
<td>File UUID to search within</td>
</tr>
<tr>
<td><code>query</code></td>
<td>string</td>
<td>Yes</td>
<td></td>
<td>Search text</td>
</tr>
<tr>
<td><code>limit</code></td>
<td>integer</td>
<td>No</td>
<td>5</td>
<td>Max results to return</td>
</tr>
<tr>
<td><code>page</code></td>
<td>integer</td>
<td>No</td>
<td>1</td>
<td>Page number</td>
</tr>
<tr>
<td><code>page_size</code></td>
<td>integer</td>
<td>No</td>
<td>5</td>
<td>Items per page</td>
</tr>
</tbody>
</table>
<h4>Example</h4>
<div class="codehilite"><pre><span></span><code>curl<span class="w"> </span>-s<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span><span class="s2">&quot;</span><span class="nv">$API</span><span class="s2">/api/v1/search/smart&quot;</span><span class="w"> </span><span class="se">\</span>
<span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Content-Type: application/json&quot;</span><span class="w"> </span><span class="se">\</span>
<span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer </span><span class="nv">$JWT</span><span class="s2">&quot;</span><span class="w"> </span><span class="se">\</span>
<span class="w"> </span>-d<span class="w"> </span><span class="s1">&#39;{&quot;file_uuid&quot;: &quot;&#39;</span><span class="s2">&quot;</span><span class="nv">$FILE_UUID</span><span class="s2">&quot;</span><span class="s1">&#39;&quot;, &quot;query&quot;: &quot;Audrey Hepburn&quot;}&#39;</span>
</code></pre></div>
<h4>Response (200)</h4>
<div class="codehilite"><pre><span></span><code><span class="p">{</span>
<span class="w"> </span><span class="nt">&quot;query&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;Audrey Hepburn&quot;</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;results&quot;</span><span class="p">:</span><span class="w"> </span><span class="p">[</span>
<span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="nt">&quot;parent_id&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">1087822</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;scene_order&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">1087822</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;start_frame&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">104438</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;end_frame&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">104538</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;fps&quot;</span><span class="p">:</span><span class="w"> </span><span class="mf">24.0</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;start_time&quot;</span><span class="p">:</span><span class="w"> </span><span class="mf">4351.6</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;end_time&quot;</span><span class="p">:</span><span class="w"> </span><span class="mf">4355.76</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;summary&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;[4352s-4356s, 4s] Cast: Audrey Hepburn. Total: 2 lines, 10 words. Speakers: Audrey Hepburn (2 lines)&quot;</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;similarity&quot;</span><span class="p">:</span><span class="w"> </span><span class="mf">0.67</span>
<span class="w"> </span><span class="p">}</span>
<span class="w"> </span><span class="p">],</span>
<span class="w"> </span><span class="nt">&quot;page&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">1</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;page_size&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">5</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;strategy&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;semantic_vector_search&quot;</span>
<span class="p">}</span>
</code></pre></div>
<hr />
<h3><code>POST /api/v1/search/universal</code></h3>
<p><strong>Auth</strong>: Required
<strong>Scope</strong>: file-level</p>
<p>Multi-type BM25 full-text search across chunks, frames, and persons. Uses PostgreSQL <code>tsvector</code>.</p>
<h4>Request Parameters</h4>
<table class="table">
<thead>
<tr>
<th>Field</th>
<th>Type</th>
<th>Required</th>
<th>Default</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td><code>query</code></td>
<td>string</td>
<td>Yes</td>
<td></td>
<td>Search text</td>
</tr>
<tr>
<td><code>file_uuid</code></td>
<td>string</td>
<td>No</td>
<td></td>
<td>Restrict to specific file</td>
</tr>
<tr>
<td><code>types</code></td>
<td>string[]</td>
<td>No</td>
<td><code>["chunk","frame","person"]</code></td>
<td>Search types</td>
</tr>
<tr>
<td><code>limit</code></td>
<td>integer</td>
<td>No</td>
<td>10</td>
<td>Max results per type</td>
</tr>
<tr>
<td><code>page</code></td>
<td>integer</td>
<td>No</td>
<td>1</td>
<td>Page number</td>
</tr>
<tr>
<td><code>page_size</code></td>
<td>integer</td>
<td>No</td>
<td>20</td>
<td>Items per page</td>
</tr>
</tbody>
</table>
<h4>Example</h4>
<div class="codehilite"><pre><span></span><code>curl<span class="w"> </span>-s<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span><span class="s2">&quot;</span><span class="nv">$API</span><span class="s2">/api/v1/search/universal&quot;</span><span class="w"> </span><span class="se">\</span>
<span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Content-Type: application/json&quot;</span><span class="w"> </span><span class="se">\</span>
<span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Authorization: Bearer </span><span class="nv">$JWT</span><span class="s2">&quot;</span><span class="w"> </span><span class="se">\</span>
<span class="w"> </span>-d<span class="w"> </span><span class="s1">&#39;{&quot;file_uuid&quot;: &quot;&#39;</span><span class="s2">&quot;</span><span class="nv">$FILE_UUID</span><span class="s2">&quot;</span><span class="s1">&#39;&quot;, &quot;query&quot;: &quot;Cary Grant&quot;}&#39;</span>
</code></pre></div>
<h4>Response (200)</h4>
<div class="codehilite"><pre><span></span><code><span class="p">{</span>
<span class="w"> </span><span class="nt">&quot;results&quot;</span><span class="p">:</span><span class="w"> </span><span class="p">[</span>
<span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="nt">&quot;type&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;chunk&quot;</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;chunk_id&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;bd80fec92b0b6963d177a2c55bf713e2_2&quot;</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;chunk_type&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;story_child&quot;</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;start_frame&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">5103</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;end_frame&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">5127</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;start_time&quot;</span><span class="p">:</span><span class="w"> </span><span class="mf">212.64</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;end_time&quot;</span><span class="p">:</span><span class="w"> </span><span class="mf">213.64</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;text&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;[213s-214s] Cary Grant: \&quot;Olá!\&quot;&quot;</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;score&quot;</span><span class="p">:</span><span class="w"> </span><span class="mf">0.9</span>
<span class="w"> </span><span class="p">}</span>
<span class="w"> </span><span class="p">],</span>
<span class="w"> </span><span class="nt">&quot;total&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">20</span><span class="p">,</span>
<span class="w"> </span><span class="nt">&quot;took_ms&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">18</span>
<span class="p">}</span>
</code></pre></div>
<hr />
<h3><code>POST /api/v1/search/frames</code></h3>
<p><strong>Auth</strong>: Required
<strong>Scope</strong>: file-level</p>
<p>Search face detection frames by identity name or trace ID.</p>
<hr />
<h3><code>POST /api/v1/search/identity_text</code></h3>
<p><strong>Auth</strong>: Required
<strong>Scope</strong>: file-level</p>
<p>Search text chunks spoken by a specific identity.</p>
<hr />
<h3>Visual Search</h3>
<table class="table">
<thead>
<tr>
<th>Method</th>
<th>Endpoint</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td>POST</td>
<td><code>/api/v1/search/visual</code></td>
<td>Search visual chunks</td>
</tr>
<tr>
<td>POST</td>
<td><code>/api/v1/search/visual/class</code></td>
<td>Search by object class</td>
</tr>
<tr>
<td>POST</td>
<td><code>/api/v1/search/visual/density</code></td>
<td>Search by object density</td>
</tr>
<tr>
<td>POST</td>
<td><code>/api/v1/search/visual/combination</code></td>
<td>Search by object combination</td>
</tr>
<tr>
<td>POST</td>
<td><code>/api/v1/search/visual/stats</code></td>
<td>Visual chunk statistics</td>
</tr>
</tbody>
</table>
<h4>Embedding Model</h4>
<table class="table">
<thead>
<tr>
<th>Detail</th>
<th>Value</th>
</tr>
</thead>
<tbody>
<tr>
<td><strong>Model</strong></td>
<td>EmbeddingGemma-300m</td>
</tr>
<tr>
<td><strong>Endpoint</strong></td>
<td><code>POST /api/v1/embeddings</code> on port 11436</td>
</tr>
<tr>
<td><strong>Dimension</strong></td>
<td>768</td>
</tr>
<tr>
<td><strong>Storage</strong></td>
<td>pgvector (<code>chunk.embedding</code> column)</td>
</tr>
</tbody>
</table>
<hr />
<p><em>Updated: 2026-05-19 12:49:24</em></p>
</div>
</body>
</html>