retoor
f101ffdc5e
This commit introduces a full-featured agent architecture including persistent memory storage using vector embeddings, multi-step planning capabilities with dynamic replanning, and an extensible tool registry supporting custom function definitions. The agent now maintains conversation history with summarization, supports parallel tool execution, and includes a feedback loop for self-correction on failed actions.
26 lines
1.2 KiB
HTML
26 lines
1.2 KiB
HTML
<div class="docs-search">
|
|
<h1>Search documentation</h1>
|
|
<form class="docs-search-bigform" method="get" action="/docs/search.html" role="search">
|
|
<input type="search" name="q" value="{{ search_query|default('', true) }}" placeholder="Search the docs…" aria-label="Search documentation" class="docs-search-input" autofocus>
|
|
<button type="submit" class="btn btn-primary">Search</button>
|
|
</form>
|
|
|
|
{% if search_query %}
|
|
{% if search_results %}
|
|
<p class="docs-search-count">{{ search_results|length }} result{{ '' if search_results|length == 1 else 's' }} for "{{ search_query }}"</p>
|
|
<ul class="docs-search-results">
|
|
{% for result in search_results %}
|
|
<li class="docs-search-result">
|
|
<a class="docs-search-result-title" href="{{ result.url }}">{{ result.title }}</a>
|
|
<p class="docs-search-snippet">{{ result.snippet | safe }}</p>
|
|
</li>
|
|
{% endfor %}
|
|
</ul>
|
|
{% else %}
|
|
<p class="docs-search-empty">No results for "{{ search_query }}".</p>
|
|
{% endif %}
|
|
{% else %}
|
|
<p class="docs-search-hint">Type a query to search across every documentation page.</p>
|
|
{% endif %}
|
|
</div>
|