Skip to content

style: format code with Autopep8 #41

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

style: format code with Autopep8 #41

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7b795f2
Add AI-powered LLM answer plugin for SearXNG
bearlike Aug 2, 2025
48fa1e7
style: format code with Autopep8
deepsource-autofix[bot] Aug 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file modified docs/scripts.xls
View file
Open in desktop
Binary file not shown.
Binary file added docs/search_llm_assist.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
8 changes: 7 additions & 1 deletion python/searxng-addons/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,13 @@ This repository contains custom engine implementations that extend SearXNG's cap

## 🔍 Available Engines

### 1. Homepage Dashboard Integration (`dashboard_services.py`)
### 1. AI Search Assist (`search_answers_llm\plugins_langchain_llm.py`)

This SearXNG plugin generates contextual, AI-powered answers by hooking into the `post_search` process. It programmatically executes a secondary, targeted search against Google and DuckDuckGo using `SearchQuery` and `EngineRef` to gather real-time context for the user's query. This context is then sent to a LLM. The plugin injects this response as a custom `Answer` result type, overriding the default template to use a custom one with the `|safe` filter, ensuring the rich text is rendered correctly on the results page.

![SearXNG LLM Assist](/docs/search_llm_assist.png)

### 2. Homepage Dashboard Integration (`dashboard_services.py`)

Integrates with [`gethomepage/homepage`](https://github.com/gethomepage/homepage), a customizable home or startpage with Docker and service API support. This enables your home lab dashboard to become fully searchable using SearXNG.

Expand Down
211 changes: 211 additions & 0 deletions python/searxng-addons/search_answers_llm/llm_answer.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,211 @@
<div class="llm-answer-container">
<div class="llm-answer-content">
{{ answer.answer|safe }}
</div>

<style>
.llm-answer-container {
background: var(--color-answer-background);
color: var(--color-answer-font);
border-left: 4px solid var(--color-btn-background);
padding: 16px;
margin: 12px 0;
border-radius: 6px;
box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
border: 1px solid var(--color-result-border);
}

/* Header styling */
.llm-answer-container .llm-header {
margin-bottom: 12px;
display: flex;
align-items: center;
gap: 8px;
}

.llm-answer-container .llm-header strong {
color: var(--color-btn-background);
}

.llm-answer-container .llm-header span {
color: var(--color-base-font);
opacity: 0.8;
}

/* Content styling */
.llm-answer-container .llm-content {
margin-bottom: 12px;
line-height: 1.6;
}

/* Markdown-generated content styling using theme variables */
.llm-answer-container h1,
.llm-answer-container h2,
.llm-answer-container h3,
.llm-answer-container h4,
.llm-answer-container h5,
.llm-answer-container h6 {
margin-top: 16px;
margin-bottom: 8px;
color: var(--color-answer-font);
}

.llm-answer-container h2 {
font-size: 1.2em;
border-bottom: 1px solid var(--color-result-border);
padding-bottom: 4px;
}

.llm-answer-container h3 {
font-size: 1.1em;
}

.llm-answer-container ul,
.llm-answer-container ol {
margin: 8px 0;
padding-left: 20px;
}

.llm-answer-container li {
margin: 4px 0;
}

.llm-answer-container p {
margin: 8px 0;
line-height: 1.5;
}

.llm-answer-container code {
background: var(--color-doc-code-background);
color: var(--color-doc-code);
padding: 2px 4px;
border-radius: 3px;
font-family: 'Monaco', 'Menlo', 'Ubuntu Mono', monospace;
font-size: 0.9em;
}

.llm-answer-container pre {
background: var(--color-doc-code-background);
color: var(--color-doc-code);
border: 1px solid var(--color-result-border);
border-radius: 4px;
padding: 12px;
overflow-x: auto;
margin: 12px 0;
}

.llm-answer-container pre code {
background: none;
padding: 0;
}

.llm-answer-container blockquote {
border-left: 3px solid var(--color-btn-background);
margin: 12px 0;
padding-left: 12px;
color: var(--color-base-font);
font-style: italic;
opacity: 0.9;
}

.llm-answer-container strong {
color: var(--color-answer-font);
font-weight: 600;
}

.llm-answer-container em {
color: var(--color-base-font);
opacity: 0.9;
}

.llm-answer-container a {
color: var(--color-result-link-font);
text-decoration: underline;
}

.llm-answer-container a:hover {
color: var(--color-result-link-font-highlight);
}

.llm-answer-container a:visited {
color: var(--color-result-link-visited-font);
}

/* Footer styling */
.llm-answer-container .llm-footer {
border-top: 1px solid var(--color-result-border);
padding-top: 8px;
margin-top: 12px;
font-size: 0.85em;
color: var(--color-base-font);
display: flex;
justify-content: space-between;
align-items: center;
flex-wrap: wrap;
gap: 8px;
}

.llm-answer-container .llm-footer .model-info {
display: flex;
align-items: center;
gap: 12px;
flex-wrap: wrap;
}

.llm-answer-container .llm-footer .model-name {
font-weight: 600;
color: var(--color-answer-font);
}

.llm-answer-container .llm-footer .disclaimer {
opacity: 0.8;
}

/* GitHub button styling with theme support */
.llm-answer-container .github-link {
display: inline-flex;
align-items: center;
background: var(--color-toolkit-badge-background);
color: var(--color-toolkit-badge-font);
padding: 4px 8px;
border-radius: 4px;
text-decoration: none;
font-size: 0.8em;
transition: all 0.2s ease;
border: 1px solid var(--color-result-border);
}

.llm-answer-container .github-link:hover {
background: var(--color-btn-background);
color: var(--color-btn-font);
transform: translateY(-1px);
text-decoration: none;
}

.llm-answer-container .github-link svg {
width: 16px;
height: 16px;
margin-right: 4px;
fill: currentColor;
transition: transform 0.2s ease;
}

.llm-answer-container .github-link:hover svg {
transform: scale(1.1);
}

/* Responsive design */
@media (max-width: 50em) {
.llm-answer-container .llm-footer {
flex-direction: column;
align-items: flex-start;
}

.llm-answer-container .llm-footer .model-info {
flex-direction: column;
align-items: flex-start;
gap: 4px;
}
}
</style>
</div>
Loading
Loading