jason/searxng
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[mod] ai_summary plugin: switch to the OpenAI chat completions API

Browse Source 
Talk to the LLM server via GET /v1/models and POST /v1/chat/completions
(SSE) instead of Ollama's native API.  Any OpenAI compatible server now
works (Ollama, vLLM, llama.cpp, LM Studio, Hugging Face TGI, ...);
Ollama serves this API natively, existing setups keep working unchanged.

The Ollama specific keep_alive option is dropped, the ai_summary.grounding
setting is added as instance wide default of the grounding preference.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
jasonwitty
2026-07-28 13:01:24 -07:00
co-authored by Claude Fable 5
parent 112541db28
commit 4abb7dba67
6 changed files with 70 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files
searx/templates/simple/preferences/ai_summary.html
+2 -2
View File
@@ -1,6 +1,6 @@
{%- if 'ai_summary_server' not in locked_preferences -%}
<fieldset>{{- '' -}}
<legend id="pref_ai_summary_server">{{- _('Ollama server URL') -}}</legend>{{- '' -}}
<legend id="pref_ai_summary_server">{{- _('AI server URL') -}}</legend>{{- '' -}}
<div class="value">{{- '' -}}
<input name="ai_summary_server" aria-labelledby="pref_ai_summary_server" type="text"
autocomplete="off" spellcheck="false" autocorrect="off"
@@ -8,7 +8,7 @@
value="{{ preferences.get_value('ai_summary_server') }}">{{- '' -}}
</div>{{- '' -}}
<div class="description">
{{- _('URL of the Ollama server that generates the summaries, e.g. http://192.168.1.10:11434.') -}}
{{- _('URL of the OpenAI compatible LLM server that generates the summaries (e.g. Ollama, LM Studio, vLLM), e.g. http://192.168.1.10:11434.') -}}
{{- ' ' -}}
{%- if ai_summary_default_server -%}
{{- _('Leave empty to use the default of this instance.') -}}