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/settings.yml
+5 -3
View File
@@ -292,14 +292,16 @@ plugins:
#
# ai_summary:
#
# # Base URL of the Ollama server; without this URL the plugin is inactive.
# # Base URL of an OpenAI compatible LLM server (Ollama, vLLM, LM Studio,
# # llama.cpp, Hugging Face TGI, ...), used as the default for the
# # ai_summary_server preference.
# base_url: "http://127.0.0.1:11434"
#
# # Default model; if empty, the first entry of models: is used.
# model: "llama3.2:3b"
#
# # Models the user can select from in the preferences; if empty, the list
# # is requested from the Ollama server (GET /api/tags) at startup.
# # Models suggested to the user in the preferences; if empty, the list
# # is requested from the LLM server (GET /v1/models) at startup.
# models:
# - "llama3.2:3b"
# - "gemma3:4b"