TySS-Dev/ollama-ai-answers-searxng
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add optional ollama unload after response, PR credit to @aestheticjmack

Browse Source
This commit is contained in:
cra88y/pc
2026-03-29 21:29:41 -05:00
parent 5b3faf57ce eda407a33d
commit 6947257575
2 changed files with 15 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -2
View File
@@ -44,8 +44,8 @@ Configure via the environment variables:
- `LLM_CONTEXT_SHALLOW_COUNT`: Results with headlines only (additional breadth). Default `15`.
- `LLM_TABS`: Tab whitelist, comma delimiter. Default `general,science,it,news`.
- `LLM_INTERACTIVE`: UI mode. Default is `true` (interactive: copy, regenerate, follow up). Set to `false` for simple response only mode.
* `LLM_OLLAMA_UNLOAD_AFTER`: If true, unload Ollama model immediately after each response (calls `/api/chat` with `keep_alive: 0`).
* `LLM_OLLAMA_UNLOAD_URL`: Override unload endpoint (default derived from `LLM_URL` host/port).
- `LLM_QUESTION_MARK_REQUIRED`: Only trigger AI answers when the query contains `?`. Default `false`.
- `LLM_OLLAMA_UNLOAD_AFTER`: Unload Ollama model after each response. Default `false`.
## How It Works
1 user initial search