jpmschweitzer/library-desk
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 5 Wiki Activity

fix: rename generation model setting to ollama_llm_model to avoid OLLAMA_MODEL env collision

Browse Source 
The deployed container sets OLLAMA_MODEL=nomic-embed-text for embeddings,
which shadowed the generation-model setting and broke Phase 0 keyword
extraction and Phase 4 LLM re-ranking on every request. The setting is now
ollama_llm_model (env: OLLAMA_LLM_MODEL, default gemma4:e2b), startup logs
the resolved generation model, and Phase 0/Phase 4 LLM calls are wrapped in
a 12s asyncio.wait_for with graceful fallback so a hung call cannot gate
retrieval for the full 120s client timeout.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
jpmschweitzer
2026-07-14 09:57:57 +02:00
co-authored by Claude Fable 5
parent d0e712760d
commit 94482bcb59
8 changed files with 51 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+1 -1
View File
@@ -9,7 +9,7 @@ SEARXNG_URL=http://192.168.86.149:8080
REDIS_HOST=192.168.86.149
PAPERLESS_URL=http://192.168.86.149:8091
OLLAMA_MODEL=mistral-nemo-large:latest
OLLAMA_LLM_MODEL=gemma4:e2b
OLLAMA_EMBEDDING_MODEL=nomic-embed-text
# Wiki.js auth