diff --git a/vars/main.yml b/vars/main.yml index bd7e55e..d649151 100644 --- a/vars/main.yml +++ b/vars/main.yml @@ -94,6 +94,16 @@ litellm_models: backend: ollama_chat/llama3.1:8b api_base: "{{ anvil_ollama_base }}" api_key: ollama-no-auth + # The structured-output tier, added 2026-09-12. llama3.1:8b answers fast but + # will not hold strict JSON: paperless-ai got "Expected ',' or '}' after + # property value in JSON at position 263" on a 1,921-token reply. The Kestra + # flows escape this by setting response_format={"type":"json_object"}; + # paperless-ai does not, so it needs a model that keeps the shape unprompted. + # 14B is the smallest that does, and at ~9 GB it co-exists with anything here. + - name: local_qwen2.5-14b + backend: ollama_chat/qwen2.5:14b + api_base: "{{ anvil_ollama_base }}" + api_key: ollama-no-auth # Shadow alias SOLELY for paperless-ai's hardcoded gpt-4o-mini validation # probe (see the "Narrow exception" note above). Routed to free local # llama3.1:8b so the probe costs nothing. Do not point real traffic here.