From 659be50c27a3c326788ebab4dde8bbf7d72d942f Mon Sep 17 00:00:00 2001 From: Karthik Tiruveedhi Date: Tue, 18 Aug 2026 17:30:50 -0700 Subject: [PATCH] Update deprecating LLM nemotron-3-nano-30b-a3b -> nemotron-3.5-lightning-30b-a3b The hosted nemotron-3-nano-30b-a3b endpoint is deprecating. Swap the summarization, chat, and notification LLMs to the successor nemotron-3.5-lightning-30b-a3b, and set extra_body.chat_template_kwargs.thinking: false on each (the successor is a reasoning model whose chain-of-thought otherwise floods content and breaks the strict-JSON contract / graph extraction). Validated end-to-end on an L4: grounded graph-RAG probe passes with a passing negative control. Co-Authored-By: Claude Opus 4.8 --- config/config.yaml | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/config/config.yaml b/config/config.yaml index 82cb8f2..09a6d19 100644 --- a/config/config.yaml +++ b/config/config.yaml @@ -17,8 +17,11 @@ summarization: enable: true method: "batch" llm: - model: nvidia/nemotron-3-nano-30b-a3b + model: nvidia/nemotron-3.5-lightning-30b-a3b base_url: https://integrate.api.nvidia.com/v1 + extra_body: + chat_template_kwargs: + thinking: false max_tokens: 2048 temperature: 0.2 top_p: 0.7 @@ -49,8 +52,11 @@ chat: top_k: 25 confidence_threshold: 0.0 llm: - model: nvidia/nemotron-3-nano-30b-a3b + model: nvidia/nemotron-3.5-lightning-30b-a3b base_url: https://integrate.api.nvidia.com/v1 + extra_body: + chat_template_kwargs: + thinking: false max_tokens: 2048 temperature: 0.5 embedding: @@ -64,8 +70,11 @@ notification: enable: false endpoint: "http://127.0.0.1:60000/via-alert-callback" llm: - model: nvidia/nemotron-3-nano-30b-a3b + model: nvidia/nemotron-3.5-lightning-30b-a3b base_url: https://integrate.api.nvidia.com/v1 + extra_body: + chat_template_kwargs: + thinking: false max_tokens: 2048 temperature: 0.2 top_p: 0.7