From 53a93f1e20616f8b4a9161efb4cbac16a51fb277 Mon Sep 17 00:00:00 2001 From: Andrej Simurka Date: Tue, 24 Mar 2026 15:50:51 +0100 Subject: [PATCH] Disable annotation in root config, document configuration options for annotations --- docs/rag_guide.md | 7 +++++++ run.yaml | 4 ++++ 2 files changed, 11 insertions(+) diff --git a/docs/rag_guide.md b/docs/rag_guide.md index fe2bed23c..556419012 100644 --- a/docs/rag_guide.md +++ b/docs/rag_guide.md @@ -20,6 +20,7 @@ This document explains how to configure and customize your RAG pipeline using th * [Add an Inference Model (LLM)](#add-an-inference-model-llm) * [Complete Configuration Reference](#complete-configuration-reference) * [System Prompt Guidance for RAG (as a tool)](#system-prompt-guidance-for-rag-as-a-tool) +* [Llama Stack RAG annotations](#llama-stack-rag-annotations) * [References](#references) @@ -493,6 +494,12 @@ When using RAG, the `knowledge_search` tool must be explicitly referenced in you ```text You are a helpful assistant with access to a 'knowledge_search' tool. When users ask questions, ALWAYS use the knowledge_search tool first to find accurate information from the documentation before answering. ``` + +--- +# Llama Stack RAG annotations + +The top-level `vector_stores` block in Llama Stack configuration may include `annotation_prompt_params` to control whether Llama Stack injects extra RAG annotation instructions into the model prompt (for example, citation-style markers). The [`run.yaml`](../run.yaml) in this repository sets `enable_annotations: false` under that block to avoid unwanted annotations. For a configuration that enables annotations and customizes the instruction template, see [`examples/run.yaml`](../examples/run.yaml). + --- # References diff --git a/run.yaml b/run.yaml index b7e56d249..7a4a78efa 100644 --- a/run.yaml +++ b/run.yaml @@ -142,6 +142,10 @@ registered_resources: # Without it, llama-stack's rag-runtime silently fails all file_search operations # with no error logged. vector_stores: + # LCORE-1498: Disables Llama Stack RAG annotation generation + # causing unwanted citation/file markers in model output. + annotation_prompt_params: + enable_annotations: false default_provider_id: faiss default_embedding_model: # Define the default embedding model for RAG provider_id: sentence-transformers