From d1b4e090effd61a29c7102ba9042b749e0727971 Mon Sep 17 00:00:00 2001 From: Jiayi Date: Wed, 10 Sep 2025 11:50:55 -0700 Subject: [PATCH] Update docs to include rerank models --- docs/static/llama-stack-spec.html | 2 +- docs/static/llama-stack-spec.yaml | 6 ++++-- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/docs/static/llama-stack-spec.html b/docs/static/llama-stack-spec.html index b260f01a7..8192a9cf6 100644 --- a/docs/static/llama-stack-spec.html +++ b/docs/static/llama-stack-spec.html @@ -17875,7 +17875,7 @@ }, { "name": "Inference", - "description": "This API provides the raw interface to the underlying models. Two kinds of models are supported:\n- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.\n- Embedding models: these models generate embeddings to be used for semantic search.", + "description": "This API provides the raw interface to the underlying models. Three kinds of models are supported:\n- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.\n- Embedding models: these models generate embeddings to be used for semantic search.\n- Rerank models: these models reorder the documents by relevance.", "x-displayName": "Llama Stack Inference API for generating completions, chat completions, and embeddings." }, { diff --git a/docs/static/llama-stack-spec.yaml b/docs/static/llama-stack-spec.yaml index ebe142557..895b939ab 100644 --- a/docs/static/llama-stack-spec.yaml +++ b/docs/static/llama-stack-spec.yaml @@ -13452,13 +13452,15 @@ tags: description: '' - name: Inference description: >- - This API provides the raw interface to the underlying models. Two kinds of models - are supported: + This API provides the raw interface to the underlying models. Three kinds of + models are supported: - LLM models: these models generate "raw" and "chat" (conversational) completions. - Embedding models: these models generate embeddings to be used for semantic search. + + - Rerank models: these models reorder the documents by relevance. x-displayName: >- Llama Stack Inference API for generating completions, chat completions, and embeddings.