Add rerank models and rerank API change

docs/static/deprecated-llama-stack-spec.html

@@ -13459,7 +13459,7 @@
         },
         {
             "name": "Inference",
-            "description": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis 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": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis 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 (Experimental): these models reorder the documents based on their relevance to a query.",
             "x-displayName": "Inference"
         },
         {

docs/static/deprecated-llama-stack-spec.yaml

@@ -10210,13 +10210,16 @@ tags:
       embeddings.
 
 
-      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 (Experimental): these models reorder the documents based on
+      their relevance to a query.
     x-displayName: Inference
   - name: Models
     description: ''

docs/static/llama-stack-spec.html

@@ -6859,7 +6859,8 @@
                 "type": "string",
                 "enum": [
                     "llm",
-                    "embedding"
+                    "embedding",
+                    "rerank"
                 ],
                 "title": "ModelType",
                 "description": "Enumeration of supported model types in Llama Stack."
@@ -13261,7 +13262,7 @@
         },
         {
             "name": "Inference",
-            "description": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis 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": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis 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 (Experimental): these models reorder the documents based on their relevance to a query.",
             "x-displayName": "Inference"
         },
         {

docs/static/llama-stack-spec.yaml

@@ -5269,6 +5269,7 @@ components:
       enum:
         - llm
         - embedding
+        - rerank
       title: ModelType
       description: >-
         Enumeration of supported model types in Llama Stack.
@@ -10182,13 +10183,16 @@ tags:
       embeddings.
 
 
-      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 (Experimental): these models reorder the documents based on
+      their relevance to a query.
     x-displayName: Inference
   - name: Inspect
     description: >-

docs/static/stainless-llama-stack-spec.html

@@ -8531,7 +8531,8 @@
                 "type": "string",
                 "enum": [
                     "llm",
-                    "embedding"
+                    "embedding",
+                    "rerank"
                 ],
                 "title": "ModelType",
                 "description": "Enumeration of supported model types in Llama Stack."
@@ -17951,7 +17952,7 @@
         },
         {
             "name": "Inference",
-            "description": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis 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": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis 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 (Experimental): these models reorder the documents based on their relevance to a query.",
             "x-displayName": "Inference"
         },
         {

docs/static/stainless-llama-stack-spec.yaml

@@ -6482,6 +6482,7 @@ components:
       enum:
         - llm
         - embedding
+        - rerank
       title: ModelType
       description: >-
         Enumeration of supported model types in Llama Stack.
@@ -13577,13 +13578,16 @@ tags:
       embeddings.
 
 
-      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 (Experimental): these models reorder the documents based on
+      their relevance to a query.
     x-displayName: Inference
   - name: Inspect
     description: >-