Merge 6b4940806f into 188a56af5c

docs/docs/providers/inference/index.mdx

@@ -1,9 +1,10 @@
 ---
 description: "Llama Stack Inference API for generating completions, chat completions, and 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."
+    - Embedding models: these models generate embeddings to be used for semantic search.
+    - Rerank models: these models reorder the documents based on their relevance to a query."
 sidebar_label: Inference
 title: Inference
 ---
@@ -14,8 +15,9 @@ title: Inference
 
 Llama Stack Inference API for generating completions, chat completions, and 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: these models reorder the documents based on their relevance to a query.
 
 This section contains documentation for all available providers for the **inference** API.

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

@@ -13335,7 +13335,7 @@
         },
         {
             "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 based on their relevance to a query.",
             "x-displayName": "Llama Stack Inference API for generating completions, chat completions, and embeddings."
         },
         {

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

@@ -9990,13 +9990,16 @@ 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 based on their relevance
+      to a query.
     x-displayName: >-
       Llama Stack Inference API for generating completions, chat completions, and
       embeddings.

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

@@ -4992,7 +4992,7 @@
                 "properties": {
                     "model": {
                         "type": "string",
-                        "description": "The identifier of the reranking model to use."
+                        "description": "The identifier of the reranking model to use. The model must be a reranking model registered with Llama Stack and available via the /models endpoint."
                     },
                     "query": {
                         "oneOf": [

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

@@ -3657,7 +3657,8 @@ components:
         model:
           type: string
           description: >-
-            The identifier of the reranking model to use.
+            The identifier of the reranking model to use. The model must be a reranking
+            model registered with Llama Stack and available via the /models endpoint.
         query:
           oneOf:
             - type: string

docs/static/llama-stack-spec.html

@@ -6829,7 +6829,8 @@
                 "type": "string",
                 "enum": [
                     "llm",
-                    "embedding"
+                    "embedding",
+                    "rerank"
                 ],
                 "title": "ModelType",
                 "description": "Enumeration of supported model types in Llama Stack."
@@ -12883,7 +12884,7 @@
         },
         {
             "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 based on their relevance to a query.",
             "x-displayName": "Llama Stack Inference API for generating completions, chat completions, and embeddings."
         },
         {

docs/static/llama-stack-spec.yaml

@@ -5158,6 +5158,7 @@ components:
       enum:
         - llm
         - embedding
+        - rerank
       title: ModelType
       description: >-
         Enumeration of supported model types in Llama Stack.
@@ -9728,13 +9729,16 @@ 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 based on their relevance
+      to a query.
     x-displayName: >-
       Llama Stack Inference API for generating completions, chat completions, and
       embeddings.

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

@@ -8838,7 +8838,8 @@
                 "type": "string",
                 "enum": [
                     "llm",
-                    "embedding"
+                    "embedding",
+                    "rerank"
                 ],
                 "title": "ModelType",
                 "description": "Enumeration of supported model types in Llama Stack."
@@ -17033,7 +17034,7 @@
                 "properties": {
                     "model": {
                         "type": "string",
-                        "description": "The identifier of the reranking model to use."
+                        "description": "The identifier of the reranking model to use. The model must be a reranking model registered with Llama Stack and available via the /models endpoint."
                     },
                     "query": {
                         "oneOf": [
@@ -18456,7 +18457,7 @@
         },
         {
             "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 based on their relevance to a query.",
             "x-displayName": "Llama Stack Inference API for generating completions, chat completions, and embeddings."
         },
         {

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

@@ -6603,6 +6603,7 @@ components:
       enum:
         - llm
         - embedding
+        - rerank
       title: ModelType
       description: >-
         Enumeration of supported model types in Llama Stack.
@@ -12693,7 +12694,8 @@ components:
         model:
           type: string
           description: >-
-            The identifier of the reranking model to use.
+            The identifier of the reranking model to use. The model must be a reranking
+            model registered with Llama Stack and available via the /models endpoint.
         query:
           oneOf:
             - type: string
@@ -13774,13 +13776,16 @@ 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 based on their relevance
+      to a query.
     x-displayName: >-
       Llama Stack Inference API for generating completions, chat completions, and
       embeddings.