Remove experimental from rerank models doc

docs/docs/providers/inference/index.mdx

@@ -6,7 +6,7 @@ description: "Inference
     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."
+    - Rerank models: these models reorder the documents based on their relevance to a query."
 sidebar_label: Inference
 title: Inference
 ---
@@ -22,6 +22,6 @@ Inference
     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.
+    - 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

@@ -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. 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.",
+            "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: these models reorder the documents based on their relevance to a query.",
             "x-displayName": "Inference"
         },
         {

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

@@ -10218,8 +10218,8 @@ tags:
       - Embedding models: these models generate embeddings to be used for semantic
       search.
 
-      - Rerank models (Experimental): these models reorder the documents based on
+      - Rerank models: these models reorder the documents based on their relevance
-      their relevance to a query.
+      to a query.
     x-displayName: Inference
   - name: Models
     description: ''

docs/static/llama-stack-spec.html

@@ -13262,7 +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. 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.",
+            "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: these models reorder the documents based on their relevance to a query.",
             "x-displayName": "Inference"
         },
         {

docs/static/llama-stack-spec.yaml

@@ -10191,8 +10191,8 @@ tags:
       - Embedding models: these models generate embeddings to be used for semantic
       search.
 
-      - Rerank models (Experimental): these models reorder the documents based on
+      - Rerank models: these models reorder the documents based on their relevance
-      their relevance to a query.
+      to a query.
     x-displayName: Inference
   - name: Inspect
     description: >-

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

@@ -17952,7 +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. 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.",
+            "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: these models reorder the documents based on their relevance to a query.",
             "x-displayName": "Inference"
         },
         {

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

@@ -13586,8 +13586,8 @@ tags:
       - Embedding models: these models generate embeddings to be used for semantic
       search.
 
-      - Rerank models (Experimental): these models reorder the documents based on
+      - Rerank models: these models reorder the documents based on their relevance
-      their relevance to a query.
+      to a query.
     x-displayName: Inference
   - name: Inspect
     description: >-

llama_stack/apis/inference/inference.py

@@ -1237,7 +1237,7 @@ class Inference(InferenceProvider):
     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.
+    - Rerank models: these models reorder the documents based on their relevance to a query.
     """
 
     @webmethod(route="/openai/v1/chat/completions", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)

llama_stack/providers/utils/inference/openai_mixin.py

@@ -48,6 +48,7 @@ class OpenAIMixin(NeedsRequestProviderData, ABC, BaseModel):
     - overwrite_completion_id: If True, overwrites the 'id' field in OpenAI responses
     - download_images: If True, downloads images and converts to base64 for providers that require it
     - embedding_model_metadata: A dictionary mapping model IDs to their embedding metadata
+    - rerank_model_list: A list of model IDs for rerank models
     - provider_data_api_key_field: Optional field name in provider data to look for API key
     - list_provider_model_ids: Method to list available models from the provider
     - get_extra_client_params: Method to provide extra parameters to the AsyncOpenAI client