Update docs

llama_stack/apis/inference/inference.py

@@ -1162,7 +1162,7 @@ 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: these models reorder the documents by relevance.
+    - 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/apis/models/models.py

@@ -27,7 +27,7 @@ class ModelType(StrEnum):
     """Enumeration of supported model types in Llama Stack.
     :cvar llm: Large language model for text generation and completion
     :cvar embedding: Embedding model for converting text to vector representations
-    :cvar rerank: Reranking model for reordering documents by relevance
+    :cvar rerank: Reranking model for reordering documents based on their relevance to a query
     """
 
     llm = "llm"