swapping to configuring the entire chunk template

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

docs/_static/llama-stack-spec.html

@@ -11134,9 +11134,9 @@
                         "type": "integer",
                         "default": 5
                     },
-                    "include_metadata_in_content": {
-                        "type": "boolean",
-                        "default": false
+                    "chunk_template": {
+                        "type": "string",
+                        "default": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n"
                     }
                 },
                 "additionalProperties": false,
@@ -11144,7 +11144,7 @@
                     "query_generator_config",
                     "max_tokens_in_context",
                     "max_chunks",
-                    "include_metadata_in_content"
+                    "chunk_template"
                 ],
                 "title": "RAGQueryConfig"
             },

docs/_static/llama-stack-spec.yaml

@@ -7690,15 +7690,20 @@ components:
         max_chunks:
           type: integer
           default: 5
-        include_metadata_in_content:
-          type: boolean
-          default: false
+        chunk_template:
+          type: string
+          default: >
+            Result {index}
+
+            Content: {chunk.content}
+
+            Metadata: {metadata}
       additionalProperties: false
       required:
         - query_generator_config
         - max_tokens_in_context
         - max_chunks
-        - include_metadata_in_content
+        - chunk_template
       title: RAGQueryConfig
     RAGQueryGeneratorConfig:
       oneOf:

docs/source/building_applications/rag.md

@@ -99,14 +99,14 @@ results = client.tool_runtime.rag_tool.query(
 )
 ```
 
-You can configure adding metadata to the context if you find it useful for your application. Simply add:
+You can configure how the RAG tool adds metadata to the context if you find it useful for your application. Simply add:
 ```python
 # Query documents
 results = client.tool_runtime.rag_tool.query(
     vector_db_ids=[vector_db_id],
     content="What do you know about...",
     query_config={
-        "include_metadata_in_content": True,
+        "chunk_template": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n",
     },
 )
 ```
@@ -131,7 +131,7 @@ agent = Agent(
                 "query_config": {
                     "chunk_size_in_tokens": 512,
                     "chunk_overlap_in_tokens": 0,
-                    "include_metadata_in_content": False,
+                    "chunk_template": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n",
                 },
             },
         }