adding comment into docstring with default value example

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

docs/_static/llama-stack-spec.html

@@ -11310,7 +11310,7 @@
                     "chunk_template": {
                         "type": "string",
                         "default": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n",
-                        "description": "Template for formatting each retrieved chunk in the context."
+                        "description": "Template for formatting each retrieved chunk in the context. Available placeholders: {index} (1-based chunk ordinal), {chunk.content} (chunk content string), {metadata} (chunk metadata dict). Default: \"Result {index}\\nContent: {chunk.content}\\nMetadata: {metadata}\\n\""
                     }
                 },
                 "additionalProperties": false,

docs/_static/llama-stack-spec.yaml

@@ -7812,7 +7812,10 @@ components:
 
             Metadata: {metadata}
           description: >-
-            Template for formatting each retrieved chunk in the context.
+            Template for formatting each retrieved chunk in the context. Available
+            placeholders: {index} (1-based chunk ordinal), {chunk.content} (chunk
+            content string), {metadata} (chunk metadata dict). Default: "Result {index}\nContent:
+            {chunk.content}\nMetadata: {metadata}\n"
       additionalProperties: false
       required:
         - query_generator_config

llama_stack/apis/tools/rag_tool.py

@@ -74,6 +74,8 @@ class RAGQueryConfig(BaseModel):
     :param max_tokens_in_context: Maximum number of tokens in the context.
     :param max_chunks: Maximum number of chunks to retrieve.
     :param chunk_template: Template for formatting each retrieved chunk in the context.
+        Available placeholders: {index} (1-based chunk ordinal), {chunk.content} (chunk content string), {metadata} (chunk metadata dict).
+        Default: "Result {index}\\nContent: {chunk.content}\\nMetadata: {metadata}\\n"
     """
 
     # This config defines how a query is generated using the messages
@@ -81,8 +83,6 @@ class RAGQueryConfig(BaseModel):
     query_generator_config: RAGQueryGeneratorConfig = Field(default=DefaultRAGQueryGeneratorConfig())
     max_tokens_in_context: int = 4096
     max_chunks: int = 5
-    # Optional template for formatting each retrieved chunk in the context.
-    # Available placeholders: {index} (1-based chunk ordinal), {metadata} (chunk metadata dict), {chunk.content} (chunk content string).
     chunk_template: str = "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n"
 
     @field_validator("chunk_template")

tests/unit/rag/test_vector_store.py

@@ -93,7 +93,6 @@ class TestVectorStore:
         chunks = make_overlapped_chunks(document_id, text, window_len, overlap_len, original_metadata)
 
         assert len(chunks) == expected_chunks
-        print(len(chunks), expected_chunks)
 
         # Check that each chunk has the right metadata
         for chunk in chunks: