llamastack · ehhuang · Oct 27, 2025
diff --git a/.stats.yml b/.stats.yml
@@ -1,4 +1,4 @@
 configured_endpoints: 104
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-97b91eca4a3ff251edc02636b1a638866675d6c1abd46cd9fc18bc50a1de9656.yml
-openapi_spec_hash: 7302f1aa50090e3de78e34c184371267
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-35c6569e5e9fcc85084c9728eb7fc7c5908297fcc77043d621d25de3c850a990.yml
+openapi_spec_hash: 0f95bbeee16f3205d36ec34cfa62c711
 config_hash: a3829dbdaa491194d01f399784d532cd
diff --git a/src/llama_stack_client/resources/moderations.py b/src/llama_stack_client/resources/moderations.py
@@ -13,7 +13,7 @@
 import httpx
 
 from ..types import moderation_create_params
-from .._types import Body, Query, Headers, NotGiven, SequenceNotStr, not_given
+from .._types import Body, Omit, Query, Headers, NotGiven, SequenceNotStr, omit, not_given
 from .._utils import maybe_transform, async_maybe_transform
 from .._compat import cached_property
 from .._resource import SyncAPIResource, AsyncAPIResource
@@ -53,7 +53,7 @@ def create(
         self,
         *,
         input: Union[str, SequenceNotStr[str]],
-        model: str,
+        model: str | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -70,7 +70,7 @@ def create(
           input: Input (or inputs) to classify. Can be a single string, an array of strings, or
               an array of multi-modal input objects similar to other models.
 
-          model: The content moderation model you would like to use.
+          model: (Optional) The content moderation model you would like to use.
 
           extra_headers: Send extra headers
 
@@ -120,7 +120,7 @@ async def create(
         self,
         *,
         input: Union[str, SequenceNotStr[str]],
-        model: str,
+        model: str | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -137,7 +137,7 @@ async def create(
           input: Input (or inputs) to classify. Can be a single string, an array of strings, or
               an array of multi-modal input objects similar to other models.
 
-          model: The content moderation model you would like to use.
+          model: (Optional) The content moderation model you would like to use.
 
           extra_headers: Send extra headers
 

diff --git a/src/llama_stack_client/resources/tool_runtime/rag_tool.py b/src/llama_stack_client/resources/tool_runtime/rag_tool.py
@@ -57,7 +57,7 @@ def insert(
         *,
         chunk_size_in_tokens: int,
         documents: Iterable[Document],
-        vector_db_id: str,
+        vector_store_id: str,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -73,7 +73,7 @@ def insert(
 
           documents: List of documents to index in the RAG system
 
-          vector_db_id: ID of the vector database to store the document embeddings
+          vector_store_id: ID of the vector database to store the document embeddings
 
           extra_headers: Send extra headers
 
@@ -90,7 +90,7 @@ def insert(
                 {
                     "chunk_size_in_tokens": chunk_size_in_tokens,
                     "documents": documents,
-                    "vector_db_id": vector_db_id,
+                    "vector_store_id": vector_store_id,
                 },
                 rag_tool_insert_params.RagToolInsertParams,
             ),
@@ -104,7 +104,7 @@ def query(
         self,
         *,
         content: InterleavedContent,
-        vector_db_ids: SequenceNotStr[str],
+        vector_store_ids: SequenceNotStr[str],
         query_config: QueryConfig | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
@@ -119,7 +119,7 @@ def query(
         Args:
           content: The query content to search for in the indexed documents
 
-          vector_db_ids: List of vector database IDs to search within
+          vector_store_ids: List of vector database IDs to search within
 
           query_config: (Optional) Configuration parameters for the query operation
 
@@ -136,7 +136,7 @@ def query(
             body=maybe_transform(
                 {
                     "content": content,
-                    "vector_db_ids": vector_db_ids,
+                    "vector_store_ids": vector_store_ids,
                     "query_config": query_config,
                 },
                 rag_tool_query_params.RagToolQueryParams,
@@ -173,7 +173,7 @@ async def insert(
         *,
         chunk_size_in_tokens: int,
         documents: Iterable[Document],
-        vector_db_id: str,
+        vector_store_id: str,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -189,7 +189,7 @@ async def insert(
 
           documents: List of documents to index in the RAG system
 
-          vector_db_id: ID of the vector database to store the document embeddings
+          vector_store_id: ID of the vector database to store the document embeddings
 
           extra_headers: Send extra headers
 
@@ -206,7 +206,7 @@ async def insert(
                 {
                     "chunk_size_in_tokens": chunk_size_in_tokens,
                     "documents": documents,
-                    "vector_db_id": vector_db_id,
+                    "vector_store_id": vector_store_id,
                 },
                 rag_tool_insert_params.RagToolInsertParams,
             ),
@@ -220,7 +220,7 @@ async def query(
         self,
         *,
         content: InterleavedContent,
-        vector_db_ids: SequenceNotStr[str],
+        vector_store_ids: SequenceNotStr[str],
         query_config: QueryConfig | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
@@ -235,7 +235,7 @@ async def query(
         Args:
           content: The query content to search for in the indexed documents
 
-          vector_db_ids: List of vector database IDs to search within
+          vector_store_ids: List of vector database IDs to search within
 
           query_config: (Optional) Configuration parameters for the query operation
 
@@ -252,7 +252,7 @@ async def query(
             body=await async_maybe_transform(
                 {
                     "content": content,
-                    "vector_db_ids": vector_db_ids,
+                    "vector_store_ids": vector_store_ids,
                     "query_config": query_config,
                 },
                 rag_tool_query_params.RagToolQueryParams,

diff --git a/src/llama_stack_client/resources/vector_io.py b/src/llama_stack_client/resources/vector_io.py
@@ -54,7 +54,7 @@ def insert(
         self,
         *,
         chunks: Iterable[vector_io_insert_params.Chunk],
-        vector_db_id: str,
+        vector_store_id: str,
         ttl_seconds: int | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
@@ -74,7 +74,7 @@ def insert(
               configure how Llama Stack formats the chunk during generation. If `embedding` is
               not provided, it will be computed later.
 
-          vector_db_id: The identifier of the vector database to insert the chunks into.
+          vector_store_id: The identifier of the vector database to insert the chunks into.
 
           ttl_seconds: The time to live of the chunks.
 
@@ -92,7 +92,7 @@ def insert(
             body=maybe_transform(
                 {
                     "chunks": chunks,
-                    "vector_db_id": vector_db_id,
+                    "vector_store_id": vector_store_id,
                     "ttl_seconds": ttl_seconds,
                 },
                 vector_io_insert_params.VectorIoInsertParams,
@@ -107,7 +107,7 @@ def query(
         self,
         *,
         query: InterleavedContent,
-        vector_db_id: str,
+        vector_store_id: str,
         params: Dict[str, Union[bool, float, str, Iterable[object], object, None]] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
@@ -122,7 +122,7 @@ def query(
         Args:
           query: The query to search for.
 
-          vector_db_id: The identifier of the vector database to query.
+          vector_store_id: The identifier of the vector database to query.
 
           params: The parameters of the query.
 
@@ -139,7 +139,7 @@ def query(
             body=maybe_transform(
                 {
                     "query": query,
-                    "vector_db_id": vector_db_id,
+                    "vector_store_id": vector_store_id,
                     "params": params,
                 },
                 vector_io_query_params.VectorIoQueryParams,
@@ -175,7 +175,7 @@ async def insert(
         self,
         *,
         chunks: Iterable[vector_io_insert_params.Chunk],
-        vector_db_id: str,
+        vector_store_id: str,
         ttl_seconds: int | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
@@ -195,7 +195,7 @@ async def insert(
               configure how Llama Stack formats the chunk during generation. If `embedding` is
               not provided, it will be computed later.
 
-          vector_db_id: The identifier of the vector database to insert the chunks into.
+          vector_store_id: The identifier of the vector database to insert the chunks into.
 
           ttl_seconds: The time to live of the chunks.
 
@@ -213,7 +213,7 @@ async def insert(
             body=await async_maybe_transform(
                 {
                     "chunks": chunks,
-                    "vector_db_id": vector_db_id,
+                    "vector_store_id": vector_store_id,
                     "ttl_seconds": ttl_seconds,
                 },
                 vector_io_insert_params.VectorIoInsertParams,
@@ -228,7 +228,7 @@ async def query(
         self,
         *,
         query: InterleavedContent,
-        vector_db_id: str,
+        vector_store_id: str,
         params: Dict[str, Union[bool, float, str, Iterable[object], object, None]] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
@@ -243,7 +243,7 @@ async def query(
         Args:
           query: The query to search for.
 
-          vector_db_id: The identifier of the vector database to query.
+          vector_store_id: The identifier of the vector database to query.
 
           params: The parameters of the query.
 
@@ -260,7 +260,7 @@ async def query(
             body=await async_maybe_transform(
                 {
                     "query": query,
-                    "vector_db_id": vector_db_id,
+                    "vector_store_id": vector_store_id,
                     "params": params,
                 },
                 vector_io_query_params.VectorIoQueryParams,

diff --git a/src/llama_stack_client/types/alpha/memory_retrieval_step.py b/src/llama_stack_client/types/alpha/memory_retrieval_step.py
@@ -29,7 +29,7 @@ class MemoryRetrievalStep(BaseModel):
     turn_id: str
     """The ID of the turn."""
 
-    vector_db_ids: str
+    vector_store_ids: str
     """The IDs of the vector databases to retrieve context from."""
 
     completed_at: Optional[datetime] = None

diff --git a/src/llama_stack_client/types/moderation_create_params.py b/src/llama_stack_client/types/moderation_create_params.py
@@ -24,5 +24,5 @@ class ModerationCreateParams(TypedDict, total=False):
     objects similar to other models.
     """
 
-    model: Required[str]
-    """The content moderation model you would like to use."""
+    model: str
+    """(Optional) The content moderation model you would like to use."""