Merge f93461de5e into sapling-pr-archive-ehhuang

llama_stack/core/routing_tables/models.py

@@ -33,7 +33,7 @@ class ModelsRoutingTable(CommonRoutingTableImpl, Models):
             try:
                 models = await provider.list_models()
             except Exception as e:
-                logger.warning(f"Model refresh failed for provider {provider_id}: {e}")
+                logger.debug(f"Model refresh failed for provider {provider_id}: {e}")
                 continue
 
             self.listed_providers.add(provider_id)

llama_stack/core/routing_tables/vector_dbs.py

@@ -245,3 +245,65 @@ class VectorDBsRoutingTable(CommonRoutingTableImpl, VectorDBs):
             vector_store_id=vector_store_id,
             file_id=file_id,
         )
+
+    async def openai_create_vector_store_file_batch(
+        self,
+        vector_store_id: str,
+        file_ids: list[str],
+        attributes: dict[str, Any] | None = None,
+        chunking_strategy: Any | None = None,
+    ):
+        await self.assert_action_allowed("update", "vector_db", vector_store_id)
+        provider = await self.get_provider_impl(vector_store_id)
+        return await provider.openai_create_vector_store_file_batch(
+            vector_store_id=vector_store_id,
+            file_ids=file_ids,
+            attributes=attributes,
+            chunking_strategy=chunking_strategy,
+        )
+
+    async def openai_retrieve_vector_store_file_batch(
+        self,
+        batch_id: str,
+        vector_store_id: str,
+    ):
+        await self.assert_action_allowed("read", "vector_db", vector_store_id)
+        provider = await self.get_provider_impl(vector_store_id)
+        return await provider.openai_retrieve_vector_store_file_batch(
+            batch_id=batch_id,
+            vector_store_id=vector_store_id,
+        )
+
+    async def openai_list_files_in_vector_store_file_batch(
+        self,
+        batch_id: str,
+        vector_store_id: str,
+        after: str | None = None,
+        before: str | None = None,
+        filter: str | None = None,
+        limit: int | None = 20,
+        order: str | None = "desc",
+    ):
+        await self.assert_action_allowed("read", "vector_db", vector_store_id)
+        provider = await self.get_provider_impl(vector_store_id)
+        return await provider.openai_list_files_in_vector_store_file_batch(
+            batch_id=batch_id,
+            vector_store_id=vector_store_id,
+            after=after,
+            before=before,
+            filter=filter,
+            limit=limit,
+            order=order,
+        )
+
+    async def openai_cancel_vector_store_file_batch(
+        self,
+        batch_id: str,
+        vector_store_id: str,
+    ):
+        await self.assert_action_allowed("update", "vector_db", vector_store_id)
+        provider = await self.get_provider_impl(vector_store_id)
+        return await provider.openai_cancel_vector_store_file_batch(
+            batch_id=batch_id,
+            vector_store_id=vector_store_id,
+        )

llama_stack/core/stack.py

@@ -274,22 +274,6 @@ def cast_image_name_to_string(config_dict: dict[str, Any]) -> dict[str, Any]:
     return config_dict
 
 
-def validate_env_pair(env_pair: str) -> tuple[str, str]:
-    """Validate and split an environment variable key-value pair."""
-    try:
-        key, value = env_pair.split("=", 1)
-        key = key.strip()
-        if not key:
-            raise ValueError(f"Empty key in environment variable pair: {env_pair}")
-        if not all(c.isalnum() or c == "_" for c in key):
-            raise ValueError(f"Key must contain only alphanumeric characters and underscores: {key}")
-        return key, value
-    except ValueError as e:
-        raise ValueError(
-            f"Invalid environment variable format '{env_pair}': {str(e)}. Expected format: KEY=value"
-        ) from e
-
-
 def add_internal_implementations(impls: dict[Api, Any], run_config: StackRunConfig) -> None:
     """Add internal implementations (inspect and providers) to the implementations dictionary.
 

llama_stack/core/start_stack.sh

@@ -25,7 +25,7 @@ error_handler() {
 trap 'error_handler ${LINENO}' ERR
 
 if [ $# -lt 3 ]; then
-  echo "Usage: $0 <env_type> <env_path_or_name> <port> [--config <yaml_config>] [--env KEY=VALUE]..."
+  echo "Usage: $0 <env_type> <env_path_or_name> <port> [--config <yaml_config>]"
   exit 1
 fi
 
@@ -43,7 +43,6 @@ SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
 
 # Initialize variables
 yaml_config=""
-env_vars=""
 other_args=""
 
 # Process remaining arguments
@@ -58,15 +57,6 @@ while [[ $# -gt 0 ]]; do
         exit 1
       fi
       ;;
-    --env)
-      if [[ -n "$2" ]]; then
-        env_vars="$env_vars --env $2"
-        shift 2
-      else
-        echo -e "${RED}Error: --env requires a KEY=VALUE argument${NC}" >&2
-        exit 1
-      fi
-      ;;
     *)
       other_args="$other_args $1"
       shift
@@ -119,7 +109,6 @@ if [[ "$env_type" == "venv" ]]; then
     llama stack run \
     $yaml_config_arg \
     --port "$port" \
-    $env_vars \
     $other_args
 elif [[ "$env_type" == "container" ]]; then
     echo -e "${RED}Warning: Llama Stack no longer supports running Containers via the 'llama stack run' command.${NC}"