add version env variable

docs/source/distributions/remote_hosted_distro/nvidia.md

@@ -22,9 +22,8 @@ The `llamastack/distribution-nvidia` distribution consists of the following prov
 The following environment variables can be configured:
 
 - `NVIDIA_API_KEY`: NVIDIA API Key (default: ``)
-- `NVIDIA_USER_ID`: NVIDIA User ID (default: `llama-stack-user`)
+- `NVIDIA_APPEND_API_VERSION`: Whether to append the API version to the base_url (default: `True`)
 - `NVIDIA_DATASET_NAMESPACE`: NVIDIA Dataset Namespace (default: `default`)
-- `NVIDIA_ACCESS_POLICIES`: NVIDIA Access Policies (default: `{}`)
 - `NVIDIA_PROJECT_ID`: NVIDIA Project ID (default: `test-project`)
 - `NVIDIA_CUSTOMIZER_URL`: NVIDIA Customizer URL (default: `https://customizer.api.nvidia.com`)
 - `NVIDIA_OUTPUT_MODEL_DIR`: NVIDIA Output Model Directory (default: `test-example-model@v1`)

docs/source/distributions/self_hosted_distro/nvidia.md

@@ -22,9 +22,7 @@ The `llamastack/distribution-nvidia` distribution consists of the following prov
 The following environment variables can be configured:
 
 - `NVIDIA_API_KEY`: NVIDIA API Key (default: ``)
-- `NVIDIA_USER_ID`: NVIDIA User ID (default: `llama-stack-user`)
 - `NVIDIA_DATASET_NAMESPACE`: NVIDIA Dataset Namespace (default: `default`)
-- `NVIDIA_ACCESS_POLICIES`: NVIDIA Access Policies (default: `{}`)
 - `NVIDIA_PROJECT_ID`: NVIDIA Project ID (default: `test-project`)
 - `NVIDIA_CUSTOMIZER_URL`: NVIDIA Customizer URL (default: `https://customizer.api.nvidia.com`)
 - `NVIDIA_OUTPUT_MODEL_DIR`: NVIDIA Output Model Directory (default: `test-example-model@v1`)

llama_stack/providers/remote/inference/nvidia/config.py

@@ -47,10 +47,15 @@ class NVIDIAConfig(BaseModel):
         default=60,
         description="Timeout for the HTTP requests",
     )
+    append_api_version: bool = Field(
+        default=lambda: os.getenv("NVIDIA_APPEND_API_VERSION", True),
+        description="Whether to append the API version to the model ID",
+    )
 
     @classmethod
     def sample_run_config(cls, **kwargs) -> Dict[str, Any]:
         return {
             "url": "${env.NVIDIA_BASE_URL:https://integrate.api.nvidia.com}",
             "api_key": "${env.NVIDIA_API_KEY:}",
+            "append_api_version": "${env.NVIDIA_APPEND_API_VERSION:True}",
         }

llama_stack/providers/remote/inference/nvidia/nvidia.py

@@ -120,13 +120,10 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
             "meta/llama-3.2-90b-vision-instruct": "https://ai.api.nvidia.com/v1/gr/meta/llama-3.2-90b-vision-instruct",
         }
 
-        # add /v1 in case of hosted models
+        base_url = f"{self._config.url}/v1" if self._config.append_api_version else self._config.url
-        base_url = self._config.url
+
-        if _is_nvidia_hosted(self._config):
+        if _is_nvidia_hosted(self._config) and provider_model_id in special_model_urls:
-            if provider_model_id in special_model_urls:
             base_url = special_model_urls[provider_model_id]
-            else:
-                base_url = f"{self._config.url}/v1"
         return _get_client_for_base_url(base_url)
 
     async def completion(

llama_stack/providers/remote/post_training/nvidia/README.md

@@ -36,7 +36,6 @@ import os
 
 os.environ["NVIDIA_API_KEY"] = "your-api-key"
 os.environ["NVIDIA_CUSTOMIZER_URL"] = "http://nemo.test"
-os.environ["NVIDIA_USER_ID"] = "llama-stack-user"
 os.environ["NVIDIA_DATASET_NAMESPACE"] = "default"
 os.environ["NVIDIA_PROJECT_ID"] = "test-project"
 os.environ["NVIDIA_OUTPUT_MODEL_DIR"] = "test-example-model@v1"

llama_stack/templates/nvidia/nvidia.py

@@ -90,19 +90,15 @@ def get_distribution_template() -> DistributionTemplate:
                 "",
                 "NVIDIA API Key",
             ),
-            ## Nemo Customizer related variables
+            "NVIDIA_APPEND_API_VERSION": (
-            "NVIDIA_USER_ID": (
+                "True",
-                "llama-stack-user",
+                "Whether to append the API version to the base_url",
-                "NVIDIA User ID",
             ),
+            ## Nemo Customizer related variables
             "NVIDIA_DATASET_NAMESPACE": (
                 "default",
                 "NVIDIA Dataset Namespace",
             ),
-            "NVIDIA_ACCESS_POLICIES": (
-                "{}",
-                "NVIDIA Access Policies",
-            ),
             "NVIDIA_PROJECT_ID": (
                 "test-project",
                 "NVIDIA Project ID",

llama_stack/templates/nvidia/run-with-safety.yaml

@@ -18,6 +18,7 @@ providers:
     config:
       url: ${env.NVIDIA_BASE_URL:https://integrate.api.nvidia.com}
       api_key: ${env.NVIDIA_API_KEY:}
+      append_api_version: ${env.NVIDIA_APPEND_API_VERSION:True}
   - provider_id: nvidia
     provider_type: remote::nvidia
     config:

llama_stack/templates/nvidia/run.yaml

@@ -18,6 +18,7 @@ providers:
     config:
       url: ${env.NVIDIA_BASE_URL:https://integrate.api.nvidia.com}
       api_key: ${env.NVIDIA_API_KEY:}
+      append_api_version: ${env.NVIDIA_APPEND_API_VERSION:True}
   vector_io:
   - provider_id: faiss
     provider_type: inline::faiss