feat(providers): sambanova updated to use LiteLLM openai-compat

docs/source/distributions/self_hosted_distro/sambanova.md

@@ -16,10 +16,10 @@ The `llamastack/distribution-sambanova` distribution consists of the following p
 | API | Provider(s) |
 |-----|-------------|
 | agents | `inline::meta-reference` |
-| inference | `remote::sambanova` |
+| inference | `remote::sambanova`, `inline::sentence-transformers` |
 | safety | `inline::llama-guard` |
 | telemetry | `inline::meta-reference` |
-| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::rag-runtime` |
+| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::rag-runtime`, `remote::model-context-protocol`, `remote::wolfram-alpha` |
 | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 
 
@@ -28,22 +28,22 @@ The `llamastack/distribution-sambanova` distribution consists of the following p
 The following environment variables can be configured:
 
 - `LLAMASTACK_PORT`: Port for the Llama Stack distribution server (default: `8321`)
-- `SAMBANOVA_API_KEY`: SambaNova.AI API Key (default: ``)
+- `SAMBANOVA_API_KEY`: SambaNova API Key (default: ``)
 
 ### Models
 
 The following models are available by default:
 
-- `Meta-Llama-3.1-8B-Instruct (aliases: meta-llama/Llama-3.1-8B-Instruct)`
-- `Meta-Llama-3.1-70B-Instruct (aliases: meta-llama/Llama-3.1-70B-Instruct)`
-- `Meta-Llama-3.1-405B-Instruct (aliases: meta-llama/Llama-3.1-405B-Instruct-FP8)`
-- `Meta-Llama-3.2-1B-Instruct (aliases: meta-llama/Llama-3.2-1B-Instruct)`
-- `Meta-Llama-3.2-3B-Instruct (aliases: meta-llama/Llama-3.2-3B-Instruct)`
-- `Meta-Llama-3.3-70B-Instruct (aliases: meta-llama/Llama-3.3-70B-Instruct)`
-- `Llama-3.2-11B-Vision-Instruct (aliases: meta-llama/Llama-3.2-11B-Vision-Instruct)`
-- `Llama-3.2-90B-Vision-Instruct (aliases: meta-llama/Llama-3.2-90B-Vision-Instruct)`
-- `Meta-Llama-Guard-3-8B (aliases: meta-llama/Llama-Guard-3-8B)`
-- `Llama-4-Scout-17B-16E-Instruct (aliases: meta-llama/Llama-4-Scout-17B-16E-Instruct)`
+- `sambanova/Meta-Llama-3.1-8B-Instruct (aliases: meta-llama/Llama-3.1-8B-Instruct)`
+- `sambanova/Meta-Llama-3.1-405B-Instruct (aliases: meta-llama/Llama-3.1-405B-Instruct-FP8)`
+- `sambanova/Meta-Llama-3.2-1B-Instruct (aliases: meta-llama/Llama-3.2-1B-Instruct)`
+- `sambanova/Meta-Llama-3.2-3B-Instruct (aliases: meta-llama/Llama-3.2-3B-Instruct)`
+- `sambanova/Meta-Llama-3.3-70B-Instruct (aliases: meta-llama/Llama-3.3-70B-Instruct)`
+- `sambanova/Llama-3.2-11B-Vision-Instruct (aliases: meta-llama/Llama-3.2-11B-Vision-Instruct)`
+- `sambanova/Llama-3.2-90B-Vision-Instruct (aliases: meta-llama/Llama-3.2-90B-Vision-Instruct)`
+- `sambanova/Llama-4-Scout-17B-16E-Instruct (aliases: meta-llama/Llama-4-Scout-17B-16E-Instruct)`
+- `sambanova/Llama-4-Maverick-17B-128E-Instruct (aliases: meta-llama/Llama-4-Maverick-17B-128E-Instruct)`
+- `sambanova/Meta-Llama-Guard-3-8B (aliases: meta-llama/Llama-Guard-3-8B)`
 
 
 ### Prerequisite: API Keys

llama_stack/providers/registry/inference.py

@@ -280,11 +280,10 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter=AdapterSpec(
                 adapter_type="sambanova",
-                pip_packages=[
-                    "openai",
-                ],
+                pip_packages=["litellm"],
                 module="llama_stack.providers.remote.inference.sambanova",
                 config_class="llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig",
+                provider_data_validator="llama_stack.providers.remote.inference.sambanova.config.SambaNovaProviderDataValidator",
             ),
         ),
         remote_provider_spec(

llama_stack/providers/remote/inference/sambanova/__init__.py

@@ -4,16 +4,12 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from pydantic import BaseModel
+from llama_stack.apis.inference import Inference
 
 from .config import SambaNovaImplConfig
 
 
-class SambaNovaProviderDataValidator(BaseModel):
-    sambanova_api_key: str
-
-
-async def get_adapter_impl(config: SambaNovaImplConfig, _deps):
+async def get_adapter_impl(config: SambaNovaImplConfig, _deps) -> Inference:
     from .sambanova import SambaNovaInferenceAdapter
 
     assert isinstance(config, SambaNovaImplConfig), f"Unexpected config type: {type(config)}"

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

@@ -6,25 +6,32 @@
 
 from typing import Any
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, SecretStr
 
 from llama_stack.schema_utils import json_schema_type
 
 
+class SambaNovaProviderDataValidator(BaseModel):
+    sambanova_api_key: str | None = Field(
+        default=None,
+        description="Sambanova Cloud API key",
+    )
+
+
 @json_schema_type
 class SambaNovaImplConfig(BaseModel):
     url: str = Field(
         default="https://api.sambanova.ai/v1",
         description="The URL for the SambaNova AI server",
     )
-    api_key: str | None = Field(
+    api_key: SecretStr | None = Field(
         default=None,
-        description="The SambaNova.ai API Key",
+        description="The SambaNova cloud API Key",
     )
 
     @classmethod
-    def sample_run_config(cls, **kwargs) -> dict[str, Any]:
+    def sample_run_config(cls, api_key: str = "${env.SAMBANOVA_API_KEY}", **kwargs) -> dict[str, Any]:
         return {
             "url": "https://api.sambanova.ai/v1",
-            "api_key": "${env.SAMBANOVA_API_KEY}",
+            "api_key": api_key,
         }

llama_stack/providers/remote/inference/sambanova/models.py

@@ -11,43 +11,43 @@
 
 MODEL_ENTRIES = [
     build_hf_repo_model_entry(
-        "Meta-Llama-3.1-8B-Instruct",
+        "sambanova/Meta-Llama-3.1-8B-Instruct",
         CoreModelId.llama3_1_8b_instruct.value,
     ),
     build_hf_repo_model_entry(
-        "Meta-Llama-3.1-70B-Instruct",
-        CoreModelId.llama3_1_70b_instruct.value,
-    ),
-    build_hf_repo_model_entry(
-        "Meta-Llama-3.1-405B-Instruct",
+        "sambanova/Meta-Llama-3.1-405B-Instruct",
         CoreModelId.llama3_1_405b_instruct.value,
     ),
     build_hf_repo_model_entry(
-        "Meta-Llama-3.2-1B-Instruct",
+        "sambanova/Meta-Llama-3.2-1B-Instruct",
         CoreModelId.llama3_2_1b_instruct.value,
     ),
     build_hf_repo_model_entry(
-        "Meta-Llama-3.2-3B-Instruct",
+        "sambanova/Meta-Llama-3.2-3B-Instruct",
         CoreModelId.llama3_2_3b_instruct.value,
     ),
     build_hf_repo_model_entry(
-        "Meta-Llama-3.3-70B-Instruct",
+        "sambanova/Meta-Llama-3.3-70B-Instruct",
         CoreModelId.llama3_3_70b_instruct.value,
     ),
     build_hf_repo_model_entry(
-        "Llama-3.2-11B-Vision-Instruct",
+        "sambanova/Llama-3.2-11B-Vision-Instruct",
         CoreModelId.llama3_2_11b_vision_instruct.value,
     ),
     build_hf_repo_model_entry(
-        "Llama-3.2-90B-Vision-Instruct",
+        "sambanova/Llama-3.2-90B-Vision-Instruct",
         CoreModelId.llama3_2_90b_vision_instruct.value,
     ),
     build_hf_repo_model_entry(
-        "Meta-Llama-Guard-3-8B",
-        CoreModelId.llama_guard_3_8b.value,
+        "sambanova/Llama-4-Scout-17B-16E-Instruct",
+        CoreModelId.llama4_scout_17b_16e_instruct.value,
     ),
     build_hf_repo_model_entry(
-        "Llama-4-Scout-17B-16E-Instruct",
-        CoreModelId.llama4_scout_17b_16e_instruct.value,
+        "sambanova/Llama-4-Maverick-17B-128E-Instruct",
+        CoreModelId.llama4_maverick_17b_128e_instruct.value,
+    ),
+    build_hf_repo_model_entry(
+        "sambanova/Meta-Llama-Guard-3-8B",
+        CoreModelId.llama_guard_3_8b.value,
     ),
 ]