llama-stack 0.0.42__py3-none-any.whl → 0.3.4__py3-none-any.whl

llama_stack/providers/registry/files.py

@@ -0,0 +1,31 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec
+from llama_stack.providers.utils.sqlstore.sqlstore import sql_store_pip_packages
+
+
+def available_providers() -> list[ProviderSpec]:
+    return [
+        InlineProviderSpec(
+            api=Api.files,
+            provider_type="inline::localfs",
+            # TODO: make this dynamic according to the sql store type
+            pip_packages=sql_store_pip_packages,
+            module="llama_stack.providers.inline.files.localfs",
+            config_class="llama_stack.providers.inline.files.localfs.config.LocalfsFilesImplConfig",
+            description="Local filesystem-based file storage provider for managing files and documents locally.",
+        ),
+        RemoteProviderSpec(
+            api=Api.files,
+            provider_type="remote::s3",
+            adapter_type="s3",
+            pip_packages=["boto3"] + sql_store_pip_packages,
+            module="llama_stack.providers.remote.files.s3",
+            config_class="llama_stack.providers.remote.files.s3.config.S3FilesImplConfig",
+            description="AWS S3-based file storage provider for scalable cloud file management with metadata persistence.",
+        ),
+    ]

llama_stack/providers/registry/inference.py

@@ -4,139 +4,294 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import List
 
-from llama_stack.distribution.datatypes import *  # noqa: F403
+from llama_stack.providers.datatypes import (
+    Api,
+    InlineProviderSpec,
+    ProviderSpec,
+    RemoteProviderSpec,
+)
 
+META_REFERENCE_DEPS = [
+    "accelerate",
+    "fairscale",
+    "torch",
+    "torchvision",
+    "transformers",
+    "zmq",
+    "lm-format-enforcer",
+    "sentence-transformers",
+    "torchao==0.8.0",
+    "fbgemm-gpu-genai==1.1.2",
+]
 
-def available_providers() -> List[ProviderSpec]:
+
+def available_providers() -> list[ProviderSpec]:
     return [
         InlineProviderSpec(
             api=Api.inference,
-            provider_type="meta-reference",
+            provider_type="inline::meta-reference",
+            pip_packages=META_REFERENCE_DEPS,
+            module="llama_stack.providers.inline.inference.meta_reference",
+            config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceInferenceConfig",
+            description="Meta's reference implementation of inference with support for various model formats and optimization techniques.",
+        ),
+        InlineProviderSpec(
+            api=Api.inference,
+            provider_type="inline::sentence-transformers",
+            # CrossEncoder depends on torchao.quantization
             pip_packages=[
-                "accelerate",
-                "blobfile",
-                "fairscale",
-                "torch",
-                "torchvision",
-                "transformers",
-                "zmq",
+                "torch torchvision torchao>=0.12.0 --extra-index-url https://download.pytorch.org/whl/cpu",
+                "sentence-transformers --no-deps",
+                # required by some SentenceTransformers architectures for tensor rearrange/merge ops
+                "einops",
+                # fast HF tokenization backend used by SentenceTransformers models
+                "tokenizers",
+                # safe and fast file format for storing and loading tensors
+                "safetensors",
             ],
-            module="llama_stack.providers.impls.meta_reference.inference",
-            config_class="llama_stack.providers.impls.meta_reference.inference.MetaReferenceInferenceConfig",
+            module="llama_stack.providers.inline.inference.sentence_transformers",
+            config_class="llama_stack.providers.inline.inference.sentence_transformers.config.SentenceTransformersInferenceConfig",
+            description="Sentence Transformers inference provider for text embeddings and similarity search.",
         ),
-        InlineProviderSpec(
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="cerebras",
+            provider_type="remote::cerebras",
+            pip_packages=[],
+            module="llama_stack.providers.remote.inference.cerebras",
+            config_class="llama_stack.providers.remote.inference.cerebras.CerebrasImplConfig",
+            description="Cerebras inference provider for running models on Cerebras Cloud platform.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="ollama",
+            provider_type="remote::ollama",
+            pip_packages=["ollama", "aiohttp", "h11>=0.16.0"],
+            config_class="llama_stack.providers.remote.inference.ollama.OllamaImplConfig",
+            module="llama_stack.providers.remote.inference.ollama",
+            description="Ollama inference provider for running local models through the Ollama runtime.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="vllm",
+            provider_type="remote::vllm",
+            pip_packages=[],
+            module="llama_stack.providers.remote.inference.vllm",
+            config_class="llama_stack.providers.remote.inference.vllm.VLLMInferenceAdapterConfig",
+            provider_data_validator="llama_stack.providers.remote.inference.vllm.VLLMProviderDataValidator",
+            description="Remote vLLM inference provider for connecting to vLLM servers.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="tgi",
+            provider_type="remote::tgi",
+            pip_packages=["huggingface_hub", "aiohttp"],
+            module="llama_stack.providers.remote.inference.tgi",
+            config_class="llama_stack.providers.remote.inference.tgi.TGIImplConfig",
+            description="Text Generation Inference (TGI) provider for HuggingFace model serving.",
+        ),
+        RemoteProviderSpec(
             api=Api.inference,
-            provider_type="meta-reference-quantized",
+            adapter_type="hf::serverless",
+            provider_type="remote::hf::serverless",
+            pip_packages=["huggingface_hub", "aiohttp"],
+            module="llama_stack.providers.remote.inference.tgi",
+            config_class="llama_stack.providers.remote.inference.tgi.InferenceAPIImplConfig",
+            description="HuggingFace Inference API serverless provider for on-demand model inference.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            provider_type="remote::hf::endpoint",
+            adapter_type="hf::endpoint",
+            pip_packages=["huggingface_hub", "aiohttp"],
+            module="llama_stack.providers.remote.inference.tgi",
+            config_class="llama_stack.providers.remote.inference.tgi.InferenceEndpointImplConfig",
+            description="HuggingFace Inference Endpoints provider for dedicated model serving.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="fireworks",
+            provider_type="remote::fireworks",
             pip_packages=[
-                "accelerate",
-                "blobfile",
-                "fairscale",
-                "fbgemm-gpu==0.8.0",
-                "torch",
-                "torchvision",
-                "transformers",
-                "zmq",
+                "fireworks-ai<=0.17.16",
             ],
-            module="llama_stack.providers.impls.meta_reference.inference",
-            config_class="llama_stack.providers.impls.meta_reference.inference.MetaReferenceQuantizedInferenceConfig",
-        ),
-        remote_provider_spec(
-            api=Api.inference,
-            adapter=AdapterSpec(
-                adapter_type="sample",
-                pip_packages=[],
-                module="llama_stack.providers.adapters.inference.sample",
-                config_class="llama_stack.providers.adapters.inference.sample.SampleConfig",
-            ),
-        ),
-        remote_provider_spec(
-            api=Api.inference,
-            adapter=AdapterSpec(
-                adapter_type="ollama",
-                pip_packages=["ollama"],
-                config_class="llama_stack.providers.adapters.inference.ollama.OllamaImplConfig",
-                module="llama_stack.providers.adapters.inference.ollama",
-            ),
-        ),
-        remote_provider_spec(
-            api=Api.inference,
-            adapter=AdapterSpec(
-                adapter_type="tgi",
-                pip_packages=["huggingface_hub", "aiohttp"],
-                module="llama_stack.providers.adapters.inference.tgi",
-                config_class="llama_stack.providers.adapters.inference.tgi.TGIImplConfig",
-            ),
-        ),
-        remote_provider_spec(
-            api=Api.inference,
-            adapter=AdapterSpec(
-                adapter_type="hf::serverless",
-                pip_packages=["huggingface_hub", "aiohttp"],
-                module="llama_stack.providers.adapters.inference.tgi",
-                config_class="llama_stack.providers.adapters.inference.tgi.InferenceAPIImplConfig",
-            ),
-        ),
-        remote_provider_spec(
-            api=Api.inference,
-            adapter=AdapterSpec(
-                adapter_type="hf::endpoint",
-                pip_packages=["huggingface_hub", "aiohttp"],
-                module="llama_stack.providers.adapters.inference.tgi",
-                config_class="llama_stack.providers.adapters.inference.tgi.InferenceEndpointImplConfig",
-            ),
-        ),
-        remote_provider_spec(
-            api=Api.inference,
-            adapter=AdapterSpec(
-                adapter_type="fireworks",
-                pip_packages=[
-                    "fireworks-ai",
-                ],
-                module="llama_stack.providers.adapters.inference.fireworks",
-                config_class="llama_stack.providers.adapters.inference.fireworks.FireworksImplConfig",
-            ),
-        ),
-        remote_provider_spec(
-            api=Api.inference,
-            adapter=AdapterSpec(
-                adapter_type="together",
-                pip_packages=[
-                    "together",
-                ],
-                module="llama_stack.providers.adapters.inference.together",
-                config_class="llama_stack.providers.adapters.inference.together.TogetherImplConfig",
-                provider_data_validator="llama_stack.providers.adapters.safety.together.TogetherProviderDataValidator",
-            ),
-        ),
-        remote_provider_spec(
-            api=Api.inference,
-            adapter=AdapterSpec(
-                adapter_type="bedrock",
-                pip_packages=["boto3"],
-                module="llama_stack.providers.adapters.inference.bedrock",
-                config_class="llama_stack.providers.adapters.inference.bedrock.BedrockConfig",
-            ),
-        ),
-        remote_provider_spec(
-            api=Api.inference,
-            adapter=AdapterSpec(
-                adapter_type="databricks",
-                pip_packages=[
-                    "openai",
-                ],
-                module="llama_stack.providers.adapters.inference.databricks",
-                config_class="llama_stack.providers.adapters.inference.databricks.DatabricksImplConfig",
-            ),
+            module="llama_stack.providers.remote.inference.fireworks",
+            config_class="llama_stack.providers.remote.inference.fireworks.FireworksImplConfig",
+            provider_data_validator="llama_stack.providers.remote.inference.fireworks.FireworksProviderDataValidator",
+            description="Fireworks AI inference provider for Llama models and other AI models on the Fireworks platform.",
         ),
-        InlineProviderSpec(
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="together",
+            provider_type="remote::together",
+            pip_packages=[
+                "together",
+            ],
+            module="llama_stack.providers.remote.inference.together",
+            config_class="llama_stack.providers.remote.inference.together.TogetherImplConfig",
+            provider_data_validator="llama_stack.providers.remote.inference.together.TogetherProviderDataValidator",
+            description="Together AI inference provider for open-source models and collaborative AI development.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="bedrock",
+            provider_type="remote::bedrock",
+            pip_packages=["boto3"],
+            module="llama_stack.providers.remote.inference.bedrock",
+            config_class="llama_stack.providers.remote.inference.bedrock.BedrockConfig",
+            description="AWS Bedrock inference provider for accessing various AI models through AWS's managed service.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="databricks",
+            provider_type="remote::databricks",
+            pip_packages=["databricks-sdk"],
+            module="llama_stack.providers.remote.inference.databricks",
+            config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig",
+            description="Databricks inference provider for running models on Databricks' unified analytics platform.",
+        ),
+        RemoteProviderSpec(
             api=Api.inference,
-            provider_type="vllm",
+            adapter_type="nvidia",
+            provider_type="remote::nvidia",
+            pip_packages=[],
+            module="llama_stack.providers.remote.inference.nvidia",
+            config_class="llama_stack.providers.remote.inference.nvidia.NVIDIAConfig",
+            description="NVIDIA inference provider for accessing NVIDIA NIM models and AI services.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="runpod",
+            provider_type="remote::runpod",
+            pip_packages=[],
+            module="llama_stack.providers.remote.inference.runpod",
+            config_class="llama_stack.providers.remote.inference.runpod.RunpodImplConfig",
+            description="RunPod inference provider for running models on RunPod's cloud GPU platform.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="openai",
+            provider_type="remote::openai",
+            pip_packages=[],
+            module="llama_stack.providers.remote.inference.openai",
+            config_class="llama_stack.providers.remote.inference.openai.OpenAIConfig",
+            provider_data_validator="llama_stack.providers.remote.inference.openai.config.OpenAIProviderDataValidator",
+            description="OpenAI inference provider for accessing GPT models and other OpenAI services.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="anthropic",
+            provider_type="remote::anthropic",
+            pip_packages=["anthropic"],
+            module="llama_stack.providers.remote.inference.anthropic",
+            config_class="llama_stack.providers.remote.inference.anthropic.AnthropicConfig",
+            provider_data_validator="llama_stack.providers.remote.inference.anthropic.config.AnthropicProviderDataValidator",
+            description="Anthropic inference provider for accessing Claude models and Anthropic's AI services.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="gemini",
+            provider_type="remote::gemini",
+            pip_packages=[],
+            module="llama_stack.providers.remote.inference.gemini",
+            config_class="llama_stack.providers.remote.inference.gemini.GeminiConfig",
+            provider_data_validator="llama_stack.providers.remote.inference.gemini.config.GeminiProviderDataValidator",
+            description="Google Gemini inference provider for accessing Gemini models and Google's AI services.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="vertexai",
+            provider_type="remote::vertexai",
             pip_packages=[
-                "vllm",
+                "google-cloud-aiplatform",
             ],
-            module="llama_stack.providers.impls.vllm",
-            config_class="llama_stack.providers.impls.vllm.VLLMConfig",
+            module="llama_stack.providers.remote.inference.vertexai",
+            config_class="llama_stack.providers.remote.inference.vertexai.VertexAIConfig",
+            provider_data_validator="llama_stack.providers.remote.inference.vertexai.config.VertexAIProviderDataValidator",
+            description="""Google Vertex AI inference provider enables you to use Google's Gemini models through Google Cloud's Vertex AI platform, providing several advantages:
+
+• Enterprise-grade security: Uses Google Cloud's security controls and IAM
+• Better integration: Seamless integration with other Google Cloud services
+• Advanced features: Access to additional Vertex AI features like model tuning and monitoring
+• Authentication: Uses Google Cloud Application Default Credentials (ADC) instead of API keys
+
+Configuration:
+- Set VERTEX_AI_PROJECT environment variable (required)
+- Set VERTEX_AI_LOCATION environment variable (optional, defaults to us-central1)
+- Use Google Cloud Application Default Credentials or service account key
+
+Authentication Setup:
+Option 1 (Recommended): gcloud auth application-default login
+Option 2: Set GOOGLE_APPLICATION_CREDENTIALS to service account key path
+
+Available Models:
+- vertex_ai/gemini-2.0-flash
+- vertex_ai/gemini-2.5-flash
+- vertex_ai/gemini-2.5-pro""",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="groq",
+            provider_type="remote::groq",
+            pip_packages=[],
+            module="llama_stack.providers.remote.inference.groq",
+            config_class="llama_stack.providers.remote.inference.groq.GroqConfig",
+            provider_data_validator="llama_stack.providers.remote.inference.groq.config.GroqProviderDataValidator",
+            description="Groq inference provider for ultra-fast inference using Groq's LPU technology.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="llama-openai-compat",
+            provider_type="remote::llama-openai-compat",
+            pip_packages=[],
+            module="llama_stack.providers.remote.inference.llama_openai_compat",
+            config_class="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaCompatConfig",
+            provider_data_validator="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaProviderDataValidator",
+            description="Llama OpenAI-compatible provider for using Llama models with OpenAI API format.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="sambanova",
+            provider_type="remote::sambanova",
+            pip_packages=[],
+            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",
+            description="SambaNova inference provider for running models on SambaNova's dataflow architecture.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="passthrough",
+            provider_type="remote::passthrough",
+            pip_packages=[],
+            module="llama_stack.providers.remote.inference.passthrough",
+            config_class="llama_stack.providers.remote.inference.passthrough.PassthroughImplConfig",
+            provider_data_validator="llama_stack.providers.remote.inference.passthrough.PassthroughProviderDataValidator",
+            description="Passthrough inference provider for connecting to any external inference service not directly supported.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            adapter_type="watsonx",
+            provider_type="remote::watsonx",
+            pip_packages=["litellm"],
+            module="llama_stack.providers.remote.inference.watsonx",
+            config_class="llama_stack.providers.remote.inference.watsonx.WatsonXConfig",
+            provider_data_validator="llama_stack.providers.remote.inference.watsonx.config.WatsonXProviderDataValidator",
+            description="IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform.",
+        ),
+        RemoteProviderSpec(
+            api=Api.inference,
+            provider_type="remote::azure",
+            adapter_type="azure",
+            pip_packages=[],
+            module="llama_stack.providers.remote.inference.azure",
+            config_class="llama_stack.providers.remote.inference.azure.AzureConfig",
+            provider_data_validator="llama_stack.providers.remote.inference.azure.config.AzureProviderDataValidator",
+            description="""
+Azure OpenAI inference provider for accessing GPT models and other Azure services.
+Provider documentation
+https://learn.microsoft.com/en-us/azure/ai-foundry/openai/overview
+""",
         ),
     ]

llama_stack/providers/registry/post_training.py

@@ -0,0 +1,69 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+
+from typing import cast
+
+from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec
+
+# We provide two versions of these providers so that distributions can package the appropriate version of torch.
+# The CPU version is used for distributions that don't have GPU support -- they result in smaller container images.
+torchtune_def = dict(
+    api=Api.post_training,
+    pip_packages=["numpy"],
+    module="llama_stack.providers.inline.post_training.torchtune",
+    config_class="llama_stack.providers.inline.post_training.torchtune.TorchtunePostTrainingConfig",
+    api_dependencies=[
+        Api.datasetio,
+        Api.datasets,
+    ],
+    description="TorchTune-based post-training provider for fine-tuning and optimizing models using Meta's TorchTune framework.",
+)
+
+
+def available_providers() -> list[ProviderSpec]:
+    return [
+        InlineProviderSpec(
+            **{  # type: ignore
+                **torchtune_def,
+                "provider_type": "inline::torchtune-cpu",
+                "pip_packages": (
+                    cast(list[str], torchtune_def["pip_packages"])
+                    + ["torch torchtune>=0.5.0 torchao>=0.12.0 --extra-index-url https://download.pytorch.org/whl/cpu"]
+                ),
+            },
+        ),
+        InlineProviderSpec(
+            **{  # type: ignore
+                **torchtune_def,
+                "provider_type": "inline::torchtune-gpu",
+                "pip_packages": (
+                    cast(list[str], torchtune_def["pip_packages"]) + ["torch torchtune>=0.5.0 torchao>=0.12.0"]
+                ),
+            },
+        ),
+        InlineProviderSpec(
+            api=Api.post_training,
+            provider_type="inline::huggingface-gpu",
+            pip_packages=["trl", "transformers", "peft", "datasets>=4.0.0", "torch"],
+            module="llama_stack.providers.inline.post_training.huggingface",
+            config_class="llama_stack.providers.inline.post_training.huggingface.HuggingFacePostTrainingConfig",
+            api_dependencies=[
+                Api.datasetio,
+                Api.datasets,
+            ],
+            description="HuggingFace-based post-training provider for fine-tuning models using the HuggingFace ecosystem.",
+        ),
+        RemoteProviderSpec(
+            api=Api.post_training,
+            adapter_type="nvidia",
+            provider_type="remote::nvidia",
+            pip_packages=["requests", "aiohttp"],
+            module="llama_stack.providers.remote.post_training.nvidia",
+            config_class="llama_stack.providers.remote.post_training.nvidia.NvidiaPostTrainingConfig",
+            description="NVIDIA's post-training provider for fine-tuning models on NVIDIA's platform.",
+        ),
+    ]

llama_stack/providers/registry/safety.py

@@ -4,70 +4,75 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import List
 
-from llama_stack.distribution.datatypes import (
-    AdapterSpec,
+from llama_stack.providers.datatypes import (
     Api,
     InlineProviderSpec,
     ProviderSpec,
-    remote_provider_spec,
+    RemoteProviderSpec,
 )
 
 
-def available_providers() -> List[ProviderSpec]:
+def available_providers() -> list[ProviderSpec]:
     return [
         InlineProviderSpec(
             api=Api.safety,
-            provider_type="meta-reference",
+            provider_type="inline::prompt-guard",
             pip_packages=[
-                "transformers",
+                "transformers[accelerate]",
                 "torch --index-url https://download.pytorch.org/whl/cpu",
             ],
-            module="llama_stack.providers.impls.meta_reference.safety",
-            config_class="llama_stack.providers.impls.meta_reference.safety.SafetyConfig",
+            module="llama_stack.providers.inline.safety.prompt_guard",
+            config_class="llama_stack.providers.inline.safety.prompt_guard.PromptGuardConfig",
+            description="Prompt Guard safety provider for detecting and filtering unsafe prompts and content.",
+        ),
+        InlineProviderSpec(
+            api=Api.safety,
+            provider_type="inline::llama-guard",
+            pip_packages=[],
+            module="llama_stack.providers.inline.safety.llama_guard",
+            config_class="llama_stack.providers.inline.safety.llama_guard.LlamaGuardConfig",
             api_dependencies=[
                 Api.inference,
             ],
+            description="Llama Guard safety provider for content moderation and safety filtering using Meta's Llama Guard model.",
         ),
-        remote_provider_spec(
+        InlineProviderSpec(
             api=Api.safety,
-            adapter=AdapterSpec(
-                adapter_type="sample",
-                pip_packages=[],
-                module="llama_stack.providers.adapters.safety.sample",
-                config_class="llama_stack.providers.adapters.safety.sample.SampleConfig",
-            ),
+            provider_type="inline::code-scanner",
+            pip_packages=[
+                "codeshield",
+            ],
+            module="llama_stack.providers.inline.safety.code_scanner",
+            config_class="llama_stack.providers.inline.safety.code_scanner.CodeScannerConfig",
+            description="Code Scanner safety provider for detecting security vulnerabilities and unsafe code patterns.",
         ),
-        remote_provider_spec(
+        RemoteProviderSpec(
             api=Api.safety,
-            adapter=AdapterSpec(
-                adapter_type="bedrock",
-                pip_packages=["boto3"],
-                module="llama_stack.providers.adapters.safety.bedrock",
-                config_class="llama_stack.providers.adapters.safety.bedrock.BedrockSafetyConfig",
-            ),
+            adapter_type="bedrock",
+            provider_type="remote::bedrock",
+            pip_packages=["boto3"],
+            module="llama_stack.providers.remote.safety.bedrock",
+            config_class="llama_stack.providers.remote.safety.bedrock.BedrockSafetyConfig",
+            description="AWS Bedrock safety provider for content moderation using AWS's safety services.",
         ),
-        remote_provider_spec(
+        RemoteProviderSpec(
             api=Api.safety,
-            adapter=AdapterSpec(
-                adapter_type="together",
-                pip_packages=[
-                    "together",
-                ],
-                module="llama_stack.providers.adapters.safety.together",
-                config_class="llama_stack.providers.adapters.safety.together.TogetherSafetyConfig",
-                provider_data_validator="llama_stack.providers.adapters.safety.together.TogetherProviderDataValidator",
-            ),
+            adapter_type="nvidia",
+            provider_type="remote::nvidia",
+            pip_packages=["requests"],
+            module="llama_stack.providers.remote.safety.nvidia",
+            config_class="llama_stack.providers.remote.safety.nvidia.NVIDIASafetyConfig",
+            description="NVIDIA's safety provider for content moderation and safety filtering.",
         ),
-        InlineProviderSpec(
+        RemoteProviderSpec(
             api=Api.safety,
-            provider_type="meta-reference/codeshield",
-            pip_packages=[
-                "codeshield",
-            ],
-            module="llama_stack.providers.impls.meta_reference.codeshield",
-            config_class="llama_stack.providers.impls.meta_reference.codeshield.CodeShieldConfig",
-            api_dependencies=[],
+            adapter_type="sambanova",
+            provider_type="remote::sambanova",
+            pip_packages=["litellm", "requests"],
+            module="llama_stack.providers.remote.safety.sambanova",
+            config_class="llama_stack.providers.remote.safety.sambanova.SambaNovaSafetyConfig",
+            provider_data_validator="llama_stack.providers.remote.safety.sambanova.config.SambaNovaProviderDataValidator",
+            description="SambaNova's safety provider for content moderation and safety filtering.",
         ),
     ]