Merged from main + fixed elasticsearch_url

src/llama_stack/distributions/ci-tests/ci_tests.py

@@ -13,6 +13,5 @@ from ..starter.starter import get_distribution_template as get_starter_distribut
 def get_distribution_template() -> DistributionTemplate:
     template = get_starter_distribution_template(name="ci-tests")
     template.description = "CI tests for Llama Stack"
-    template.run_configs.pop("run-with-postgres-store.yaml", None)
 
     return template

src/llama_stack/distributions/ci-tests/run-with-postgres-store.yaml

@@ -0,0 +1,293 @@
+version: 2
+image_name: ci-tests
+apis:
+- agents
+- batches
+- datasetio
+- eval
+- files
+- inference
+- post_training
+- safety
+- scoring
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
+    provider_type: remote::cerebras
+    config:
+      base_url: https://api.cerebras.ai
+      api_key: ${env.CEREBRAS_API_KEY:=}
+  - provider_id: ${env.OLLAMA_URL:+ollama}
+    provider_type: remote::ollama
+    config:
+      url: ${env.OLLAMA_URL:=http://localhost:11434}
+  - provider_id: ${env.VLLM_URL:+vllm}
+    provider_type: remote::vllm
+    config:
+      url: ${env.VLLM_URL:=}
+      max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
+      api_token: ${env.VLLM_API_TOKEN:=fake}
+      tls_verify: ${env.VLLM_TLS_VERIFY:=true}
+  - provider_id: ${env.TGI_URL:+tgi}
+    provider_type: remote::tgi
+    config:
+      url: ${env.TGI_URL:=}
+  - provider_id: fireworks
+    provider_type: remote::fireworks
+    config:
+      url: https://api.fireworks.ai/inference/v1
+      api_key: ${env.FIREWORKS_API_KEY:=}
+  - provider_id: together
+    provider_type: remote::together
+    config:
+      url: https://api.together.xyz/v1
+      api_key: ${env.TOGETHER_API_KEY:=}
+  - provider_id: bedrock
+    provider_type: remote::bedrock
+    config:
+      api_key: ${env.AWS_BEDROCK_API_KEY:=}
+      region_name: ${env.AWS_DEFAULT_REGION:=us-east-2}
+  - provider_id: ${env.NVIDIA_API_KEY:+nvidia}
+    provider_type: remote::nvidia
+    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: openai
+    provider_type: remote::openai
+    config:
+      api_key: ${env.OPENAI_API_KEY:=}
+      base_url: ${env.OPENAI_BASE_URL:=https://api.openai.com/v1}
+  - provider_id: anthropic
+    provider_type: remote::anthropic
+    config:
+      api_key: ${env.ANTHROPIC_API_KEY:=}
+  - provider_id: gemini
+    provider_type: remote::gemini
+    config:
+      api_key: ${env.GEMINI_API_KEY:=}
+  - provider_id: ${env.VERTEX_AI_PROJECT:+vertexai}
+    provider_type: remote::vertexai
+    config:
+      project: ${env.VERTEX_AI_PROJECT:=}
+      location: ${env.VERTEX_AI_LOCATION:=us-central1}
+  - provider_id: groq
+    provider_type: remote::groq
+    config:
+      url: https://api.groq.com
+      api_key: ${env.GROQ_API_KEY:=}
+  - provider_id: sambanova
+    provider_type: remote::sambanova
+    config:
+      url: https://api.sambanova.ai/v1
+      api_key: ${env.SAMBANOVA_API_KEY:=}
+  - provider_id: ${env.AZURE_API_KEY:+azure}
+    provider_type: remote::azure
+    config:
+      api_key: ${env.AZURE_API_KEY:=}
+      api_base: ${env.AZURE_API_BASE:=}
+      api_version: ${env.AZURE_API_VERSION:=}
+      api_type: ${env.AZURE_API_TYPE:=}
+  - provider_id: sentence-transformers
+    provider_type: inline::sentence-transformers
+  vector_io:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      persistence:
+        namespace: vector_io::faiss
+        backend: kv_default
+  - provider_id: sqlite-vec
+    provider_type: inline::sqlite-vec
+    config:
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/sqlite_vec.db
+      persistence:
+        namespace: vector_io::sqlite_vec
+        backend: kv_default
+  - provider_id: ${env.MILVUS_URL:+milvus}
+    provider_type: inline::milvus
+    config:
+      db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/ci-tests}/milvus.db
+      persistence:
+        namespace: vector_io::milvus
+        backend: kv_default
+  - provider_id: ${env.CHROMADB_URL:+chromadb}
+    provider_type: remote::chromadb
+    config:
+      url: ${env.CHROMADB_URL:=}
+      persistence:
+        namespace: vector_io::chroma_remote
+        backend: kv_default
+  - provider_id: ${env.PGVECTOR_DB:+pgvector}
+    provider_type: remote::pgvector
+    config:
+      host: ${env.PGVECTOR_HOST:=localhost}
+      port: ${env.PGVECTOR_PORT:=5432}
+      db: ${env.PGVECTOR_DB:=}
+      user: ${env.PGVECTOR_USER:=}
+      password: ${env.PGVECTOR_PASSWORD:=}
+      persistence:
+        namespace: vector_io::pgvector
+        backend: kv_default
+  - provider_id: ${env.QDRANT_URL:+qdrant}
+    provider_type: remote::qdrant
+    config:
+      api_key: ${env.QDRANT_API_KEY:=}
+      persistence:
+        namespace: vector_io::qdrant_remote
+        backend: kv_default
+  - provider_id: ${env.WEAVIATE_CLUSTER_URL:+weaviate}
+    provider_type: remote::weaviate
+    config:
+      weaviate_api_key: null
+      weaviate_cluster_url: ${env.WEAVIATE_CLUSTER_URL:=localhost:8080}
+      persistence:
+        namespace: vector_io::weaviate
+        backend: kv_default
+  files:
+  - provider_id: meta-reference-files
+    provider_type: inline::localfs
+    config:
+      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/ci-tests/files}
+      metadata_store:
+        table_name: files_metadata
+        backend: sql_default
+  safety:
+  - provider_id: llama-guard
+    provider_type: inline::llama-guard
+    config:
+      excluded_categories: []
+  - provider_id: code-scanner
+    provider_type: inline::code-scanner
+  agents:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      persistence:
+        agent_state:
+          namespace: agents
+          backend: kv_default
+        responses:
+          table_name: responses
+          backend: sql_default
+          max_write_queue_size: 10000
+          num_writers: 4
+  post_training:
+  - provider_id: torchtune-cpu
+    provider_type: inline::torchtune-cpu
+    config:
+      checkpoint_format: meta
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        namespace: eval
+        backend: kv_default
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config:
+      kvstore:
+        namespace: datasetio::huggingface
+        backend: kv_default
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config:
+      kvstore:
+        namespace: datasetio::localfs
+        backend: kv_default
+  scoring:
+  - provider_id: basic
+    provider_type: inline::basic
+  - provider_id: llm-as-judge
+    provider_type: inline::llm-as-judge
+  - provider_id: braintrust
+    provider_type: inline::braintrust
+    config:
+      openai_api_key: ${env.OPENAI_API_KEY:=}
+  tool_runtime:
+  - provider_id: brave-search
+    provider_type: remote::brave-search
+    config:
+      api_key: ${env.BRAVE_SEARCH_API_KEY:=}
+      max_results: 3
+  - provider_id: tavily-search
+    provider_type: remote::tavily-search
+    config:
+      api_key: ${env.TAVILY_SEARCH_API_KEY:=}
+      max_results: 3
+  - provider_id: rag-runtime
+    provider_type: inline::rag-runtime
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+  batches:
+  - provider_id: reference
+    provider_type: inline::reference
+    config:
+      kvstore:
+        namespace: batches
+        backend: kv_default
+storage:
+  backends:
+    kv_default:
+      type: kv_postgres
+      host: ${env.POSTGRES_HOST:=localhost}
+      port: ${env.POSTGRES_PORT:=5432}
+      db: ${env.POSTGRES_DB:=llamastack}
+      user: ${env.POSTGRES_USER:=llamastack}
+      password: ${env.POSTGRES_PASSWORD:=llamastack}
+      table_name: ${env.POSTGRES_TABLE_NAME:=llamastack_kvstore}
+    sql_default:
+      type: sql_postgres
+      host: ${env.POSTGRES_HOST:=localhost}
+      port: ${env.POSTGRES_PORT:=5432}
+      db: ${env.POSTGRES_DB:=llamastack}
+      user: ${env.POSTGRES_USER:=llamastack}
+      password: ${env.POSTGRES_PASSWORD:=llamastack}
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
+    prompts:
+      namespace: prompts
+      backend: kv_default
+registered_resources:
+  models: []
+  shields:
+  - shield_id: llama-guard
+    provider_id: ${env.SAFETY_MODEL:+llama-guard}
+    provider_shield_id: ${env.SAFETY_MODEL:=}
+  - shield_id: code-scanner
+    provider_id: ${env.CODE_SCANNER_MODEL:+code-scanner}
+    provider_shield_id: ${env.CODE_SCANNER_MODEL:=}
+  vector_dbs: []
+  datasets: []
+  scoring_fns: []
+  benchmarks: []
+  tool_groups:
+  - toolgroup_id: builtin::websearch
+    provider_id: tavily-search
+  - toolgroup_id: builtin::rag
+    provider_id: rag-runtime
+server:
+  port: 8321
+telemetry:
+  enabled: true
+vector_stores:
+  default_provider_id: faiss
+  default_embedding_model:
+    provider_id: sentence-transformers
+    model_id: nomic-ai/nomic-embed-text-v1.5
+safety:
+  default_shield_id: llama-guard

src/llama_stack/distributions/dell/dell.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from llama_stack.apis.models import ModelType
 from llama_stack.core.datatypes import (
     BuildProvider,
     ModelInput,
@@ -17,6 +16,7 @@ from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
 from llama_stack.providers.remote.vector_io.chroma import ChromaVectorIOConfig
+from llama_stack_api import ModelType
 
 
 def get_distribution_template() -> DistributionTemplate:

src/llama_stack/distributions/meta-reference-gpu/meta_reference.py

@@ -6,7 +6,6 @@
 
 from pathlib import Path
 
-from llama_stack.apis.models import ModelType
 from llama_stack.core.datatypes import (
     BuildProvider,
     ModelInput,
@@ -22,6 +21,7 @@ from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
 from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
+from llama_stack_api import ModelType
 
 
 def get_distribution_template() -> DistributionTemplate:

src/llama_stack/distributions/oci/__init__.py

@@ -0,0 +1,7 @@
+# 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 .oci import get_distribution_template  # noqa: F401

src/llama_stack/distributions/oci/build.yaml

@@ -0,0 +1,35 @@
+version: 2
+distribution_spec:
+  description: Use Oracle Cloud Infrastructure (OCI) Generative AI for running LLM
+    inference with scalable cloud services
+  providers:
+    inference:
+    - provider_type: remote::oci
+    vector_io:
+    - provider_type: inline::faiss
+    - provider_type: remote::chromadb
+    - provider_type: remote::pgvector
+    safety:
+    - provider_type: inline::llama-guard
+    agents:
+    - provider_type: inline::meta-reference
+    eval:
+    - provider_type: inline::meta-reference
+    datasetio:
+    - provider_type: remote::huggingface
+    - provider_type: inline::localfs
+    scoring:
+    - provider_type: inline::basic
+    - provider_type: inline::llm-as-judge
+    - provider_type: inline::braintrust
+    tool_runtime:
+    - provider_type: remote::brave-search
+    - provider_type: remote::tavily-search
+    - provider_type: inline::rag-runtime
+    - provider_type: remote::model-context-protocol
+    files:
+    - provider_type: inline::localfs
+image_type: venv
+additional_pip_packages:
+- aiosqlite
+- sqlalchemy[asyncio]

src/llama_stack/distributions/oci/doc_template.md

@@ -0,0 +1,140 @@
+---
+orphan: true
+---
+# OCI Distribution
+
+The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
+
+{{ providers_table }}
+
+{% if run_config_env_vars %}
+### Environment Variables
+
+The following environment variables can be configured:
+
+{% for var, (default_value, description) in run_config_env_vars.items() %}
+- `{{ var }}`: {{ description }} (default: `{{ default_value }}`)
+{% endfor %}
+{% endif %}
+
+{% if default_models %}
+### Models
+
+The following models are available by default:
+
+{% for model in default_models %}
+- `{{ model.model_id }} {{ model.doc_string }}`
+{% endfor %}
+{% endif %}
+
+## Prerequisites
+### Oracle Cloud Infrastructure Setup
+
+Before using the OCI Generative AI distribution, ensure you have:
+
+1. **Oracle Cloud Infrastructure Account**: Sign up at [Oracle Cloud Infrastructure](https://cloud.oracle.com/)
+2. **Generative AI Service Access**: Enable the Generative AI service in your OCI tenancy
+3. **Compartment**: Create or identify a compartment where you'll deploy Generative AI models
+4. **Authentication**: Configure authentication using either:
+   - **Instance Principal** (recommended for cloud-hosted deployments)
+   - **API Key** (for on-premises or development environments)
+
+### Authentication Methods
+
+#### Instance Principal Authentication (Recommended)
+Instance Principal authentication allows OCI resources to authenticate using the identity of the compute instance they're running on. This is the most secure method for production deployments.
+
+Requirements:
+- Instance must be running in an Oracle Cloud Infrastructure compartment
+- Instance must have appropriate IAM policies to access Generative AI services
+
+#### API Key Authentication
+For development or on-premises deployments, follow [this doc](https://docs.oracle.com/en-us/iaas/Content/API/Concepts/apisigningkey.htm) to learn how to create your API signing key for your config file.
+
+### Required IAM Policies
+
+Ensure your OCI user or instance has the following policy statements:
+
+```
+Allow group <group_name> to use generative-ai-inference-endpoints in compartment <compartment_name>
+Allow group <group_name> to manage generative-ai-inference-endpoints in compartment <compartment_name>
+```
+
+## Supported Services
+
+### Inference: OCI Generative AI
+Oracle Cloud Infrastructure Generative AI provides access to high-performance AI models through OCI's Platform-as-a-Service offering. The service supports:
+
+- **Chat Completions**: Conversational AI with context awareness
+- **Text Generation**: Complete prompts and generate text content
+
+#### Available Models
+Common OCI Generative AI models include access to Meta, Cohere, OpenAI, Grok, and more models.
+
+### Safety: Llama Guard
+For content safety and moderation, this distribution uses Meta's LlamaGuard model through the OCI Generative AI service to provide:
+- Content filtering and moderation
+- Policy compliance checking
+- Harmful content detection
+
+### Vector Storage: Multiple Options
+The distribution supports several vector storage providers:
+- **FAISS**: Local in-memory vector search
+- **ChromaDB**: Distributed vector database
+- **PGVector**: PostgreSQL with vector extensions
+
+### Additional Services
+- **Dataset I/O**: Local filesystem and Hugging Face integration
+- **Tool Runtime**: Web search (Brave, Tavily) and RAG capabilities
+- **Evaluation**: Meta reference evaluation framework
+
+## Running Llama Stack with OCI
+
+You can run the OCI distribution via Docker or local virtual environment.
+
+### Via venv
+
+If you've set up your local development environment, you can also build the image using your local virtual environment.
+
+```bash
+OCI_AUTH=$OCI_AUTH_TYPE OCI_REGION=$OCI_REGION OCI_COMPARTMENT_OCID=$OCI_COMPARTMENT_OCID llama stack run --port 8321 oci
+```
+
+### Configuration Examples
+
+#### Using Instance Principal (Recommended for Production)
+```bash
+export OCI_AUTH_TYPE=instance_principal
+export OCI_REGION=us-chicago-1
+export OCI_COMPARTMENT_OCID=ocid1.compartment.oc1..<your-compartment-id>
+```
+
+#### Using API Key Authentication (Development)
+```bash
+export OCI_AUTH_TYPE=config_file
+export OCI_CONFIG_FILE_PATH=~/.oci/config
+export OCI_CLI_PROFILE=DEFAULT
+export OCI_REGION=us-chicago-1
+export OCI_COMPARTMENT_OCID=ocid1.compartment.oc1..your-compartment-id
+```
+
+## Regional Endpoints
+
+OCI Generative AI is available in multiple regions. The service automatically routes to the appropriate regional endpoint based on your configuration. For a full list of regional model availability, visit:
+
+https://docs.oracle.com/en-us/iaas/Content/generative-ai/overview.htm#regions
+
+## Troubleshooting
+
+### Common Issues
+
+1. **Authentication Errors**: Verify your OCI credentials and IAM policies
+2. **Model Not Found**: Ensure the model OCID is correct and the model is available in your region
+3. **Permission Denied**: Check compartment permissions and Generative AI service access
+4. **Region Unavailable**: Verify the specified region supports Generative AI services
+
+### Getting Help
+
+For additional support:
+- [OCI Generative AI Documentation](https://docs.oracle.com/en-us/iaas/Content/generative-ai/home.htm)
+- [Llama Stack Issues](https://github.com/meta-llama/llama-stack/issues)

src/llama_stack/distributions/oci/oci.py

@@ -0,0 +1,108 @@
+# 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 pathlib import Path
+
+from llama_stack.core.datatypes import BuildProvider, Provider, ToolGroupInput
+from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings
+from llama_stack.providers.inline.files.localfs.config import LocalfsFilesImplConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
+from llama_stack.providers.remote.inference.oci.config import OCIConfig
+
+
+def get_distribution_template(name: str = "oci") -> DistributionTemplate:
+    providers = {
+        "inference": [BuildProvider(provider_type="remote::oci")],
+        "vector_io": [
+            BuildProvider(provider_type="inline::faiss"),
+            BuildProvider(provider_type="remote::chromadb"),
+            BuildProvider(provider_type="remote::pgvector"),
+        ],
+        "safety": [BuildProvider(provider_type="inline::llama-guard")],
+        "agents": [BuildProvider(provider_type="inline::meta-reference")],
+        "eval": [BuildProvider(provider_type="inline::meta-reference")],
+        "datasetio": [
+            BuildProvider(provider_type="remote::huggingface"),
+            BuildProvider(provider_type="inline::localfs"),
+        ],
+        "scoring": [
+            BuildProvider(provider_type="inline::basic"),
+            BuildProvider(provider_type="inline::llm-as-judge"),
+            BuildProvider(provider_type="inline::braintrust"),
+        ],
+        "tool_runtime": [
+            BuildProvider(provider_type="remote::brave-search"),
+            BuildProvider(provider_type="remote::tavily-search"),
+            BuildProvider(provider_type="inline::rag-runtime"),
+            BuildProvider(provider_type="remote::model-context-protocol"),
+        ],
+        "files": [BuildProvider(provider_type="inline::localfs")],
+    }
+
+    inference_provider = Provider(
+        provider_id="oci",
+        provider_type="remote::oci",
+        config=OCIConfig.sample_run_config(),
+    )
+
+    vector_io_provider = Provider(
+        provider_id="faiss",
+        provider_type="inline::faiss",
+        config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
+    )
+
+    files_provider = Provider(
+        provider_id="meta-reference-files",
+        provider_type="inline::localfs",
+        config=LocalfsFilesImplConfig.sample_run_config(f"~/.llama/distributions/{name}"),
+    )
+    default_tool_groups = [
+        ToolGroupInput(
+            toolgroup_id="builtin::websearch",
+            provider_id="tavily-search",
+        ),
+    ]
+
+    return DistributionTemplate(
+        name=name,
+        distro_type="remote_hosted",
+        description="Use Oracle Cloud Infrastructure (OCI) Generative AI for running LLM inference with scalable cloud services",
+        container_image=None,
+        template_path=Path(__file__).parent / "doc_template.md",
+        providers=providers,
+        run_configs={
+            "run.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": [inference_provider],
+                    "vector_io": [vector_io_provider],
+                    "files": [files_provider],
+                },
+                default_tool_groups=default_tool_groups,
+            ),
+        },
+        run_config_env_vars={
+            "OCI_AUTH_TYPE": (
+                "instance_principal",
+                "OCI authentication type (instance_principal or config_file)",
+            ),
+            "OCI_REGION": (
+                "",
+                "OCI region (e.g., us-ashburn-1, us-chicago-1, us-phoenix-1, eu-frankfurt-1)",
+            ),
+            "OCI_COMPARTMENT_OCID": (
+                "",
+                "OCI compartment ID for the Generative AI service",
+            ),
+            "OCI_CONFIG_FILE_PATH": (
+                "~/.oci/config",
+                "OCI config file path (required if OCI_AUTH_TYPE is config_file)",
+            ),
+            "OCI_CLI_PROFILE": (
+                "DEFAULT",
+                "OCI CLI profile name to use from config file",
+            ),
+        },
+    )

src/llama_stack/distributions/oci/run.yaml

@@ -0,0 +1,136 @@
+version: 2
+image_name: oci
+apis:
+- agents
+- datasetio
+- eval
+- files
+- inference
+- safety
+- scoring
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: oci
+    provider_type: remote::oci
+    config:
+      oci_auth_type: ${env.OCI_AUTH_TYPE:=instance_principal}
+      oci_config_file_path: ${env.OCI_CONFIG_FILE_PATH:=~/.oci/config}
+      oci_config_profile: ${env.OCI_CLI_PROFILE:=DEFAULT}
+      oci_region: ${env.OCI_REGION:=us-ashburn-1}
+      oci_compartment_id: ${env.OCI_COMPARTMENT_OCID:=}
+  vector_io:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      persistence:
+        namespace: vector_io::faiss
+        backend: kv_default
+  safety:
+  - provider_id: llama-guard
+    provider_type: inline::llama-guard
+    config:
+      excluded_categories: []
+  agents:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      persistence:
+        agent_state:
+          namespace: agents
+          backend: kv_default
+        responses:
+          table_name: responses
+          backend: sql_default
+          max_write_queue_size: 10000
+          num_writers: 4
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        namespace: eval
+        backend: kv_default
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config:
+      kvstore:
+        namespace: datasetio::huggingface
+        backend: kv_default
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config:
+      kvstore:
+        namespace: datasetio::localfs
+        backend: kv_default
+  scoring:
+  - provider_id: basic
+    provider_type: inline::basic
+  - provider_id: llm-as-judge
+    provider_type: inline::llm-as-judge
+  - provider_id: braintrust
+    provider_type: inline::braintrust
+    config:
+      openai_api_key: ${env.OPENAI_API_KEY:=}
+  tool_runtime:
+  - provider_id: brave-search
+    provider_type: remote::brave-search
+    config:
+      api_key: ${env.BRAVE_SEARCH_API_KEY:=}
+      max_results: 3
+  - provider_id: tavily-search
+    provider_type: remote::tavily-search
+    config:
+      api_key: ${env.TAVILY_SEARCH_API_KEY:=}
+      max_results: 3
+  - provider_id: rag-runtime
+    provider_type: inline::rag-runtime
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+  files:
+  - provider_id: meta-reference-files
+    provider_type: inline::localfs
+    config:
+      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/oci/files}
+      metadata_store:
+        table_name: files_metadata
+        backend: sql_default
+storage:
+  backends:
+    kv_default:
+      type: kv_sqlite
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/oci}/kvstore.db
+    sql_default:
+      type: sql_sqlite
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/oci}/sql_store.db
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
+    prompts:
+      namespace: prompts
+      backend: kv_default
+registered_resources:
+  models: []
+  shields: []
+  vector_dbs: []
+  datasets: []
+  scoring_fns: []
+  benchmarks: []
+  tool_groups:
+  - toolgroup_id: builtin::websearch
+    provider_id: tavily-search
+server:
+  port: 8321
+telemetry:
+  enabled: true

src/llama_stack/distributions/open-benchmark/open_benchmark.py

@@ -5,8 +5,6 @@
 # the root directory of this source tree.
 
 
-from llama_stack.apis.datasets import DatasetPurpose, URIDataSource
-from llama_stack.apis.models import ModelType
 from llama_stack.core.datatypes import (
     BenchmarkInput,
     BuildProvider,
@@ -34,6 +32,7 @@ from llama_stack.providers.remote.vector_io.pgvector.config import (
     PGVectorVectorIOConfig,
 )
 from llama_stack.providers.utils.inference.model_registry import ProviderModelEntry
+from llama_stack_api import DatasetPurpose, ModelType, URIDataSource
 
 
 def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderModelEntry]]]:

src/llama_stack/distributions/starter-gpu/run-with-postgres-store.yaml

@@ -173,20 +173,15 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
-      persistence_store:
-        type: sql_postgres
-        host: ${env.POSTGRES_HOST:=localhost}
-        port: ${env.POSTGRES_PORT:=5432}
-        db: ${env.POSTGRES_DB:=llamastack}
-        user: ${env.POSTGRES_USER:=llamastack}
-        password: ${env.POSTGRES_PASSWORD:=llamastack}
-      responses_store:
-        type: sql_postgres
-        host: ${env.POSTGRES_HOST:=localhost}
-        port: ${env.POSTGRES_PORT:=5432}
-        db: ${env.POSTGRES_DB:=llamastack}
-        user: ${env.POSTGRES_USER:=llamastack}
-        password: ${env.POSTGRES_PASSWORD:=llamastack}
+      persistence:
+        agent_state:
+          namespace: agents
+          backend: kv_default
+        responses:
+          table_name: responses
+          backend: sql_default
+          max_write_queue_size: 10000
+          num_writers: 4
   post_training:
   - provider_id: huggingface-gpu
     provider_type: inline::huggingface-gpu
@@ -245,10 +240,10 @@ providers:
     config:
       kvstore:
         namespace: batches
-        backend: kv_postgres
+        backend: kv_default
 storage:
   backends:
-    kv_postgres:
+    kv_default:
       type: kv_postgres
       host: ${env.POSTGRES_HOST:=localhost}
       port: ${env.POSTGRES_PORT:=5432}
@@ -256,7 +251,7 @@ storage:
       user: ${env.POSTGRES_USER:=llamastack}
       password: ${env.POSTGRES_PASSWORD:=llamastack}
       table_name: ${env.POSTGRES_TABLE_NAME:=llamastack_kvstore}
-    sql_postgres:
+    sql_default:
       type: sql_postgres
       host: ${env.POSTGRES_HOST:=localhost}
       port: ${env.POSTGRES_PORT:=5432}
@@ -266,27 +261,44 @@ storage:
   stores:
     metadata:
       namespace: registry
-      backend: kv_postgres
+      backend: kv_default
     inference:
       table_name: inference_store
-      backend: sql_postgres
+      backend: sql_default
       max_write_queue_size: 10000
       num_writers: 4
     conversations:
       table_name: openai_conversations
-      backend: sql_postgres
+      backend: sql_default
     prompts:
       namespace: prompts
-      backend: kv_postgres
+      backend: kv_default
 registered_resources:
   models: []
-  shields: []
+  shields:
+  - shield_id: llama-guard
+    provider_id: ${env.SAFETY_MODEL:+llama-guard}
+    provider_shield_id: ${env.SAFETY_MODEL:=}
+  - shield_id: code-scanner
+    provider_id: ${env.CODE_SCANNER_MODEL:+code-scanner}
+    provider_shield_id: ${env.CODE_SCANNER_MODEL:=}
   vector_dbs: []
   datasets: []
   scoring_fns: []
   benchmarks: []
-  tool_groups: []
+  tool_groups:
+  - toolgroup_id: builtin::websearch
+    provider_id: tavily-search
+  - toolgroup_id: builtin::rag
+    provider_id: rag-runtime
 server:
   port: 8321
 telemetry:
   enabled: true
+vector_stores:
+  default_provider_id: faiss
+  default_embedding_model:
+    provider_id: sentence-transformers
+    model_id: nomic-ai/nomic-embed-text-v1.5
+safety:
+  default_shield_id: llama-guard

src/llama_stack/distributions/starter/run-with-postgres-store.yaml

@@ -173,20 +173,15 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
-      persistence_store:
-        type: sql_postgres
-        host: ${env.POSTGRES_HOST:=localhost}
-        port: ${env.POSTGRES_PORT:=5432}
-        db: ${env.POSTGRES_DB:=llamastack}
-        user: ${env.POSTGRES_USER:=llamastack}
-        password: ${env.POSTGRES_PASSWORD:=llamastack}
-      responses_store:
-        type: sql_postgres
-        host: ${env.POSTGRES_HOST:=localhost}
-        port: ${env.POSTGRES_PORT:=5432}
-        db: ${env.POSTGRES_DB:=llamastack}
-        user: ${env.POSTGRES_USER:=llamastack}
-        password: ${env.POSTGRES_PASSWORD:=llamastack}
+      persistence:
+        agent_state:
+          namespace: agents
+          backend: kv_default
+        responses:
+          table_name: responses
+          backend: sql_default
+          max_write_queue_size: 10000
+          num_writers: 4
   post_training:
   - provider_id: torchtune-cpu
     provider_type: inline::torchtune-cpu
@@ -242,10 +237,10 @@ providers:
     config:
       kvstore:
         namespace: batches
-        backend: kv_postgres
+        backend: kv_default
 storage:
   backends:
-    kv_postgres:
+    kv_default:
       type: kv_postgres
       host: ${env.POSTGRES_HOST:=localhost}
       port: ${env.POSTGRES_PORT:=5432}
@@ -253,7 +248,7 @@ storage:
       user: ${env.POSTGRES_USER:=llamastack}
       password: ${env.POSTGRES_PASSWORD:=llamastack}
       table_name: ${env.POSTGRES_TABLE_NAME:=llamastack_kvstore}
-    sql_postgres:
+    sql_default:
       type: sql_postgres
       host: ${env.POSTGRES_HOST:=localhost}
       port: ${env.POSTGRES_PORT:=5432}
@@ -263,27 +258,44 @@ storage:
   stores:
     metadata:
       namespace: registry
-      backend: kv_postgres
+      backend: kv_default
     inference:
       table_name: inference_store
-      backend: sql_postgres
+      backend: sql_default
       max_write_queue_size: 10000
       num_writers: 4
     conversations:
       table_name: openai_conversations
-      backend: sql_postgres
+      backend: sql_default
     prompts:
       namespace: prompts
-      backend: kv_postgres
+      backend: kv_default
 registered_resources:
   models: []
-  shields: []
+  shields:
+  - shield_id: llama-guard
+    provider_id: ${env.SAFETY_MODEL:+llama-guard}
+    provider_shield_id: ${env.SAFETY_MODEL:=}
+  - shield_id: code-scanner
+    provider_id: ${env.CODE_SCANNER_MODEL:+code-scanner}
+    provider_shield_id: ${env.CODE_SCANNER_MODEL:=}
   vector_dbs: []
   datasets: []
   scoring_fns: []
   benchmarks: []
-  tool_groups: []
+  tool_groups:
+  - toolgroup_id: builtin::websearch
+    provider_id: tavily-search
+  - toolgroup_id: builtin::rag
+    provider_id: rag-runtime
 server:
   port: 8321
 telemetry:
   enabled: true
+vector_stores:
+  default_provider_id: faiss
+  default_embedding_model:
+    provider_id: sentence-transformers
+    model_id: nomic-ai/nomic-embed-text-v1.5
+safety:
+  default_shield_id: llama-guard

src/llama_stack/distributions/starter/starter.py

@@ -17,14 +17,10 @@ from llama_stack.core.datatypes import (
     ToolGroupInput,
     VectorStoresConfig,
 )
-from llama_stack.core.storage.datatypes import (
-    InferenceStoreReference,
-    KVStoreReference,
-    SqlStoreReference,
-)
+from llama_stack.core.storage.kvstore.config import PostgresKVStoreConfig
+from llama_stack.core.storage.sqlstore.sqlstore import PostgresSqlStoreConfig
 from llama_stack.core.utils.dynamic import instantiate_class_type
 from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings
-from llama_stack.providers.datatypes import RemoteProviderSpec
 from llama_stack.providers.inline.files.localfs.config import LocalfsFilesImplConfig
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
@@ -36,14 +32,13 @@ from llama_stack.providers.inline.vector_io.sqlite_vec.config import (
 )
 from llama_stack.providers.registry.inference import available_providers
 from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig
+from llama_stack.providers.remote.vector_io.elasticsearch.config import ElasticsearchVectorIOConfig
 from llama_stack.providers.remote.vector_io.pgvector.config import (
     PGVectorVectorIOConfig,
 )
 from llama_stack.providers.remote.vector_io.qdrant.config import QdrantVectorIOConfig
 from llama_stack.providers.remote.vector_io.weaviate.config import WeaviateVectorIOConfig
-from llama_stack.providers.remote.vector_io.elasticsearch.config import ElasticsearchVectorIOConfig
-from llama_stack.providers.utils.kvstore.config import PostgresKVStoreConfig
-from llama_stack.providers.utils.sqlstore.sqlstore import PostgresSqlStoreConfig
+from llama_stack_api import RemoteProviderSpec
 
 
 def _get_config_for_provider(provider_spec: ProviderSpec) -> dict[str, Any]:
@@ -156,10 +151,11 @@ def get_distribution_template(name: str = "starter") -> DistributionTemplate:
             BuildProvider(provider_type="inline::reference"),
         ],
     }
+    files_config = LocalfsFilesImplConfig.sample_run_config(f"~/.llama/distributions/{name}")
     files_provider = Provider(
         provider_id="meta-reference-files",
         provider_type="inline::localfs",
-        config=LocalfsFilesImplConfig.sample_run_config(f"~/.llama/distributions/{name}"),
+        config=files_config,
     )
     embedding_provider = Provider(
         provider_id="sentence-transformers",
@@ -189,7 +185,8 @@ def get_distribution_template(name: str = "starter") -> DistributionTemplate:
             provider_shield_id="${env.CODE_SCANNER_MODEL:=}",
         ),
     ]
-    postgres_config = PostgresSqlStoreConfig.sample_run_config()
+    postgres_sql_config = PostgresSqlStoreConfig.sample_run_config()
+    postgres_kv_config = PostgresKVStoreConfig.sample_run_config()
     default_overrides = {
         "inference": remote_inference_providers + [embedding_provider],
         "vector_io": [
@@ -255,6 +252,33 @@ def get_distribution_template(name: str = "starter") -> DistributionTemplate:
         "files": [files_provider],
     }
 
+    base_run_settings = RunConfigSettings(
+        provider_overrides=default_overrides,
+        default_models=[],
+        default_tool_groups=default_tool_groups,
+        default_shields=default_shields,
+        vector_stores_config=VectorStoresConfig(
+            default_provider_id="faiss",
+            default_embedding_model=QualifiedModel(
+                provider_id="sentence-transformers",
+                model_id="nomic-ai/nomic-embed-text-v1.5",
+            ),
+        ),
+        safety_config=SafetyConfig(
+            default_shield_id="llama-guard",
+        ),
+    )
+
+    postgres_run_settings = base_run_settings.model_copy(
+        update={
+            "storage_backends": {
+                "kv_default": postgres_kv_config,
+                "sql_default": postgres_sql_config,
+            }
+        },
+        deep=True,
+    )
+
     return DistributionTemplate(
         name=name,
         distro_type="self_hosted",
@@ -264,71 +288,8 @@ def get_distribution_template(name: str = "starter") -> DistributionTemplate:
         providers=providers,
         additional_pip_packages=list(set(PostgresSqlStoreConfig.pip_packages() + PostgresKVStoreConfig.pip_packages())),
         run_configs={
-            "run.yaml": RunConfigSettings(
-                provider_overrides=default_overrides,
-                default_models=[],
-                default_tool_groups=default_tool_groups,
-                default_shields=default_shields,
-                vector_stores_config=VectorStoresConfig(
-                    default_provider_id="faiss",
-                    default_embedding_model=QualifiedModel(
-                        provider_id="sentence-transformers",
-                        model_id="nomic-ai/nomic-embed-text-v1.5",
-                    ),
-                ),
-                safety_config=SafetyConfig(
-                    default_shield_id="llama-guard",
-                ),
-            ),
-            "run-with-postgres-store.yaml": RunConfigSettings(
-                provider_overrides={
-                    **default_overrides,
-                    "agents": [
-                        Provider(
-                            provider_id="meta-reference",
-                            provider_type="inline::meta-reference",
-                            config=dict(
-                                persistence_store=postgres_config,
-                                responses_store=postgres_config,
-                            ),
-                        )
-                    ],
-                    "batches": [
-                        Provider(
-                            provider_id="reference",
-                            provider_type="inline::reference",
-                            config=dict(
-                                kvstore=KVStoreReference(
-                                    backend="kv_postgres",
-                                    namespace="batches",
-                                ).model_dump(exclude_none=True),
-                            ),
-                        )
-                    ],
-                },
-                storage_backends={
-                    "kv_postgres": PostgresKVStoreConfig.sample_run_config(),
-                    "sql_postgres": postgres_config,
-                },
-                storage_stores={
-                    "metadata": KVStoreReference(
-                        backend="kv_postgres",
-                        namespace="registry",
-                    ).model_dump(exclude_none=True),
-                    "inference": InferenceStoreReference(
-                        backend="sql_postgres",
-                        table_name="inference_store",
-                    ).model_dump(exclude_none=True),
-                    "conversations": SqlStoreReference(
-                        backend="sql_postgres",
-                        table_name="openai_conversations",
-                    ).model_dump(exclude_none=True),
-                    "prompts": KVStoreReference(
-                        backend="kv_postgres",
-                        namespace="prompts",
-                    ).model_dump(exclude_none=True),
-                },
-            ),
+            "run.yaml": base_run_settings,
+            "run-with-postgres-store.yaml": postgres_run_settings,
         },
         run_config_env_vars={
             "LLAMA_STACK_PORT": (

src/llama_stack/distributions/template.py

@@ -12,8 +12,6 @@ import rich
 import yaml
 from pydantic import BaseModel, Field
 
-from llama_stack.apis.datasets import DatasetPurpose
-from llama_stack.apis.models import ModelType
 from llama_stack.core.datatypes import (
     LLAMA_STACK_RUN_CONFIG_VERSION,
     Api,
@@ -37,13 +35,14 @@ from llama_stack.core.storage.datatypes import (
     SqlStoreReference,
     StorageBackendType,
 )
+from llama_stack.core.storage.kvstore.config import SqliteKVStoreConfig
+from llama_stack.core.storage.kvstore.config import get_pip_packages as get_kv_pip_packages
+from llama_stack.core.storage.sqlstore.sqlstore import SqliteSqlStoreConfig
+from llama_stack.core.storage.sqlstore.sqlstore import get_pip_packages as get_sql_pip_packages
 from llama_stack.core.utils.dynamic import instantiate_class_type
 from llama_stack.core.utils.image_types import LlamaStackImageType
 from llama_stack.providers.utils.inference.model_registry import ProviderModelEntry
-from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
-from llama_stack.providers.utils.kvstore.config import get_pip_packages as get_kv_pip_packages
-from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
-from llama_stack.providers.utils.sqlstore.sqlstore import get_pip_packages as get_sql_pip_packages
+from llama_stack_api import DatasetPurpose, ModelType
 
 
 def filter_empty_values(obj: Any) -> Any: