Refactor persistence config to use stores key with unified backends

- Add StoresConfig to group all store references under persistence.stores
- Use single 'default' backend instead of separate metadata_backend/inference_backend
- Update resolver to access persistence.stores.{metadata,inference,conversations}
- All SQLite distributions now use single store.db file with shared backend

llama_stack/distributions/ci-tests/run.yaml

@@ -14,7 +14,7 @@ apis:
 - tool_runtime
 - vector_io
 providers:
-  inference:
+    inference:
   - provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
     provider_type: remote::cerebras
     config:
@@ -220,16 +220,14 @@ providers:
         db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/batches.db
 persistence:
   backends:
-    metadata_backend:
+    default:
       type: sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/registry.db
-    inference_backend:
-      type: sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/inference_store.db
-  metadata:
-    backend: metadata_backend
-  inference:
-    backend: inference_backend
+  stores:
+    metadata:
+      backend: default
+    inference:
+      backend: default
 models: []
 shields:
 - shield_id: llama-guard

llama_stack/distributions/dell/run.yaml

@@ -11,7 +11,7 @@ apis:
 - tool_runtime
 - vector_io
 providers:
-  inference:
+    inference:
   - provider_id: tgi0
     provider_type: remote::tgi
     config:
@@ -93,16 +93,14 @@ providers:
     provider_type: inline::rag-runtime
 persistence:
   backends:
-    metadata_backend:
+    default:
       type: sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/registry.db
-    inference_backend:
-      type: sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/inference_store.db
-  metadata:
-    backend: metadata_backend
-  inference:
-    backend: inference_backend
+  stores:
+    metadata:
+      backend: default
+    inference:
+      backend: default
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}

llama_stack/distributions/dell/run.yaml.bak

@@ -0,0 +1,121 @@
+version: 2
+image_name: dell
+apis:
+- agents
+- datasetio
+- eval
+- inference
+- safety
+- scoring
+- telemetry
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: tgi0
+    provider_type: remote::tgi
+    config:
+      url: ${env.DEH_URL}
+  - provider_id: sentence-transformers
+    provider_type: inline::sentence-transformers
+  vector_io:
+  - provider_id: chromadb
+    provider_type: remote::chromadb
+    config:
+      url: ${env.CHROMADB_URL:=}
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell/}/chroma_remote_registry.db
+  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_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/agents_store.db
+      responses_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/responses_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
+      sinks: ${env.TELEMETRY_SINKS:=sqlite}
+      sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/trace_store.db
+      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/meta_reference_eval.db
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/huggingface_datasetio.db
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/localfs_datasetio.db
+  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
+metadata_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/registry.db
+inference_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/inference_store.db
+models:
+- metadata: {}
+  model_id: ${env.INFERENCE_MODEL}
+  provider_id: tgi0
+  model_type: llm
+- metadata:
+    embedding_dimension: 384
+  model_id: all-MiniLM-L6-v2
+  provider_id: sentence-transformers
+  model_type: embedding
+shields: []
+vector_dbs: []
+datasets: []
+scoring_fns: []
+benchmarks: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: brave-search
+- toolgroup_id: builtin::rag
+  provider_id: rag-runtime
+server:
+  port: 8321

llama_stack/distributions/meta-reference-gpu/run.yaml

@@ -11,7 +11,7 @@ apis:
 - tool_runtime
 - vector_io
 providers:
-  inference:
+    inference:
   - provider_id: meta-reference-inference
     provider_type: inline::meta-reference
     config:
@@ -100,16 +100,14 @@ providers:
     provider_type: remote::model-context-protocol
 persistence:
   backends:
-    metadata_backend:
+    default:
       type: sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/registry.db
-    inference_backend:
-      type: sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/inference_store.db
-  metadata:
-    backend: metadata_backend
-  inference:
-    backend: inference_backend
+  stores:
+    metadata:
+      backend: default
+    inference:
+      backend: default
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}

llama_stack/distributions/meta-reference-gpu/run.yaml.bak

@@ -0,0 +1,128 @@
+version: 2
+image_name: meta-reference-gpu
+apis:
+- agents
+- datasetio
+- eval
+- inference
+- safety
+- scoring
+- telemetry
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: meta-reference-inference
+    provider_type: inline::meta-reference
+    config:
+      model: ${env.INFERENCE_MODEL}
+      checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:=null}
+      quantization:
+        type: ${env.QUANTIZATION_TYPE:=bf16}
+      model_parallel_size: ${env.MODEL_PARALLEL_SIZE:=0}
+      max_batch_size: ${env.MAX_BATCH_SIZE:=1}
+      max_seq_len: ${env.MAX_SEQ_LEN:=4096}
+  - provider_id: sentence-transformers
+    provider_type: inline::sentence-transformers
+  vector_io:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/faiss_store.db
+  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_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/agents_store.db
+      responses_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/responses_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
+      sinks: ${env.TELEMETRY_SINKS:=sqlite}
+      sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/trace_store.db
+      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/meta_reference_eval.db
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/huggingface_datasetio.db
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/localfs_datasetio.db
+  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
+metadata_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/registry.db
+inference_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/inference_store.db
+models:
+- metadata: {}
+  model_id: ${env.INFERENCE_MODEL}
+  provider_id: meta-reference-inference
+  model_type: llm
+- metadata:
+    embedding_dimension: 384
+  model_id: all-MiniLM-L6-v2
+  provider_id: sentence-transformers
+  model_type: embedding
+shields: []
+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

llama_stack/distributions/nvidia/run.yaml

@@ -13,7 +13,7 @@ apis:
 - tool_runtime
 - vector_io
 providers:
-  inference:
+    inference:
   - provider_id: nvidia
     provider_type: remote::nvidia
     config:
@@ -88,16 +88,14 @@ providers:
         db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/files_metadata.db
 persistence:
   backends:
-    metadata_backend:
+    default:
       type: sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/registry.db
-    inference_backend:
-      type: sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/inference_store.db
-  metadata:
-    backend: metadata_backend
-  inference:
-    backend: inference_backend
+  stores:
+    metadata:
+      backend: default
+    inference:
+      backend: default
 models: []
 shields: []
 vector_dbs: []

llama_stack/distributions/nvidia/run.yaml.bak

@@ -0,0 +1,105 @@
+version: 2
+image_name: nvidia
+apis:
+- agents
+- datasetio
+- eval
+- files
+- inference
+- post_training
+- safety
+- scoring
+- telemetry
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: 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}
+  vector_io:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/faiss_store.db
+  safety:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:=http://localhost:7331}
+      config_id: ${env.NVIDIA_GUARDRAILS_CONFIG_ID:=self-check}
+  agents:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      persistence_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/agents_store.db
+      responses_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/responses_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
+      sinks: ${env.TELEMETRY_SINKS:=sqlite}
+      sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/trace_store.db
+      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
+  eval:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      evaluator_url: ${env.NVIDIA_EVALUATOR_URL:=http://localhost:7331}
+  post_training:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      api_key: ${env.NVIDIA_API_KEY:=}
+      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
+      project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
+      customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:=http://nemo.test}
+  datasetio:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      api_key: ${env.NVIDIA_API_KEY:=}
+      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:=default}
+      project_id: ${env.NVIDIA_PROJECT_ID:=test-project}
+      datasets_url: ${env.NVIDIA_DATASETS_URL:=http://nemo.test}
+  scoring:
+  - provider_id: basic
+    provider_type: inline::basic
+  tool_runtime:
+  - provider_id: rag-runtime
+    provider_type: inline::rag-runtime
+  files:
+  - provider_id: meta-reference-files
+    provider_type: inline::localfs
+    config:
+      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/nvidia/files}
+      metadata_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/files_metadata.db
+metadata_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/registry.db
+inference_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/inference_store.db
+models: []
+shields: []
+vector_dbs: []
+datasets: []
+scoring_fns: []
+benchmarks: []
+tool_groups:
+- toolgroup_id: builtin::rag
+  provider_id: rag-runtime
+server:
+  port: 8321

llama_stack/distributions/open-benchmark/run.yaml

@@ -11,7 +11,7 @@ apis:
 - tool_runtime
 - vector_io
 providers:
-  inference:
+    inference:
   - provider_id: openai
     provider_type: remote::openai
     config:
@@ -130,16 +130,14 @@ providers:
     provider_type: remote::model-context-protocol
 persistence:
   backends:
-    metadata_backend:
+    default:
       type: sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/registry.db
-    inference_backend:
-      type: sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/inference_store.db
-  metadata:
-    backend: metadata_backend
-  inference:
-    backend: inference_backend
+  stores:
+    metadata:
+      backend: default
+    inference:
+      backend: default
 models:
 - metadata: {}
   model_id: gpt-4o

llama_stack/distributions/open-benchmark/run.yaml.bak

@@ -0,0 +1,241 @@
+version: 2
+image_name: open-benchmark
+apis:
+- agents
+- datasetio
+- eval
+- inference
+- safety
+- scoring
+- telemetry
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - 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: groq
+    provider_type: remote::groq
+    config:
+      url: https://api.groq.com
+      api_key: ${env.GROQ_API_KEY:=}
+  - provider_id: together
+    provider_type: remote::together
+    config:
+      url: https://api.together.xyz/v1
+      api_key: ${env.TOGETHER_API_KEY:=}
+  vector_io:
+  - provider_id: sqlite-vec
+    provider_type: inline::sqlite-vec
+    config:
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/sqlite_vec.db
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/sqlite_vec_registry.db
+  - provider_id: ${env.ENABLE_CHROMADB:+chromadb}
+    provider_type: remote::chromadb
+    config:
+      url: ${env.CHROMADB_URL:=}
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/chroma_remote_registry.db
+  - provider_id: ${env.ENABLE_PGVECTOR:+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:=}
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/pgvector_registry.db
+  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_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/agents_store.db
+      responses_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/responses_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
+      sinks: ${env.TELEMETRY_SINKS:=sqlite}
+      sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/trace_store.db
+      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/meta_reference_eval.db
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/huggingface_datasetio.db
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/localfs_datasetio.db
+  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
+metadata_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/registry.db
+inference_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/inference_store.db
+models:
+- metadata: {}
+  model_id: gpt-4o
+  provider_id: openai
+  provider_model_id: gpt-4o
+  model_type: llm
+- metadata: {}
+  model_id: claude-3-5-sonnet-latest
+  provider_id: anthropic
+  provider_model_id: claude-3-5-sonnet-latest
+  model_type: llm
+- metadata: {}
+  model_id: gemini/gemini-1.5-flash
+  provider_id: gemini
+  provider_model_id: gemini/gemini-1.5-flash
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama-3.3-70b-versatile
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-405B-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
+  model_type: llm
+shields:
+- shield_id: meta-llama/Llama-Guard-3-8B
+vector_dbs: []
+datasets:
+- purpose: eval/messages-answer
+  source:
+    type: uri
+    uri: huggingface://datasets/llamastack/simpleqa?split=train
+  metadata: {}
+  dataset_id: simpleqa
+- purpose: eval/messages-answer
+  source:
+    type: uri
+    uri: huggingface://datasets/llamastack/mmlu_cot?split=test&name=all
+  metadata: {}
+  dataset_id: mmlu_cot
+- purpose: eval/messages-answer
+  source:
+    type: uri
+    uri: huggingface://datasets/llamastack/gpqa_0shot_cot?split=test&name=gpqa_main
+  metadata: {}
+  dataset_id: gpqa_cot
+- purpose: eval/messages-answer
+  source:
+    type: uri
+    uri: huggingface://datasets/llamastack/math_500?split=test
+  metadata: {}
+  dataset_id: math_500
+- purpose: eval/messages-answer
+  source:
+    type: uri
+    uri: huggingface://datasets/llamastack/IfEval?split=train
+  metadata: {}
+  dataset_id: ifeval
+- purpose: eval/messages-answer
+  source:
+    type: uri
+    uri: huggingface://datasets/llamastack/docvqa?split=val
+  metadata: {}
+  dataset_id: docvqa
+scoring_fns: []
+benchmarks:
+- dataset_id: simpleqa
+  scoring_functions:
+  - llm-as-judge::405b-simpleqa
+  metadata: {}
+  benchmark_id: meta-reference-simpleqa
+- dataset_id: mmlu_cot
+  scoring_functions:
+  - basic::regex_parser_multiple_choice_answer
+  metadata: {}
+  benchmark_id: meta-reference-mmlu-cot
+- dataset_id: gpqa_cot
+  scoring_functions:
+  - basic::regex_parser_multiple_choice_answer
+  metadata: {}
+  benchmark_id: meta-reference-gpqa-cot
+- dataset_id: math_500
+  scoring_functions:
+  - basic::regex_parser_math_response
+  metadata: {}
+  benchmark_id: meta-reference-math-500
+- dataset_id: ifeval
+  scoring_functions:
+  - basic::ifeval
+  metadata: {}
+  benchmark_id: meta-reference-ifeval
+- dataset_id: docvqa
+  scoring_functions:
+  - basic::docvqa
+  metadata: {}
+  benchmark_id: meta-reference-docvqa
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::rag
+  provider_id: rag-runtime
+server:
+  port: 8321

llama_stack/distributions/postgres-demo/run.yaml

@@ -80,11 +80,11 @@ persistence:
       db: ${env.POSTGRES_DB:=llamastack}
       user: ${env.POSTGRES_USER:=llamastack}
       password: ${env.POSTGRES_PASSWORD:=llamastack}
-      table_name: ${env.POSTGRES_TABLE_NAME:=llamastack_kvstore}
-  metadata:
-    backend: default
-  inference:
-    backend: default
+  stores:
+    metadata:
+      backend: default
+    inference:
+      backend: default
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}

llama_stack/distributions/starter-gpu/run.yaml

@@ -14,7 +14,7 @@ apis:
 - tool_runtime
 - vector_io
 providers:
-  inference:
+    inference:
   - provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
     provider_type: remote::cerebras
     config:
@@ -223,16 +223,14 @@ providers:
         db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/batches.db
 persistence:
   backends:
-    metadata_backend:
+    default:
       type: sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/registry.db
-    inference_backend:
-      type: sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/inference_store.db
-  metadata:
-    backend: metadata_backend
-  inference:
-    backend: inference_backend
+  stores:
+    metadata:
+      backend: default
+    inference:
+      backend: default
 models: []
 shields:
 - shield_id: llama-guard

llama_stack/distributions/starter-gpu/run.yaml.bak

@@ -0,0 +1,248 @@
+version: 2
+image_name: starter-gpu
+apis:
+- agents
+- batches
+- datasetio
+- eval
+- files
+- inference
+- post_training
+- safety
+- scoring
+- telemetry
+- 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
+  - 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:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/faiss_store.db
+  - provider_id: sqlite-vec
+    provider_type: inline::sqlite-vec
+    config:
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/sqlite_vec.db
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/sqlite_vec_registry.db
+  - provider_id: ${env.MILVUS_URL:+milvus}
+    provider_type: inline::milvus
+    config:
+      db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/starter-gpu}/milvus.db
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/milvus_registry.db
+  - provider_id: ${env.CHROMADB_URL:+chromadb}
+    provider_type: remote::chromadb
+    config:
+      url: ${env.CHROMADB_URL:=}
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu/}/chroma_remote_registry.db
+  - 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:=}
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/pgvector_registry.db
+  files:
+  - provider_id: meta-reference-files
+    provider_type: inline::localfs
+    config:
+      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter-gpu/files}
+      metadata_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/files_metadata.db
+  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_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/agents_store.db
+      responses_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/responses_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
+      sinks: ${env.TELEMETRY_SINKS:=sqlite}
+      sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/trace_store.db
+      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
+  post_training:
+  - provider_id: huggingface-gpu
+    provider_type: inline::huggingface-gpu
+    config:
+      checkpoint_format: huggingface
+      distributed_backend: null
+      device: cpu
+      dpo_output_dir: ~/.llama/distributions/starter-gpu/dpo_output
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/meta_reference_eval.db
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/huggingface_datasetio.db
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/localfs_datasetio.db
+  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:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/batches.db
+metadata_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/registry.db
+inference_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/inference_store.db
+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

llama_stack/distributions/starter/run.yaml

@@ -220,16 +220,14 @@ providers:
         db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/batches.db
 persistence:
   backends:
-    metadata_backend:
+    default:
       type: sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/registry.db
-    inference_backend:
-      type: sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/inference_store.db
-  metadata:
-    backend: metadata_backend
-  inference:
-    backend: inference_backend
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/store.db
+  stores:
+    metadata:
+      backend: default
+    inference:
+      backend: default
 models: []
 shields:
 - shield_id: llama-guard

llama_stack/distributions/watsonx/run.yaml

@@ -12,7 +12,7 @@ apis:
 - vector_io
 - files
 providers:
-  inference:
+    inference:
   - provider_id: watsonx
     provider_type: remote::watsonx
     config:
@@ -105,16 +105,14 @@ providers:
         db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/files_metadata.db
 persistence:
   backends:
-    metadata_backend:
+    default:
       type: sqlite
       db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/registry.db
-    inference_backend:
-      type: sqlite
-      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/inference_store.db
-  metadata:
-    backend: metadata_backend
-  inference:
-    backend: inference_backend
+  stores:
+    metadata:
+      backend: default
+    inference:
+      backend: default
 models:
 - metadata: {}
   model_id: meta-llama/llama-3-3-70b-instruct

llama_stack/distributions/watsonx/run.yaml.bak

@@ -0,0 +1,219 @@
+version: 2
+image_name: watsonx
+apis:
+- agents
+- datasetio
+- eval
+- inference
+- safety
+- scoring
+- telemetry
+- tool_runtime
+- vector_io
+- files
+providers:
+  inference:
+  - provider_id: watsonx
+    provider_type: remote::watsonx
+    config:
+      url: ${env.WATSONX_BASE_URL:=https://us-south.ml.cloud.ibm.com}
+      api_key: ${env.WATSONX_API_KEY:=}
+      project_id: ${env.WATSONX_PROJECT_ID:=}
+  - provider_id: sentence-transformers
+    provider_type: inline::sentence-transformers
+  vector_io:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/faiss_store.db
+  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_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/agents_store.db
+      responses_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/responses_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
+      sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
+      sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/trace_store.db
+      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/meta_reference_eval.db
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/huggingface_datasetio.db
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config:
+      kvstore:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/localfs_datasetio.db
+  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/watsonx/files}
+      metadata_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/files_metadata.db
+metadata_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/registry.db
+inference_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/inference_store.db
+models:
+- metadata: {}
+  model_id: meta-llama/llama-3-3-70b-instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-3-70b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-3-70b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/llama-2-13b-chat
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-2-13b-chat
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-2-13b
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-2-13b-chat
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/llama-3-1-70b-instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-1-70b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-70B-Instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-1-70b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/llama-3-1-8b-instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-1-8b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-8B-Instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-1-8b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/llama-3-2-11b-vision-instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-2-11b-vision-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-2-11b-vision-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/llama-3-2-1b-instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-2-1b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-1B-Instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-2-1b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/llama-3-2-3b-instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-2-3b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-3B-Instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-2-3b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/llama-3-2-90b-vision-instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-2-90b-vision-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-3-2-90b-vision-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/llama-guard-3-11b-vision
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-guard-3-11b-vision
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-Guard-3-11B-Vision
+  provider_id: watsonx
+  provider_model_id: meta-llama/llama-guard-3-11b-vision
+  model_type: llm
+- metadata:
+    embedding_dimension: 384
+  model_id: all-MiniLM-L6-v2
+  provider_id: sentence-transformers
+  model_type: embedding
+shields: []
+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