Merge remote-tracking branch 'origin/main' into stores

llama_stack/distributions/dell/doc_template.md

@@ -117,11 +117,11 @@ docker run -it \
   # NOTE: mount the llama-stack directory if testing local changes else not needed
   -v $HOME/git/llama-stack:/app/llama-stack-source \
   # localhost/distribution-dell:dev if building / testing locally
+  -e INFERENCE_MODEL=$INFERENCE_MODEL \
+  -e DEH_URL=$DEH_URL \
+  -e CHROMA_URL=$CHROMA_URL \
   llamastack/distribution-{{ name }}\
-  --port $LLAMA_STACK_PORT  \
-  --env INFERENCE_MODEL=$INFERENCE_MODEL \
-  --env DEH_URL=$DEH_URL \
-  --env CHROMA_URL=$CHROMA_URL
+  --port $LLAMA_STACK_PORT
 
 ```
 
@@ -142,14 +142,14 @@ docker run \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v $HOME/.llama:/root/.llama \
   -v ./llama_stack/distributions/tgi/run-with-safety.yaml:/root/my-run.yaml \
+  -e INFERENCE_MODEL=$INFERENCE_MODEL \
+  -e DEH_URL=$DEH_URL \
+  -e SAFETY_MODEL=$SAFETY_MODEL \
+  -e DEH_SAFETY_URL=$DEH_SAFETY_URL \
+  -e CHROMA_URL=$CHROMA_URL \
   llamastack/distribution-{{ name }} \
   --config /root/my-run.yaml \
-  --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=$INFERENCE_MODEL \
-  --env DEH_URL=$DEH_URL \
-  --env SAFETY_MODEL=$SAFETY_MODEL \
-  --env DEH_SAFETY_URL=$DEH_SAFETY_URL \
-  --env CHROMA_URL=$CHROMA_URL
+  --port $LLAMA_STACK_PORT
 ```
 
 ### Via Conda
@@ -158,21 +158,21 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
 
 ```bash
 llama stack build --distro {{ name }} --image-type conda
-llama stack run {{ name }}
-  --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=$INFERENCE_MODEL \
-  --env DEH_URL=$DEH_URL \
-  --env CHROMA_URL=$CHROMA_URL
+INFERENCE_MODEL=$INFERENCE_MODEL \
+DEH_URL=$DEH_URL \
+CHROMA_URL=$CHROMA_URL \
+llama stack run {{ name }} \
+  --port $LLAMA_STACK_PORT
 ```
 
 If you are using Llama Stack Safety / Shield APIs, use:
 
 ```bash
+INFERENCE_MODEL=$INFERENCE_MODEL \
+DEH_URL=$DEH_URL \
+SAFETY_MODEL=$SAFETY_MODEL \
+DEH_SAFETY_URL=$DEH_SAFETY_URL \
+CHROMA_URL=$CHROMA_URL \
 llama stack run ./run-with-safety.yaml \
-  --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=$INFERENCE_MODEL \
-  --env DEH_URL=$DEH_URL \
-  --env SAFETY_MODEL=$SAFETY_MODEL \
-  --env DEH_SAFETY_URL=$DEH_SAFETY_URL \
-  --env CHROMA_URL=$CHROMA_URL
+  --port $LLAMA_STACK_PORT
 ```

llama_stack/distributions/dell/run-with-safety.yaml

@@ -101,6 +101,9 @@ metadata_store:
 inference_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/inference_store.db
+conversations_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/conversations.db
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}

llama_stack/distributions/meta-reference-gpu/doc_template.md

@@ -29,31 +29,7 @@ The following environment variables can be configured:
 
 ## Prerequisite: Downloading Models
 
-Please use `llama model list --downloaded` to check that you have llama model checkpoints downloaded in `~/.llama` before proceeding. See [installation guide](../../references/llama_cli_reference/download_models.md) here to download the models. Run `llama model list` to see the available models to download, and `llama model download` to download the checkpoints.
-
-```
-$ llama model list --downloaded
-┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┓
-┃ Model                                   ┃ Size     ┃ Modified Time       ┃
-┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━┩
-│ Llama3.2-1B-Instruct:int4-qlora-eo8     │ 1.53 GB  │ 2025-02-26 11:22:28 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama3.2-1B                             │ 2.31 GB  │ 2025-02-18 21:48:52 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Prompt-Guard-86M                        │ 0.02 GB  │ 2025-02-26 11:29:28 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama3.2-3B-Instruct:int4-spinquant-eo8 │ 3.69 GB  │ 2025-02-26 11:37:41 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama3.2-3B                             │ 5.99 GB  │ 2025-02-18 21:51:26 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama3.1-8B                             │ 14.97 GB │ 2025-02-16 10:36:37 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama3.2-1B-Instruct:int4-spinquant-eo8 │ 1.51 GB  │ 2025-02-26 11:35:02 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama-Guard-3-1B                        │ 2.80 GB  │ 2025-02-26 11:20:46 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama-Guard-3-1B:int4                   │ 0.43 GB  │ 2025-02-26 11:33:33 │
-└─────────────────────────────────────────┴──────────┴─────────────────────┘
+Please check that you have llama model checkpoints downloaded in `~/.llama` before proceeding. See [installation guide](../../references/llama_cli_reference/download_models.md) here to download the models using the Hugging Face CLI.
 ```
 
 ## Running the Distribution
@@ -72,9 +48,9 @@ docker run \
   --gpu all \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
+  -e INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
   llamastack/distribution-{{ name }} \
-  --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
+  --port $LLAMA_STACK_PORT
 ```
 
 If you are using Llama Stack Safety / Shield APIs, use:
@@ -86,10 +62,10 @@ docker run \
   --gpu all \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
+  -e INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+  -e SAFETY_MODEL=meta-llama/Llama-Guard-3-1B \
   llamastack/distribution-{{ name }} \
-  --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
-  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
+  --port $LLAMA_STACK_PORT
 ```
 
 ### Via venv
@@ -98,16 +74,16 @@ Make sure you have done `uv pip install llama-stack` and have the Llama Stack CL
 
 ```bash
 llama stack build --distro {{ name }} --image-type venv
+INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
 llama stack run distributions/{{ name }}/run.yaml \
-  --port 8321 \
-  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
+  --port 8321
 ```
 
 If you are using Llama Stack Safety / Shield APIs, use:
 
 ```bash
+INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+SAFETY_MODEL=meta-llama/Llama-Guard-3-1B \
 llama stack run distributions/{{ name }}/run-with-safety.yaml \
-  --port 8321 \
-  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
-  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
+  --port 8321
 ```

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

@@ -114,6 +114,9 @@ metadata_store:
 inference_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/inference_store.db
+conversations_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/conversations.db
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}

llama_stack/distributions/nvidia/doc_template.md

@@ -118,10 +118,10 @@ docker run \
   --pull always \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ./run.yaml:/root/my-run.yaml \
+  -e NVIDIA_API_KEY=$NVIDIA_API_KEY \
   llamastack/distribution-{{ name }} \
   --config /root/my-run.yaml \
-  --port $LLAMA_STACK_PORT \
-  --env NVIDIA_API_KEY=$NVIDIA_API_KEY
+  --port $LLAMA_STACK_PORT
 ```
 
 ### Via venv
@@ -131,10 +131,10 @@ If you've set up your local development environment, you can also build the imag
 ```bash
 INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
 llama stack build --distro nvidia --image-type venv
+NVIDIA_API_KEY=$NVIDIA_API_KEY \
+INFERENCE_MODEL=$INFERENCE_MODEL \
 llama stack run ./run.yaml \
-  --port 8321 \
-  --env NVIDIA_API_KEY=$NVIDIA_API_KEY \
-  --env INFERENCE_MODEL=$INFERENCE_MODEL
+  --port 8321
 ```
 
 ## Example Notebooks

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

@@ -103,6 +103,9 @@ metadata_store:
 inference_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/inference_store.db
+conversations_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/conversations.db
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}

llama_stack/distributions/template.py

@@ -181,6 +181,7 @@ class RunConfigSettings(BaseModel):
     default_benchmarks: list[BenchmarkInput] | None = None
     metadata_store: dict | None = None
     inference_store: dict | None = None
+    conversations_store: dict | None = None
 
     def run_config(
         self,
@@ -240,6 +241,11 @@ class RunConfigSettings(BaseModel):
                 __distro_dir__=f"~/.llama/distributions/{name}",
                 db_name="inference_store.db",
             ),
+            "conversations_store": self.conversations_store
+            or SqliteSqlStoreConfig.sample_run_config(
+                __distro_dir__=f"~/.llama/distributions/{name}",
+                db_name="conversations.db",
+            ),
             "models": [m.model_dump(exclude_none=True) for m in (self.default_models or [])],
             "shields": [s.model_dump(exclude_none=True) for s in (self.default_shields or [])],
             "vector_dbs": [],

llama_stack/distributions/watsonx/__init__.py

@@ -3,3 +3,5 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
+
+from .watsonx import get_distribution_template  # noqa: F401

llama_stack/distributions/watsonx/build.yaml

@@ -3,44 +3,33 @@ distribution_spec:
   description: Use watsonx for running LLM inference
   providers:
     inference:
-    - provider_id: watsonx
-      provider_type: remote::watsonx
-    - provider_id: sentence-transformers
-      provider_type: inline::sentence-transformers
+    - provider_type: remote::watsonx
+    - provider_type: inline::sentence-transformers
     vector_io:
-    - provider_id: faiss
-      provider_type: inline::faiss
+    - provider_type: inline::faiss
     safety:
-    - provider_id: llama-guard
-      provider_type: inline::llama-guard
+    - provider_type: inline::llama-guard
     agents:
-    - provider_id: meta-reference
-      provider_type: inline::meta-reference
+    - provider_type: inline::meta-reference
     telemetry:
-    - provider_id: meta-reference
-      provider_type: inline::meta-reference
+    - provider_type: inline::meta-reference
     eval:
-    - provider_id: meta-reference
-      provider_type: inline::meta-reference
+    - provider_type: inline::meta-reference
     datasetio:
-    - provider_id: huggingface
-      provider_type: remote::huggingface
-    - provider_id: localfs
-      provider_type: inline::localfs
+    - provider_type: remote::huggingface
+    - provider_type: inline::localfs
     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
+    - 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]
-- aiosqlite
-- aiosqlite

llama_stack/distributions/watsonx/watsonx.py

@@ -4,17 +4,11 @@
 # 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.apis.models import ModelType
-from llama_stack.core.datatypes import BuildProvider, ModelInput, Provider, ToolGroupInput
-from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings, get_model_registry
+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.inference.sentence_transformers import (
-    SentenceTransformersInferenceConfig,
-)
 from llama_stack.providers.remote.inference.watsonx import WatsonXConfig
-from llama_stack.providers.remote.inference.watsonx.models import MODEL_ENTRIES
 
 
 def get_distribution_template(name: str = "watsonx") -> DistributionTemplate:
@@ -52,15 +46,6 @@ def get_distribution_template(name: str = "watsonx") -> DistributionTemplate:
         config=WatsonXConfig.sample_run_config(),
     )
 
-    embedding_provider = Provider(
-        provider_id="sentence-transformers",
-        provider_type="inline::sentence-transformers",
-        config=SentenceTransformersInferenceConfig.sample_run_config(),
-    )
-
-    available_models = {
-        "watsonx": MODEL_ENTRIES,
-    }
     default_tool_groups = [
         ToolGroupInput(
             toolgroup_id="builtin::websearch",
@@ -72,36 +57,25 @@ def get_distribution_template(name: str = "watsonx") -> DistributionTemplate:
         ),
     ]
 
-    embedding_model = ModelInput(
-        model_id="all-MiniLM-L6-v2",
-        provider_id="sentence-transformers",
-        model_type=ModelType.embedding,
-        metadata={
-            "embedding_dimension": 384,
-        },
-    )
-
     files_provider = Provider(
         provider_id="meta-reference-files",
         provider_type="inline::localfs",
         config=LocalfsFilesImplConfig.sample_run_config(f"~/.llama/distributions/{name}"),
     )
-    default_models, _ = get_model_registry(available_models)
     return DistributionTemplate(
         name=name,
         distro_type="remote_hosted",
         description="Use watsonx for running LLM inference",
         container_image=None,
-        template_path=Path(__file__).parent / "doc_template.md",
+        template_path=None,
         providers=providers,
-        available_models_by_provider=available_models,
         run_configs={
             "run.yaml": RunConfigSettings(
                 provider_overrides={
-                    "inference": [inference_provider, embedding_provider],
+                    "inference": [inference_provider],
                     "files": [files_provider],
                 },
-                default_models=default_models + [embedding_model],
+                default_models=[],
                 default_tool_groups=default_tool_groups,
             ),
         },