Merge remote-tracking branch 'origin/main' into stack-config-default-embed

.dockerignore

@@ -0,0 +1,19 @@
+.venv
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+*.so
+.git
+.gitignore
+htmlcov*
+.coverage
+coverage*
+.cache
+.mypy_cache
+.pytest_cache
+.ruff_cache
+uv.lock
+node_modules
+build
+/tmp

.github/actions/run-and-record-tests/action.yml

@@ -82,11 +82,14 @@ runs:
           echo "No recording changes"
         fi
 
-    - name: Write inference logs to file
+    - name: Write docker logs to file
       if: ${{ always() }}
       shell: bash
       run: |
         sudo docker logs ollama > ollama-${{ inputs.inference-mode }}.log || true
+        distro_name=$(echo "${{ inputs.stack-config }}" | sed 's/^docker://' | sed 's/^server://')
+        stack_container_name="llama-stack-test-$distro_name"
+        sudo docker logs $stack_container_name > docker-${distro_name}-${{ inputs.inference-mode }}.log || true
 
     - name: Upload logs
       if: ${{ always() }}

.github/actions/setup-test-environment/action.yml

@@ -57,7 +57,7 @@ runs:
         echo "Building Llama Stack"
 
         LLAMA_STACK_DIR=. \
-          uv run --no-sync llama stack build --template ci-tests --image-type venv
+          uv run --no-sync llama stack list-deps ci-tests | xargs -L1 uv pip install
 
     - name: Configure git for commits
       shell: bash

.github/workflows/README.md

@@ -14,6 +14,7 @@ Llama Stack uses GitHub Actions for Continuous Integration (CI). Below is a tabl
 | Pre-commit | [pre-commit.yml](pre-commit.yml) | Run pre-commit checks |
 | Pre-commit Bot | [precommit-trigger.yml](precommit-trigger.yml) | Pre-commit bot for PR |
 | Test Llama Stack Build | [providers-build.yml](providers-build.yml) | Test llama stack build |
+| Test llama stack list-deps | [providers-list-deps.yml](providers-list-deps.yml) | Test llama stack list-deps |
 | Python Package Build Test | [python-build-test.yml](python-build-test.yml) | Test building the llama-stack PyPI project |
 | Integration Tests (Record) | [record-integration-tests.yml](record-integration-tests.yml) | Run the integration test suite from tests/integration |
 | Check semantic PR titles | [semantic-pr.yml](semantic-pr.yml) | Ensure that PR titles follow the conventional commit spec |

.github/workflows/install-script-ci.yml

@@ -30,8 +30,11 @@ jobs:
 
       - name: Build a single provider
         run: |
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run --no-sync \
+          docker build . \
-            llama stack build --template starter --image-type container --image-name test
+            -f containers/Containerfile \
+            --build-arg INSTALL_MODE=editable \
+            --build-arg DISTRO_NAME=starter \
+            --tag llama-stack:starter-ci
 
       - name: Run installer end-to-end
         run: |

.github/workflows/integration-auth-tests.yml

@@ -73,6 +73,24 @@ jobs:
           image_name: kube
           apis: []
           providers: {}
+          storage:
+            backends:
+              kv_default:
+                type: kv_sqlite
+                db_path: $run_dir/kvstore.db
+              sql_default:
+                type: sql_sqlite
+                db_path: $run_dir/sql_store.db
+            stores:
+              metadata:
+                namespace: registry
+                backend: kv_default
+              inference:
+                table_name: inference_store
+                backend: sql_default
+              conversations:
+                table_name: openai_conversations
+                backend: sql_default
           server:
             port: 8321
           EOF

.github/workflows/integration-tests.yml

@@ -47,7 +47,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        client-type: [library, server]
+        client-type: [library, server, docker]
         # Use Python 3.13 only on nightly schedule (daily latest client test), otherwise use 3.12
         python-version: ${{ github.event.schedule == '0 0 * * *' && fromJSON('["3.12", "3.13"]') || fromJSON('["3.12"]') }}
         client-version: ${{ (github.event.schedule == '0 0 * * *' || github.event.inputs.test-all-client-versions == 'true') && fromJSON('["published", "latest"]') || fromJSON('["latest"]') }}
@@ -82,7 +82,7 @@ jobs:
         env:
           OPENAI_API_KEY: dummy
         with:
-          stack-config: ${{ matrix.client-type == 'library' && 'ci-tests' || 'server:ci-tests' }}
+          stack-config: ${{ matrix.client-type == 'library' && 'ci-tests' || matrix.client-type == 'server' && 'server:ci-tests' || 'docker:ci-tests' }}
           setup: ${{ matrix.config.setup }}
           inference-mode: 'replay'
           suite: ${{ matrix.config.suite }}

.github/workflows/integration-vector-io-tests.yml

@@ -144,7 +144,7 @@ jobs:
 
       - name: Build Llama Stack
         run: |
-          uv run --no-sync llama stack build --template ci-tests --image-type venv
+          uv run --no-sync llama stack list-deps ci-tests | xargs -L1 uv pip install
 
       - name: Check Storage and Memory Available Before Tests
         if: ${{ always() }}

.github/workflows/providers-build.yml

@@ -14,6 +14,8 @@ on:
       - '.github/workflows/providers-build.yml'
       - 'llama_stack/distributions/**'
       - 'pyproject.toml'
+      - 'containers/Containerfile'
+      - '.dockerignore'
 
   pull_request:
     paths:
@@ -24,6 +26,8 @@ on:
       - '.github/workflows/providers-build.yml'
       - 'llama_stack/distributions/**'
       - 'pyproject.toml'
+      - 'containers/Containerfile'
+      - '.dockerignore'
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
@@ -60,15 +64,19 @@ jobs:
       - name: Install dependencies
         uses: ./.github/actions/setup-runner
 
-      - name: Print build dependencies
+      - name: Install distribution into venv
+        if: matrix.image-type == 'venv'
         run: |
-          uv run llama stack build --distro ${{ matrix.distro }} --image-type ${{ matrix.image-type }} --image-name test --print-deps-only
+          uv run llama stack list-deps ${{ matrix.distro }} | xargs -L1 uv pip install
 
-      - name: Run Llama Stack Build
+      - name: Build container image
+        if: matrix.image-type == 'container'
         run: |
-          # USE_COPY_NOT_MOUNT is set to true since mounting is not supported by docker buildx, we use COPY instead
+          docker build . \
-          # LLAMA_STACK_DIR is set to the current directory so we are building from the source
+            -f containers/Containerfile \
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack build --distro ${{ matrix.distro }} --image-type ${{ matrix.image-type }} --image-name test
+            --build-arg INSTALL_MODE=editable \
+            --build-arg DISTRO_NAME=${{ matrix.distro }} \
+            --tag llama-stack:${{ matrix.distro }}-ci
 
       - name: Print dependencies in the image
         if: matrix.image-type == 'venv'
@@ -86,8 +94,8 @@ jobs:
 
       - name: Build a single provider
         run: |
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack build --image-type venv --image-name test --providers inference=remote::ollama
+          uv pip install -e .
-
+          uv run --no-sync llama stack list-deps --providers inference=remote::ollama | xargs -L1 uv pip install
   build-custom-container-distribution:
     runs-on: ubuntu-latest
     steps:
@@ -97,11 +105,16 @@ jobs:
       - name: Install dependencies
         uses: ./.github/actions/setup-runner
 
-      - name: Build a single provider
+      - name: Build container image
         run: |
-          yq -i '.image_type = "container"' llama_stack/distributions/ci-tests/build.yaml
+          BASE_IMAGE=$(yq -r '.distribution_spec.container_image // "python:3.12-slim"' llama_stack/distributions/ci-tests/build.yaml)
-          yq -i '.image_name = "test"' llama_stack/distributions/ci-tests/build.yaml
+          docker build . \
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack build --config llama_stack/distributions/ci-tests/build.yaml
+            -f containers/Containerfile \
+            --build-arg INSTALL_MODE=editable \
+            --build-arg DISTRO_NAME=ci-tests \
+            --build-arg BASE_IMAGE="$BASE_IMAGE" \
+            --build-arg RUN_CONFIG_PATH=/workspace/llama_stack/distributions/ci-tests/run.yaml \
+            -t llama-stack:ci-tests
 
       - name: Inspect the container image entrypoint
         run: |
@@ -112,7 +125,7 @@ jobs:
           fi
           entrypoint=$(docker inspect --format '{{ .Config.Entrypoint }}' $IMAGE_ID)
           echo "Entrypoint: $entrypoint"
-          if [ "$entrypoint" != "[llama stack run /app/run.yaml]" ]; then
+          if [ "$entrypoint" != "[/usr/local/bin/llama-stack-entrypoint.sh]" ]; then
             echo "Entrypoint is not correct"
             exit 1
           fi
@@ -129,17 +142,19 @@ jobs:
       - name: Pin distribution to UBI9 base
         run: |
           yq -i '
-            .image_type    = "container" |
-            .image_name    = "ubi9-test" |
             .distribution_spec.container_image = "registry.access.redhat.com/ubi9:latest"
           ' llama_stack/distributions/ci-tests/build.yaml
 
-      - name: Build dev container (UBI9)
+      - name: Build UBI9 container image
-        env:
-          USE_COPY_NOT_MOUNT: "true"
-          LLAMA_STACK_DIR: "."
         run: |
-          uv run llama stack build --config llama_stack/distributions/ci-tests/build.yaml
+          BASE_IMAGE=$(yq -r '.distribution_spec.container_image // "registry.access.redhat.com/ubi9:latest"' llama_stack/distributions/ci-tests/build.yaml)
+          docker build . \
+            -f containers/Containerfile \
+            --build-arg INSTALL_MODE=editable \
+            --build-arg DISTRO_NAME=ci-tests \
+            --build-arg BASE_IMAGE="$BASE_IMAGE" \
+            --build-arg RUN_CONFIG_PATH=/workspace/llama_stack/distributions/ci-tests/run.yaml \
+            -t llama-stack:ci-tests-ubi9
 
       - name: Inspect UBI9 image
         run: |
@@ -150,7 +165,7 @@ jobs:
           fi
           entrypoint=$(docker inspect --format '{{ .Config.Entrypoint }}' $IMAGE_ID)
           echo "Entrypoint: $entrypoint"
-          if [ "$entrypoint" != "[llama stack run /app/run.yaml]" ]; then
+          if [ "$entrypoint" != "[/usr/local/bin/llama-stack-entrypoint.sh]" ]; then
             echo "Entrypoint is not correct"
             exit 1
           fi

.github/workflows/providers-list-deps.yml

@@ -0,0 +1,105 @@
+name: Test llama stack list-deps
+
+run-name: Test llama stack list-deps
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - 'llama_stack/cli/stack/list_deps.py'
+      - 'llama_stack/cli/stack/_list_deps.py'
+      - 'llama_stack/core/build.*'
+      - 'llama_stack/core/*.sh'
+      - '.github/workflows/providers-list-deps.yml'
+      - 'llama_stack/templates/**'
+      - 'pyproject.toml'
+
+  pull_request:
+    paths:
+      - 'llama_stack/cli/stack/list_deps.py'
+      - 'llama_stack/cli/stack/_list_deps.py'
+      - 'llama_stack/core/build.*'
+      - 'llama_stack/core/*.sh'
+      - '.github/workflows/providers-list-deps.yml'
+      - 'llama_stack/templates/**'
+      - 'pyproject.toml'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  generate-matrix:
+    runs-on: ubuntu-latest
+    outputs:
+      distros: ${{ steps.set-matrix.outputs.distros }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Generate Distribution List
+        id: set-matrix
+        run: |
+          distros=$(ls llama_stack/distributions/*/*build.yaml | awk -F'/' '{print $(NF-1)}' | jq -R -s -c 'split("\n")[:-1]')
+          echo "distros=$distros" >> "$GITHUB_OUTPUT"
+
+  list-deps:
+    needs: generate-matrix
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        distro: ${{ fromJson(needs.generate-matrix.outputs.distros) }}
+        image-type: [venv, container]
+      fail-fast: false # We want to run all jobs even if some fail
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Install dependencies
+        uses: ./.github/actions/setup-runner
+
+      - name: Print dependencies
+        run: |
+          uv run llama stack list-deps ${{ matrix.distro }}
+
+      - name: Install Distro using llama stack list-deps
+        run: |
+          # USE_COPY_NOT_MOUNT is set to true since mounting is not supported by docker buildx, we use COPY instead
+          # LLAMA_STACK_DIR is set to the current directory so we are building from the source
+          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack list-deps ${{ matrix.distro }} | xargs -L1 uv pip install
+
+      - name: Print dependencies in the image
+        if: matrix.image-type == 'venv'
+        run: |
+          uv pip list
+
+  show-single-provider:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Install dependencies
+        uses: ./.github/actions/setup-runner
+
+      - name: Show a single provider
+        run: |
+          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack list-deps --providers inference=remote::ollama
+
+  list-deps-from-config:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Install dependencies
+        uses: ./.github/actions/setup-runner
+
+      - name: list-des from Config
+        env:
+          USE_COPY_NOT_MOUNT: "true"
+          LLAMA_STACK_DIR: "."
+        run: |
+          uv run llama stack list-deps llama_stack/distributions/ci-tests/build.yaml

.github/workflows/test-external-provider-module.yml

@@ -46,9 +46,9 @@ jobs:
           yq -i '.image_type = "${{ matrix.image-type }}"' tests/external/ramalama-stack/run.yaml
           cat tests/external/ramalama-stack/run.yaml
 
-      - name: Build distro from config file
+      - name: Install distribution dependencies
         run: |
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack build --config tests/external/ramalama-stack/build.yaml
+          uv run llama stack list-deps tests/external/ramalama-stack/build.yaml | xargs -L1 uv pip install
 
       - name: Start Llama Stack server in background
         if: ${{ matrix.image-type }} == 'venv'

.github/workflows/test-external.yml

@@ -44,11 +44,14 @@ jobs:
 
       - name: Print distro dependencies
         run: |
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run --no-sync llama stack build --config tests/external/build.yaml --print-deps-only
+          uv run --no-sync llama stack list-deps tests/external/build.yaml
 
       - name: Build distro from config file
         run: |
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run --no-sync llama stack build --config tests/external/build.yaml
+          uv venv ci-test
+          source ci-test/bin/activate
+          uv pip install -e .
+          LLAMA_STACK_LOGGING=all=CRITICAL llama stack list-deps tests/external/build.yaml | xargs -L1 uv pip install
 
       - name: Start Llama Stack server in background
         if: ${{ matrix.image-type }} == 'venv'

CONTRIBUTING.md

@@ -167,9 +167,9 @@ under the LICENSE file in the root directory of this source tree.
 
 Some tips about common tasks you work on while contributing to Llama Stack:
 
-### Using `llama stack build`
+### Installing dependencies of distributions
 
-Building a stack image will use the production version of the `llama-stack` and `llama-stack-client` packages. If you are developing with a llama-stack repository checked out and need your code to be reflected in the stack image, set `LLAMA_STACK_DIR` and `LLAMA_STACK_CLIENT_DIR` to the appropriate checked out directories when running any of the `llama` CLI commands.
+When installing dependencies for a distribution, you can use `llama stack list-deps` to view and install the required packages.
 
 Example:
 ```bash
@@ -177,7 +177,12 @@ cd work/
 git clone https://github.com/llamastack/llama-stack.git
 git clone https://github.com/llamastack/llama-stack-client-python.git
 cd llama-stack
-LLAMA_STACK_DIR=$(pwd) LLAMA_STACK_CLIENT_DIR=../llama-stack-client-python llama stack build --distro <...>
+
+# Show dependencies for a distribution
+llama stack list-deps <distro-name>
+
+# Install dependencies
+llama stack list-deps <distro-name> | xargs -L1 uv pip install
 ```
 
 ### Updating distribution configurations

README.md

@@ -27,8 +27,11 @@ MODEL="Llama-4-Scout-17B-16E-Instruct"
 # get meta url from llama.com
 huggingface-cli download meta-llama/$MODEL --local-dir ~/.llama/$MODEL
 
+# install dependencies for the distribution
+llama stack list-deps meta-reference-gpu | xargs -L1 uv pip install
+
 # start a llama stack server
-INFERENCE_MODEL=meta-llama/$MODEL llama stack build --run --template meta-reference-gpu
+INFERENCE_MODEL=meta-llama/$MODEL llama stack run meta-reference-gpu
 
 # install client to interact with the server
 pip install llama-stack-client
@@ -89,7 +92,7 @@ As more providers start supporting Llama 4, you can use them in Llama Stack as w
 To try Llama Stack locally, run:
 
 ```bash
-curl -LsSf https://github.com/meta-llama/llama-stack/raw/main/scripts/install.sh | bash
+curl -LsSf https://github.com/llamastack/llama-stack/raw/main/scripts/install.sh | bash
 ```
 
 ### Overview

benchmarking/k8s-benchmark/stack-configmap.yaml

@@ -98,21 +98,30 @@ data:
       - provider_id: model-context-protocol
         provider_type: remote::model-context-protocol
         config: {}
-    metadata_store:
+    storage:
-      type: postgres
+      backends:
-      host: ${env.POSTGRES_HOST:=localhost}
+        kv_default:
-      port: ${env.POSTGRES_PORT:=5432}
+          type: kv_postgres
-      db: ${env.POSTGRES_DB:=llamastack}
+          host: ${env.POSTGRES_HOST:=localhost}
-      user: ${env.POSTGRES_USER:=llamastack}
+          port: ${env.POSTGRES_PORT:=5432}
-      password: ${env.POSTGRES_PASSWORD:=llamastack}
+          db: ${env.POSTGRES_DB:=llamastack}
-      table_name: llamastack_kvstore
+          user: ${env.POSTGRES_USER:=llamastack}
-    inference_store:
+          password: ${env.POSTGRES_PASSWORD:=llamastack}
-      type: postgres
+          table_name: ${env.POSTGRES_TABLE_NAME:=llamastack_kvstore}
-      host: ${env.POSTGRES_HOST:=localhost}
+        sql_default:
-      port: ${env.POSTGRES_PORT:=5432}
+          type: sql_postgres
-      db: ${env.POSTGRES_DB:=llamastack}
+          host: ${env.POSTGRES_HOST:=localhost}
-      user: ${env.POSTGRES_USER:=llamastack}
+          port: ${env.POSTGRES_PORT:=5432}
-      password: ${env.POSTGRES_PASSWORD:=llamastack}
+          db: ${env.POSTGRES_DB:=llamastack}
+          user: ${env.POSTGRES_USER:=llamastack}
+          password: ${env.POSTGRES_PASSWORD:=llamastack}
+      references:
+        metadata:
+          backend: kv_default
+          namespace: registry
+        inference:
+          backend: sql_default
+          table_name: inference_store
     models:
     - metadata:
         embedding_dimension: 768
@@ -137,5 +146,4 @@ data:
       port: 8323
 kind: ConfigMap
 metadata:
-  creationTimestamp: null
   name: llama-stack-config

benchmarking/k8s-benchmark/stack_run_config.yaml

@@ -95,21 +95,30 @@ providers:
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
     config: {}
-metadata_store:
+storage:
-  type: postgres
+  backends:
-  host: ${env.POSTGRES_HOST:=localhost}
+    kv_default:
-  port: ${env.POSTGRES_PORT:=5432}
+      type: kv_postgres
-  db: ${env.POSTGRES_DB:=llamastack}
+      host: ${env.POSTGRES_HOST:=localhost}
-  user: ${env.POSTGRES_USER:=llamastack}
+      port: ${env.POSTGRES_PORT:=5432}
-  password: ${env.POSTGRES_PASSWORD:=llamastack}
+      db: ${env.POSTGRES_DB:=llamastack}
-  table_name: llamastack_kvstore
+      user: ${env.POSTGRES_USER:=llamastack}
-inference_store:
+      password: ${env.POSTGRES_PASSWORD:=llamastack}
-  type: postgres
+      table_name: ${env.POSTGRES_TABLE_NAME:=llamastack_kvstore}
-  host: ${env.POSTGRES_HOST:=localhost}
+    sql_default:
-  port: ${env.POSTGRES_PORT:=5432}
+      type: sql_postgres
-  db: ${env.POSTGRES_DB:=llamastack}
+      host: ${env.POSTGRES_HOST:=localhost}
-  user: ${env.POSTGRES_USER:=llamastack}
+      port: ${env.POSTGRES_PORT:=5432}
-  password: ${env.POSTGRES_PASSWORD:=llamastack}
+      db: ${env.POSTGRES_DB:=llamastack}
+      user: ${env.POSTGRES_USER:=llamastack}
+      password: ${env.POSTGRES_PASSWORD:=llamastack}
+  references:
+    metadata:
+      backend: kv_default
+      namespace: registry
+    inference:
+      backend: sql_default
+      table_name: inference_store
 models:
 - metadata:
     embedding_dimension: 768

containers/Containerfile

@@ -0,0 +1,136 @@
+# syntax=docker/dockerfile:1.6
+#
+# This Dockerfile is used to build the Llama Stack container image.
+# Example:
+# docker build \
+#   -f containers/Containerfile \
+#   --build-arg DISTRO_NAME=starter \
+#   --tag llama-stack:starter .
+
+ARG BASE_IMAGE=python:3.12-slim
+FROM ${BASE_IMAGE}
+
+ARG INSTALL_MODE="pypi"
+ARG LLAMA_STACK_DIR="/workspace"
+ARG LLAMA_STACK_CLIENT_DIR=""
+ARG PYPI_VERSION=""
+ARG TEST_PYPI_VERSION=""
+ARG KEEP_WORKSPACE=""
+ARG DISTRO_NAME="starter"
+ARG RUN_CONFIG_PATH=""
+ARG UV_HTTP_TIMEOUT=500
+ENV UV_HTTP_TIMEOUT=${UV_HTTP_TIMEOUT}
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PIP_DISABLE_PIP_VERSION_CHECK=1
+WORKDIR /app
+
+RUN set -eux; \
+    if command -v dnf >/dev/null 2>&1; then \
+        dnf -y update && \
+        dnf install -y iputils git net-tools wget \
+            vim-minimal python3.12 python3.12-pip python3.12-wheel \
+            python3.12-setuptools python3.12-devel gcc gcc-c++ make && \
+        ln -sf /usr/bin/pip3.12 /usr/local/bin/pip && \
+        ln -sf /usr/bin/python3.12 /usr/local/bin/python && \
+        dnf clean all; \
+    elif command -v apt-get >/dev/null 2>&1; then \
+        apt-get update && \
+        apt-get install -y --no-install-recommends \
+            iputils-ping net-tools iproute2 dnsutils telnet \
+            curl wget git procps psmisc lsof traceroute bubblewrap \
+            gcc g++ && \
+        rm -rf /var/lib/apt/lists/*; \
+    else \
+        echo "Unsupported base image: expected dnf or apt-get" >&2; \
+        exit 1; \
+    fi
+
+RUN pip install --no-cache-dir uv
+ENV UV_SYSTEM_PYTHON=1
+
+ENV INSTALL_MODE=${INSTALL_MODE}
+ENV LLAMA_STACK_DIR=${LLAMA_STACK_DIR}
+ENV LLAMA_STACK_CLIENT_DIR=${LLAMA_STACK_CLIENT_DIR}
+ENV PYPI_VERSION=${PYPI_VERSION}
+ENV TEST_PYPI_VERSION=${TEST_PYPI_VERSION}
+ENV KEEP_WORKSPACE=${KEEP_WORKSPACE}
+ENV DISTRO_NAME=${DISTRO_NAME}
+ENV RUN_CONFIG_PATH=${RUN_CONFIG_PATH}
+
+# Copy the repository so editable installs and run configurations are available.
+COPY . /workspace
+
+# Install llama-stack
+RUN set -eux; \
+    if [ "$INSTALL_MODE" = "editable" ]; then \
+        if [ ! -d "$LLAMA_STACK_DIR" ]; then \
+            echo "INSTALL_MODE=editable requires LLAMA_STACK_DIR to point to a directory inside the build context" >&2; \
+            exit 1; \
+        fi; \
+        uv pip install --no-cache-dir -e "$LLAMA_STACK_DIR"; \
+    elif [ "$INSTALL_MODE" = "test-pypi" ]; then \
+        uv pip install --no-cache-dir fastapi libcst; \
+        if [ -n "$TEST_PYPI_VERSION" ]; then \
+            uv pip install --no-cache-dir --extra-index-url https://test.pypi.org/simple/ --index-strategy unsafe-best-match "llama-stack==$TEST_PYPI_VERSION"; \
+        else \
+            uv pip install --no-cache-dir --extra-index-url https://test.pypi.org/simple/ --index-strategy unsafe-best-match llama-stack; \
+        fi; \
+    else \
+        if [ -n "$PYPI_VERSION" ]; then \
+            uv pip install --no-cache-dir "llama-stack==$PYPI_VERSION"; \
+        else \
+            uv pip install --no-cache-dir llama-stack; \
+        fi; \
+    fi;
+
+# Install the client package if it is provided
+RUN set -eux; \
+    if [ -n "$LLAMA_STACK_CLIENT_DIR" ]; then \
+        if [ ! -d "$LLAMA_STACK_CLIENT_DIR" ]; then \
+            echo "LLAMA_STACK_CLIENT_DIR is set but $LLAMA_STACK_CLIENT_DIR does not exist" >&2; \
+            exit 1; \
+        fi; \
+        uv pip install --no-cache-dir -e "$LLAMA_STACK_CLIENT_DIR"; \
+    fi;
+
+# Install the dependencies for the distribution
+RUN set -eux; \
+    if [ -z "$DISTRO_NAME" ]; then \
+        echo "DISTRO_NAME must be provided" >&2; \
+        exit 1; \
+    fi; \
+    deps="$(llama stack list-deps "$DISTRO_NAME")"; \
+    if [ -n "$deps" ]; then \
+        printf '%s\n' "$deps" | xargs -L1 uv pip install --no-cache-dir; \
+    fi
+
+# Cleanup
+RUN set -eux; \
+    pip uninstall -y uv; \
+    should_remove=1; \
+    if [ -n "$KEEP_WORKSPACE" ]; then should_remove=0; fi; \
+    if [ "$INSTALL_MODE" = "editable" ]; then should_remove=0; fi; \
+    case "$RUN_CONFIG_PATH" in \
+        /workspace*) should_remove=0 ;; \
+    esac; \
+    if [ "$should_remove" -eq 1 ] && [ -d /workspace ]; then rm -rf /workspace; fi
+
+RUN cat <<'EOF' >/usr/local/bin/llama-stack-entrypoint.sh
+#!/bin/sh
+set -e
+
+if [ -n "$RUN_CONFIG_PATH" ] && [ -f "$RUN_CONFIG_PATH" ]; then
+  exec llama stack run "$RUN_CONFIG_PATH" "$@"
+fi
+
+if [ -n "$DISTRO_NAME" ]; then
+  exec llama stack run "$DISTRO_NAME" "$@"
+fi
+
+exec llama stack run "$@"
+EOF
+RUN chmod +x /usr/local/bin/llama-stack-entrypoint.sh
+
+RUN mkdir -p /.llama /.cache && chmod -R g+rw /app /.llama /.cache
+
+ENTRYPOINT ["/usr/local/bin/llama-stack-entrypoint.sh"]

docs/docs/advanced_apis/post_training.mdx

@@ -51,8 +51,8 @@ device: cpu
 You can access the HuggingFace trainer via the `starter` distribution:
 
 ```bash
-llama stack build --distro starter --image-type venv
+llama stack list-deps starter | xargs -L1 uv pip install
-llama stack run ~/.llama/distributions/starter/starter-run.yaml
+llama stack run starter
 ```
 
 ### Usage Example

docs/docs/building_applications/playground.mdx

@@ -175,8 +175,7 @@ llama-stack-client benchmarks register \
 **1. Start the Llama Stack API Server**
 
 ```bash
-# Build and run a distribution (example: together)
+llama stack list-deps together | xargs -L1 uv pip install
-llama stack build --distro together --image-type venv
 llama stack run together
 ```
 
@@ -209,7 +208,7 @@ The playground works with any Llama Stack distribution. Popular options include:
 <TabItem value="together" label="Together AI">
 
 ```bash
-llama stack build --distro together --image-type venv
+llama stack list-deps together | xargs -L1 uv pip install
 llama stack run together
 ```
 
@@ -222,7 +221,7 @@ llama stack run together
 <TabItem value="ollama" label="Ollama (Local)">
 
 ```bash
-llama stack build --distro ollama --image-type venv
+llama stack list-deps ollama | xargs -L1 uv pip install
 llama stack run ollama
 ```
 
@@ -235,7 +234,7 @@ llama stack run ollama
 <TabItem value="meta-reference" label="Meta Reference">
 
 ```bash
-llama stack build --distro meta-reference --image-type venv
+llama stack list-deps meta-reference | xargs -L1 uv pip install
 llama stack run meta-reference
 ```
 

docs/docs/building_applications/rag.mdx

@@ -20,7 +20,8 @@ RAG enables your applications to reference and recall information from external
 In one terminal, start the Llama Stack server:
 
 ```bash
-uv run llama stack build --distro starter --image-type venv --run
+llama stack list-deps starter | xargs -L1 uv pip install
+llama stack run starter
 ```
 
 ### 2. Connect with OpenAI Client

docs/docs/concepts/apis/api_leveling.mdx

@@ -62,6 +62,10 @@ The new `/v2` API must be introduced alongside the existing `/v1` API and run in
 
 When a `/v2` API is introduced, a clear and generous deprecation policy for the `/v1` API must be published simultaneously. This policy must outline the timeline for the eventual removal of the `/v1` API, giving users ample time to migrate.
 
+### Deprecated APIs
+
+Deprecated APIs are those that are no longer actively maintained or supported. Depreated APIs are marked with the flag `deprecated = True` in the OpenAPI spec. These APIs will be removed in a future release.
+
 ### API Stability vs. Provider Stability
 
 The leveling introduced in this document relates to the stability of the API and not specifically the providers within the API.

docs/docs/contributing/index.mdx

@@ -158,17 +158,16 @@ under the LICENSE file in the root directory of this source tree.
 
 Some tips about common tasks you work on while contributing to Llama Stack:
 
-### Using `llama stack build`
+### Setup for development
 
-Building a stack image will use the production version of the `llama-stack` and `llama-stack-client` packages. If you are developing with a llama-stack repository checked out and need your code to be reflected in the stack image, set `LLAMA_STACK_DIR` and `LLAMA_STACK_CLIENT_DIR` to the appropriate checked out directories when running any of the `llama` CLI commands.
-
-Example:
 ```bash
-cd work/
 git clone https://github.com/meta-llama/llama-stack.git
-git clone https://github.com/meta-llama/llama-stack-client-python.git
 cd llama-stack
-LLAMA_STACK_DIR=$(pwd) LLAMA_STACK_CLIENT_DIR=../llama-stack-client-python llama stack build --distro <...>
+uv run llama stack list-deps <distro-name> | xargs -L1 uv pip install
+
+# (Optional) If you are developing the llama-stack-client-python package, you can add it as an editable package.
+git clone https://github.com/meta-llama/llama-stack-client-python.git
+uv add --editable ../llama-stack-client-python
 ```
 
 ### Updating distribution configurations

docs/docs/contributing/new_api_provider.mdx

@@ -67,7 +67,7 @@ def get_base_url(self) -> str:
 
 ## Testing the Provider
 
-Before running tests, you must have required dependencies installed. This depends on the providers or distributions you are testing. For example, if you are testing the `together` distribution, you should install dependencies via `llama stack build --distro together`.
+Before running tests, you must have required dependencies installed. This depends on the providers or distributions you are testing. For example, if you are testing the `together` distribution, install its dependencies with `llama stack list-deps together | xargs -L1 uv pip install`.
 
 ### 1. Integration Testing
 

docs/docs/distributions/building_distro.mdx

@@ -5,225 +5,79 @@ sidebar_label: Build your own Distribution
 sidebar_position: 3
 ---
 
-This guide will walk you through the steps to get started with building a Llama Stack distribution from scratch with your choice of API providers.
+This guide walks you through inspecting existing distributions, customising their configuration, and building runnable artefacts for your own deployment.
 
+### Explore existing distributions
 
-### Setting your log level
+All first-party distributions live under `llama_stack/distributions/`. Each directory contains:
 
-In order to specify the proper logging level users can apply the following environment variable `LLAMA_STACK_LOGGING` with the following format:
+- `build.yaml` – the distribution specification (providers, additional dependencies, optional external provider directories).
+- `run.yaml` – sample run configuration (when provided).
+- Documentation fragments that power this site.
 
-`LLAMA_STACK_LOGGING=server=debug;core=info`
+Browse that folder to understand available providers and copy a distribution to use as a starting point. When creating a new stack, duplicate an existing directory, rename it, and adjust the `build.yaml` file to match your requirements.
-
-Where each category in the following list:
-
-- all
-- core
-- server
-- router
-- inference
-- agents
-- safety
-- eval
-- tools
-- client
-
-Can be set to any of the following log levels:
-
-- debug
-- info
-- warning
-- error
-- critical
-
-The default global log level is `info`. `all` sets the log level for all components.
-
-A user can also set `LLAMA_STACK_LOG_FILE` which will pipe the logs to the specified path as well as to the terminal. An example would be: `export LLAMA_STACK_LOG_FILE=server.log`
-
-### Llama Stack Build
-
-In order to build your own distribution, we recommend you clone the `llama-stack` repository.
-
-
-```
-git clone git@github.com:meta-llama/llama-stack.git
-cd llama-stack
-pip install -e .
-```
-Use the CLI to build your distribution.
-The main points to consider are:
-1. **Image Type** - Do you want a venv environment or a Container (eg. Docker)
-2. **Template** - Do you want to use a template to build your distribution? or start from scratch ?
-3. **Config** - Do you want to use a pre-existing config file to build your distribution?
-
-```
-llama stack build -h
-usage: llama stack build [-h] [--config CONFIG] [--template TEMPLATE] [--distro DISTRIBUTION] [--list-distros] [--image-type {container,venv}] [--image-name IMAGE_NAME] [--print-deps-only]
-                         [--run] [--providers PROVIDERS]
-
-Build a Llama stack container
-
-options:
-  -h, --help            show this help message and exit
-  --config CONFIG       Path to a config file to use for the build. You can find example configs in llama_stack.cores/**/build.yaml. If this argument is not provided, you will be prompted to
-                        enter information interactively (default: None)
-  --template TEMPLATE   (deprecated) Name of the example template config to use for build. You may use `llama stack build --list-distros` to check out the available distributions (default:
-                        None)
-  --distro DISTRIBUTION, --distribution DISTRIBUTION
-                        Name of the distribution to use for build. You may use `llama stack build --list-distros` to check out the available distributions (default: None)
-  --list-distros, --list-distributions
-                        Show the available distributions for building a Llama Stack distribution (default: False)
-  --image-type {container,venv}
-                        Image Type to use for the build. If not specified, will use the image type from the template config. (default: None)
-  --image-name IMAGE_NAME
-                        [for image-type=container|venv] Name of the virtual environment to use for the build. If not specified, currently active environment will be used if found. (default:
-                        None)
-  --print-deps-only     Print the dependencies for the stack only, without building the stack (default: False)
-  --run                 Run the stack after building using the same image type, name, and other applicable arguments (default: False)
-  --providers PROVIDERS
-                        Build a config for a list of providers and only those providers. This list is formatted like: api1=provider1,api2=provider2. Where there can be multiple providers per
-                        API. (default: None)
-```
-
-After this step is complete, a file named `<name>-build.yaml` and template file `<name>-run.yaml` will be generated and saved at the output file path specified at the end of the command.
 
 import Tabs from '@theme/Tabs';
 import TabItem from '@theme/TabItem';
-
 <Tabs>
-<TabItem value="template" label="Building from a template">
+<TabItem value="container" label="Building a container">
-To build from alternative API providers, we provide distribution templates for users to get started building a distribution backed by different providers.
 
-The following command will allow you to see the available templates and their corresponding providers.
+Use the Containerfile at `containers/Containerfile`, which installs `llama-stack`, resolves distribution dependencies via `llama stack list-deps`, and sets the entrypoint to `llama stack run`.
-```
+
-llama stack build --list-templates
+```bash
+docker build . \
+  -f containers/Containerfile \
+  --build-arg DISTRO_NAME=starter \
+  --tag llama-stack:starter
 ```
 
-```
+Handy build arguments:
-------------------------------+-----------------------------------------------------------------------------+
-| Template Name                | Description                                                                 |
-+------------------------------+-----------------------------------------------------------------------------+
-| watsonx                      | Use watsonx for running LLM inference                                       |
-+------------------------------+-----------------------------------------------------------------------------+
-| vllm-gpu                     | Use a built-in vLLM engine for running LLM inference                        |
-+------------------------------+-----------------------------------------------------------------------------+
-| together                     | Use Together.AI for running LLM inference                                   |
-+------------------------------+-----------------------------------------------------------------------------+
-| tgi                          | Use (an external) TGI server for running LLM inference                      |
-+------------------------------+-----------------------------------------------------------------------------+
-| starter                      | Quick start template for running Llama Stack with several popular providers |
-+------------------------------+-----------------------------------------------------------------------------+
-| sambanova                    | Use SambaNova for running LLM inference and safety                          |
-+------------------------------+-----------------------------------------------------------------------------+
-| remote-vllm                  | Use (an external) vLLM server for running LLM inference                     |
-+------------------------------+-----------------------------------------------------------------------------+
-| postgres-demo                | Quick start template for running Llama Stack with several popular providers |
-+------------------------------+-----------------------------------------------------------------------------+
-| passthrough                  | Use Passthrough hosted llama-stack endpoint for LLM inference               |
-+------------------------------+-----------------------------------------------------------------------------+
-| open-benchmark               | Distribution for running open benchmarks                                    |
-+------------------------------+-----------------------------------------------------------------------------+
-| ollama                       | Use (an external) Ollama server for running LLM inference                   |
-+------------------------------+-----------------------------------------------------------------------------+
-| nvidia                       | Use NVIDIA NIM for running LLM inference, evaluation and safety             |
-+------------------------------+-----------------------------------------------------------------------------+
-| meta-reference-gpu           | Use Meta Reference for running LLM inference                                |
-+------------------------------+-----------------------------------------------------------------------------+
-| llama_api                    | Distribution for running e2e tests in CI                                    |
-+------------------------------+-----------------------------------------------------------------------------+
-| hf-serverless                | Use (an external) Hugging Face Inference Endpoint for running LLM inference |
-+------------------------------+-----------------------------------------------------------------------------+
-| hf-endpoint                  | Use (an external) Hugging Face Inference Endpoint for running LLM inference |
-+------------------------------+-----------------------------------------------------------------------------+
-| groq                         | Use Groq for running LLM inference                                          |
-+------------------------------+-----------------------------------------------------------------------------+
-| fireworks                    | Use Fireworks.AI for running LLM inference                                  |
-+------------------------------+-----------------------------------------------------------------------------+
-| experimental-post-training   | Experimental template for post training                                     |
-+------------------------------+-----------------------------------------------------------------------------+
-| dell                         | Dell's distribution of Llama Stack. TGI inference via Dell's custom         |
-|                              | container                                                                   |
-+------------------------------+-----------------------------------------------------------------------------+
-| ci-tests                     | Distribution for running e2e tests in CI                                    |
-+------------------------------+-----------------------------------------------------------------------------+
-| cerebras                     | Use Cerebras for running LLM inference                                      |
-+------------------------------+-----------------------------------------------------------------------------+
-| bedrock                      | Use AWS Bedrock for running LLM inference and safety                        |
-+------------------------------+-----------------------------------------------------------------------------+
-```
 
-You may then pick a template to build your distribution with providers fitted to your liking.
+- `DISTRO_NAME` – distribution directory name (defaults to `starter`).
+- `RUN_CONFIG_PATH` – absolute path inside the build context for a run config that should be baked into the image (e.g. `/workspace/run.yaml`).
+- `INSTALL_MODE=editable` – install the repository copied into `/workspace` with `uv pip install -e`. Pair it with `--build-arg LLAMA_STACK_DIR=/workspace`.
+- `LLAMA_STACK_CLIENT_DIR` – optional editable install of the Python client.
+- `PYPI_VERSION` / `TEST_PYPI_VERSION` – pin specific releases when not using editable installs.
+- `KEEP_WORKSPACE=1` – retain `/workspace` in the final image if you need to access additional files (such as sample configs or provider bundles).
 
-For example, to build a distribution with TGI as the inference provider, you can run:
+Make sure any custom `build.yaml`, run configs, or provider directories you reference are included in the Docker build context so the Containerfile can read them.
-```
-$ llama stack build --distro starter
-...
-You can now edit ~/.llama/distributions/llamastack-starter/starter-run.yaml and run `llama stack run ~/.llama/distributions/llamastack-starter/starter-run.yaml`
-```
 
-```{tip}
-The generated `run.yaml` file is a starting point for your configuration. For comprehensive guidance on customizing it for your specific needs, infrastructure, and deployment scenarios, see [Customizing Your run.yaml Configuration](customizing_run_yaml.md).
-```
 </TabItem>
-<TabItem value="scratch" label="Building from Scratch">
+<TabItem value="external" label="Building with external providers">
 
-If the provided templates do not fit your use case, you could start off with running `llama stack build` which will allow you to a interactively enter wizard where you will be prompted to enter build configurations.
+External providers live outside the main repository but can be bundled by pointing `external_providers_dir` to a directory that contains your provider packages.
 
-It would be best to start with a template and understand the structure of the config file and the various concepts ( APIS, providers, resources, etc.) before starting from scratch.
+1. Copy providers into the build context, for example `cp -R path/to/providers providers.d`.
-```
+2. Update `build.yaml` with the directory and provider entries.
-llama stack build
+3. Adjust run configs to use the in-container path (usually `/.llama/providers.d`). Pass `--build-arg RUN_CONFIG_PATH=/workspace/run.yaml` if you want to bake the config.
 
-> Enter a name for your Llama Stack (e.g. my-local-stack): my-stack
+Example `build.yaml` excerpt for a custom Ollama provider:
-> Enter the image type you want your Llama Stack to be built as (container or venv): venv
-
-Llama Stack is composed of several APIs working together. Let's select
-the provider types (implementations) you want to use for these APIs.
-
-Tip: use <TAB> to see options for the providers.
-
-> Enter provider for API inference: inline::meta-reference
-> Enter provider for API safety: inline::llama-guard
-> Enter provider for API agents: inline::meta-reference
-> Enter provider for API memory: inline::faiss
-> Enter provider for API datasetio: inline::meta-reference
-> Enter provider for API scoring: inline::meta-reference
-> Enter provider for API eval: inline::meta-reference
-> Enter provider for API telemetry: inline::meta-reference
-
- > (Optional) Enter a short description for your Llama Stack:
-
-You can now edit ~/.llama/distributions/llamastack-my-local-stack/my-local-stack-run.yaml and run `llama stack run ~/.llama/distributions/llamastack-my-local-stack/my-local-stack-run.yaml`
-```
-</TabItem>
-<TabItem value="config" label="Building from a pre-existing build config file">
-- In addition to templates, you may customize the build to your liking through editing config files and build from config files with the following command.
-
-- The config file will be of contents like the ones in `llama_stack/distributions/*build.yaml`.
-
-```
-llama stack build --config llama_stack/distributions/starter/build.yaml
-```
-</TabItem>
-<TabItem value="external" label="Building with External Providers">
-
-Llama Stack supports external providers that live outside of the main codebase. This allows you to create and maintain your own providers independently or use community-provided providers.
-
-To build a distribution with external providers, you need to:
-
-1. Configure the `external_providers_dir` in your build configuration file:
 
 ```yaml
-# Example my-external-stack.yaml with external providers
-version: '2'
 distribution_spec:
-  description: Custom distro for CI tests
   providers:
     inference:
-    - remote::custom_ollama
+      - remote::custom_ollama
-# Add more providers as needed
+external_providers_dir: /workspace/providers.d
-image_type: container
+```
-image_name: ci-test
+
-# Path to external provider implementations
+Inside `providers.d/custom_ollama/provider.py`, define `get_provider_spec()` so the CLI can discover dependencies:
-external_providers_dir: ~/.llama/providers.d
+
+```python
+from llama_stack.providers.datatypes import ProviderSpec
+
+
+def get_provider_spec() -> ProviderSpec:
+    return ProviderSpec(
+        provider_type="remote::custom_ollama",
+        module="llama_stack_ollama_provider",
+        config_class="llama_stack_ollama_provider.config.OllamaImplConfig",
+        pip_packages=[
+            "ollama",
+            "aiohttp",
+            "llama-stack-provider-ollama",
+        ],
+    )
 ```
 
 Here's an example for a custom Ollama provider:
@@ -232,9 +86,9 @@ Here's an example for a custom Ollama provider:
 adapter:
   adapter_type: custom_ollama
   pip_packages:
-  - ollama
+    - ollama
-  - aiohttp
+    - aiohttp
-  - llama-stack-provider-ollama # This is the provider package
+    - llama-stack-provider-ollama  # This is the provider package
   config_class: llama_stack_ollama_provider.config.OllamaImplConfig
   module: llama_stack_ollama_provider
 api_dependencies: []
@@ -245,53 +99,22 @@ The `pip_packages` section lists the Python packages required by the provider, a
 provider package itself. The package must be available on PyPI or can be provided from a local
 directory or a git repository (git must be installed on the build environment).
 
-2. Build your distribution using the config file:
+For deeper guidance, see the [External Providers documentation](../providers/external/).
 
-```
-llama stack build --config my-external-stack.yaml
-```
-
-For more information on external providers, including directory structure, provider types, and implementation requirements, see the [External Providers documentation](../providers/external/).
 </TabItem>
-<TabItem value="container" label="Building Container">
+</Tabs>
 
-:::tip Podman Alternative
+### Run your stack server
-Podman is supported as an alternative to Docker. Set `CONTAINER_BINARY` to `podman` in your environment to use Podman.
-:::
 
-To build a container image, you may start off from a template and use the `--image-type container` flag to specify `container` as the build image type.
+After building the image, launch it directly with Docker or Podman—the entrypoint calls `llama stack run` using the baked distribution or the bundled run config:
-
-```
-llama stack build --distro starter --image-type container
-```
-
-```
-$ llama stack build --distro starter --image-type container
-...
-Containerfile created successfully in /tmp/tmp.viA3a3Rdsg/ContainerfileFROM python:3.10-slim
-...
-```
-
-You can now edit ~/meta-llama/llama-stack/tmp/configs/ollama-run.yaml and run `llama stack run ~/meta-llama/llama-stack/tmp/configs/ollama-run.yaml`
-```
-
-Now set some environment variables for the inference model ID and Llama Stack Port and create a local directory to mount into the container's file system.
 
 ```bash
-export INFERENCE_MODEL="llama3.2:3b"
-export LLAMA_STACK_PORT=8321
-mkdir -p ~/.llama
-```
-
-After this step is successful, you should be able to find the built container image and test it with the below Docker command:
-
-```
 docker run -d \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
   -e INFERENCE_MODEL=$INFERENCE_MODEL \
   -e OLLAMA_URL=http://host.docker.internal:11434 \
-  localhost/distribution-ollama:dev \
+  llama-stack:starter \
   --port $LLAMA_STACK_PORT
 ```
 
@@ -311,131 +134,14 @@ Here are the docker flags and their uses:
 
 * `--port $LLAMA_STACK_PORT`: Port number for the server to listen on
 
-</TabItem>
-</Tabs>
 
 
-### Running your Stack server
+If you prepared a custom run config, mount it into the container and reference it explicitly:
-Now, let's start the Llama Stack Distribution Server. You will need the YAML configuration file which was written out at the end by the `llama stack build` step.
 
+```bash
+docker run \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v $(pwd)/run.yaml:/app/run.yaml \
+  llama-stack:starter \
+  /app/run.yaml
 ```
-llama stack run -h
-usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME]
-                       [--image-type {venv}] [--enable-ui]
-                       [config | distro]
-
-Start the server for a Llama Stack Distribution. You should have already built (or downloaded) and configured the distribution.
-
-positional arguments:
-  config | distro       Path to config file to use for the run or name of known distro (`llama stack list` for a list). (default: None)
-
-options:
-  -h, --help            show this help message and exit
-  --port PORT           Port to run the server on. It can also be passed via the env var LLAMA_STACK_PORT. (default: 8321)
-  --image-name IMAGE_NAME
-                        [DEPRECATED] This flag is no longer supported. Please activate your virtual environment before running. (default: None)
-  --image-type {venv}
-                        [DEPRECATED] This flag is no longer supported. Please activate your virtual environment before running. (default: None)
-  --enable-ui           Start the UI server (default: False)
-```
-
-**Note:** Container images built with `llama stack build --image-type container` cannot be run using `llama stack run`. Instead, they must be run directly using Docker or Podman commands as shown in the container building section above.
-
-```
-# Start using template name
-llama stack run tgi
-
-# Start using config file
-llama stack run ~/.llama/distributions/llamastack-my-local-stack/my-local-stack-run.yaml
-```
-
-```
-$ llama stack run ~/.llama/distributions/llamastack-my-local-stack/my-local-stack-run.yaml
-
-Serving API inspect
- GET /health
- GET /providers/list
- GET /routes/list
-Serving API inference
- POST /inference/chat_completion
- POST /inference/completion
- POST /inference/embeddings
-...
-Serving API agents
- POST /agents/create
- POST /agents/session/create
- POST /agents/turn/create
- POST /agents/delete
- POST /agents/session/delete
- POST /agents/session/get
- POST /agents/step/get
- POST /agents/turn/get
-
-Listening on ['::', '0.0.0.0']:8321
-INFO:     Started server process [2935911]
-INFO:     Waiting for application startup.
-INFO:     Application startup complete.
-INFO:     Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit)
-INFO:     2401:db00:35c:2d2b:face:0:c9:0:54678 - "GET /models/list HTTP/1.1" 200 OK
-```
-
-### Listing Distributions
-Using the list command, you can view all existing Llama Stack distributions, including stacks built from templates, from scratch, or using custom configuration files.
-
-```
-llama stack list -h
-usage: llama stack list [-h]
-
-list the build stacks
-
-options:
-  -h, --help  show this help message and exit
-```
-
-Example Usage
-
-```
-llama stack list
-```
-
-```
-------------------------------+-----------------------------------------------------------------+--------------+------------+
-| Stack Name                  | Path                                                            | Build Config | Run Config |
-+------------------------------+-----------------------------------------------------------------------------+--------------+
-| together                    | ~/.llama/distributions/together                                 | Yes          | No         |
-+------------------------------+-----------------------------------------------------------------------------+--------------+
-| bedrock                     | ~/.llama/distributions/bedrock                                  | Yes          | No         |
-+------------------------------+-----------------------------------------------------------------------------+--------------+
-| starter                     | ~/.llama/distributions/starter                                  | Yes          | Yes        |
-+------------------------------+-----------------------------------------------------------------------------+--------------+
-| remote-vllm                 | ~/.llama/distributions/remote-vllm                              | Yes          | Yes        |
-+------------------------------+-----------------------------------------------------------------------------+--------------+
-```
-
-### Removing a Distribution
-Use the remove command to delete a distribution you've previously built.
-
-```
-llama stack rm -h
-usage: llama stack rm [-h] [--all] [name]
-
-Remove the build stack
-
-positional arguments:
-  name        Name of the stack to delete (default: None)
-
-options:
-  -h, --help  show this help message and exit
-  --all, -a   Delete all stacks (use with caution) (default: False)
-```
-
-Example
-```
-llama stack rm llamastack-test
-```
-
-To keep your environment organized and avoid clutter, consider using `llama stack list` to review old or unused distributions and `llama stack rm <name>` to delete them when they're no longer needed.
-
-### Troubleshooting
-
-If you encounter any issues, ask questions in our discord or search through our [GitHub Issues](https://github.com/meta-llama/llama-stack/issues), or file an new issue.

docs/docs/distributions/configuration.mdx

@@ -44,18 +44,32 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
-      persistence_store:
+      persistence:
-        type: sqlite
+        agent_state:
-        namespace: null
+          backend: kv_default
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/agents_store.db
+          namespace: agents
+        responses:
+          backend: sql_default
+          table_name: responses
   telemetry:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config: {}
-metadata_store:
+storage:
-  namespace: null
+  backends:
-  type: sqlite
+    kv_default:
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/registry.db
+      type: kv_sqlite
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/kvstore.db
+    sql_default:
+      type: sql_sqlite
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/sqlstore.db
+  references:
+    metadata:
+      backend: kv_default
+      namespace: registry
+    inference:
+      backend: sql_default
+      table_name: inference_store
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}

docs/docs/distributions/importing_as_library.mdx

@@ -12,7 +12,7 @@ This avoids the overhead of setting up a server.
 ```bash
 # setup
 uv pip install llama-stack
-llama stack build --distro starter --image-type venv
+llama stack list-deps starter | xargs -L1 uv pip install
 ```
 
 ```python

docs/docs/distributions/k8s/stack-configmap.yaml

@@ -1,56 +1,155 @@
 apiVersion: v1
 data:
-  stack_run_config.yaml: "version: '2'\nimage_name: kubernetes-demo\napis:\n- agents\n-
+  stack_run_config.yaml: |
-    inference\n- files\n- safety\n- telemetry\n- tool_runtime\n- vector_io\nproviders:\n
+    version: '2'
-    \ inference:\n  - provider_id: vllm-inference\n    provider_type: remote::vllm\n
+    image_name: kubernetes-demo
-    \   config:\n      url: ${env.VLLM_URL:=http://localhost:8000/v1}\n      max_tokens:
+    apis:
-    ${env.VLLM_MAX_TOKENS:=4096}\n      api_token: ${env.VLLM_API_TOKEN:=fake}\n      tls_verify:
+    - agents
-    ${env.VLLM_TLS_VERIFY:=true}\n  - provider_id: vllm-safety\n    provider_type:
+    - inference
-    remote::vllm\n    config:\n      url: ${env.VLLM_SAFETY_URL:=http://localhost:8000/v1}\n
+    - files
-    \     max_tokens: ${env.VLLM_MAX_TOKENS:=4096}\n      api_token: ${env.VLLM_API_TOKEN:=fake}\n
+    - safety
-    \     tls_verify: ${env.VLLM_TLS_VERIFY:=true}\n  - provider_id: sentence-transformers\n
+    - telemetry
-    \   provider_type: inline::sentence-transformers\n    config: {}\n  vector_io:\n
+    - tool_runtime
-    \ - provider_id: ${env.ENABLE_CHROMADB:+chromadb}\n    provider_type: remote::chromadb\n
+    - vector_io
-    \   config:\n      url: ${env.CHROMADB_URL:=}\n      kvstore:\n        type: postgres\n
+    providers:
-    \       host: ${env.POSTGRES_HOST:=localhost}\n        port: ${env.POSTGRES_PORT:=5432}\n
+      inference:
-    \       db: ${env.POSTGRES_DB:=llamastack}\n        user: ${env.POSTGRES_USER:=llamastack}\n
+      - provider_id: vllm-inference
-    \       password: ${env.POSTGRES_PASSWORD:=llamastack}\n  files:\n  - provider_id:
+        provider_type: remote::vllm
-    meta-reference-files\n    provider_type: inline::localfs\n    config:\n      storage_dir:
+        config:
-    ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}\n      metadata_store:\n
+          url: ${env.VLLM_URL:=http://localhost:8000/v1}
-    \       type: sqlite\n        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db
+          max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
-    \ \n  safety:\n  - provider_id: llama-guard\n    provider_type: inline::llama-guard\n
+          api_token: ${env.VLLM_API_TOKEN:=fake}
-    \   config:\n      excluded_categories: []\n  agents:\n  - provider_id: meta-reference\n
+          tls_verify: ${env.VLLM_TLS_VERIFY:=true}
-    \   provider_type: inline::meta-reference\n    config:\n      persistence_store:\n
+      - provider_id: vllm-safety
-    \       type: postgres\n        host: ${env.POSTGRES_HOST:=localhost}\n        port:
+        provider_type: remote::vllm
-    ${env.POSTGRES_PORT:=5432}\n        db: ${env.POSTGRES_DB:=llamastack}\n        user:
+        config:
-    ${env.POSTGRES_USER:=llamastack}\n        password: ${env.POSTGRES_PASSWORD:=llamastack}\n
+          url: ${env.VLLM_SAFETY_URL:=http://localhost:8000/v1}
-    \     responses_store:\n        type: postgres\n        host: ${env.POSTGRES_HOST:=localhost}\n
+          max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
-    \       port: ${env.POSTGRES_PORT:=5432}\n        db: ${env.POSTGRES_DB:=llamastack}\n
+          api_token: ${env.VLLM_API_TOKEN:=fake}
-    \       user: ${env.POSTGRES_USER:=llamastack}\n        password: ${env.POSTGRES_PASSWORD:=llamastack}\n
+          tls_verify: ${env.VLLM_TLS_VERIFY:=true}
-    \ telemetry:\n  - provider_id: meta-reference\n    provider_type: inline::meta-reference\n
+      - provider_id: sentence-transformers
-    \   config:\n      service_name: \"${env.OTEL_SERVICE_NAME:=\\u200B}\"\n      sinks:
+        provider_type: inline::sentence-transformers
-    ${env.TELEMETRY_SINKS:=console}\n  tool_runtime:\n  - provider_id: brave-search\n
+        config: {}
-    \   provider_type: remote::brave-search\n    config:\n      api_key: ${env.BRAVE_SEARCH_API_KEY:+}\n
+      vector_io:
-    \     max_results: 3\n  - provider_id: tavily-search\n    provider_type: remote::tavily-search\n
+      - provider_id: ${env.ENABLE_CHROMADB:+chromadb}
-    \   config:\n      api_key: ${env.TAVILY_SEARCH_API_KEY:+}\n      max_results:
+        provider_type: remote::chromadb
-    3\n  - provider_id: rag-runtime\n    provider_type: inline::rag-runtime\n    config:
+        config:
-    {}\n  - provider_id: model-context-protocol\n    provider_type: remote::model-context-protocol\n
+          url: ${env.CHROMADB_URL:=}
-    \   config: {}\nmetadata_store:\n  type: postgres\n  host: ${env.POSTGRES_HOST:=localhost}\n
+          kvstore:
-    \ port: ${env.POSTGRES_PORT:=5432}\n  db: ${env.POSTGRES_DB:=llamastack}\n  user:
+            type: postgres
-    ${env.POSTGRES_USER:=llamastack}\n  password: ${env.POSTGRES_PASSWORD:=llamastack}\n
+            host: ${env.POSTGRES_HOST:=localhost}
-    \ table_name: llamastack_kvstore\ninference_store:\n  type: postgres\n  host:
+            port: ${env.POSTGRES_PORT:=5432}
-    ${env.POSTGRES_HOST:=localhost}\n  port: ${env.POSTGRES_PORT:=5432}\n  db: ${env.POSTGRES_DB:=llamastack}\n
+            db: ${env.POSTGRES_DB:=llamastack}
-    \ user: ${env.POSTGRES_USER:=llamastack}\n  password: ${env.POSTGRES_PASSWORD:=llamastack}\nmodels:\n-
+            user: ${env.POSTGRES_USER:=llamastack}
-    metadata:\n    embedding_dimension: 384\n  model_id: all-MiniLM-L6-v2\n  provider_id:
+            password: ${env.POSTGRES_PASSWORD:=llamastack}
-    sentence-transformers\n  model_type: embedding\n- metadata: {}\n  model_id: ${env.INFERENCE_MODEL}\n
+      files:
-    \ provider_id: vllm-inference\n  model_type: llm\n- metadata: {}\n  model_id:
+      - provider_id: meta-reference-files
-    ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}\n  provider_id: vllm-safety\n
+        provider_type: inline::localfs
-    \ model_type: llm\nshields:\n- shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}\nvector_dbs:
+        config:
-    []\ndatasets: []\nscoring_fns: []\nbenchmarks: []\ntool_groups:\n- toolgroup_id:
+          storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}
-    builtin::websearch\n  provider_id: tavily-search\n- toolgroup_id: builtin::rag\n
+          metadata_store:
-    \ provider_id: rag-runtime\nserver:\n  port: 8321\n  auth:\n    provider_config:\n
+            type: sqlite
-    \     type: github_token\n"
+            db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.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: 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: postgres
+            host: ${env.POSTGRES_HOST:=localhost}
+            port: ${env.POSTGRES_PORT:=5432}
+            db: ${env.POSTGRES_DB:=llamastack}
+            user: ${env.POSTGRES_USER:=llamastack}
+            password: ${env.POSTGRES_PASSWORD:=llamastack}
+      telemetry:
+      - provider_id: meta-reference
+        provider_type: inline::meta-reference
+        config:
+          service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
+          sinks: ${env.TELEMETRY_SINKS:=console}
+      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
+        config: {}
+      - provider_id: model-context-protocol
+        provider_type: remote::model-context-protocol
+        config: {}
+    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}
+      references:
+        metadata:
+          backend: kv_default
+          namespace: registry
+        inference:
+          backend: sql_default
+          table_name: inference_store
+    models:
+    - metadata:
+        embedding_dimension: 768
+      model_id: nomic-embed-text-v1.5
+      provider_id: sentence-transformers
+      model_type: embedding
+    - metadata: {}
+      model_id: ${env.INFERENCE_MODEL}
+      provider_id: vllm-inference
+      model_type: llm
+    - metadata: {}
+      model_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
+      provider_id: vllm-safety
+      model_type: llm
+    shields:
+    - shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
+    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
+      auth:
+        provider_config:
+          type: github_token
 kind: ConfigMap
 metadata:
-  creationTimestamp: null
   name: llama-stack-config

docs/docs/distributions/k8s/stack_run_config.yaml

@@ -93,21 +93,30 @@ providers:
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
     config: {}
-metadata_store:
+storage:
-  type: postgres
+  backends:
-  host: ${env.POSTGRES_HOST:=localhost}
+    kv_default:
-  port: ${env.POSTGRES_PORT:=5432}
+      type: kv_postgres
-  db: ${env.POSTGRES_DB:=llamastack}
+      host: ${env.POSTGRES_HOST:=localhost}
-  user: ${env.POSTGRES_USER:=llamastack}
+      port: ${env.POSTGRES_PORT:=5432}
-  password: ${env.POSTGRES_PASSWORD:=llamastack}
+      db: ${env.POSTGRES_DB:=llamastack}
-  table_name: llamastack_kvstore
+      user: ${env.POSTGRES_USER:=llamastack}
-inference_store:
+      password: ${env.POSTGRES_PASSWORD:=llamastack}
-  type: postgres
+      table_name: ${env.POSTGRES_TABLE_NAME:=llamastack_kvstore}
-  host: ${env.POSTGRES_HOST:=localhost}
+    sql_default:
-  port: ${env.POSTGRES_PORT:=5432}
+      type: sql_postgres
-  db: ${env.POSTGRES_DB:=llamastack}
+      host: ${env.POSTGRES_HOST:=localhost}
-  user: ${env.POSTGRES_USER:=llamastack}
+      port: ${env.POSTGRES_PORT:=5432}
-  password: ${env.POSTGRES_PASSWORD:=llamastack}
+      db: ${env.POSTGRES_DB:=llamastack}
+      user: ${env.POSTGRES_USER:=llamastack}
+      password: ${env.POSTGRES_PASSWORD:=llamastack}
+  references:
+    metadata:
+      backend: kv_default
+      namespace: registry
+    inference:
+      backend: sql_default
+      table_name: inference_store
 models:
 - metadata:
     embedding_dimension: 768

docs/docs/distributions/ondevice_distro/android_sdk.md

@@ -59,7 +59,7 @@ Start a Llama Stack server on localhost. Here is an example of how you can do th
 uv venv starter --python 3.12
 source starter/bin/activate  # On Windows: starter\Scripts\activate
 pip install --no-cache llama-stack==0.2.2
-llama stack build --distro starter --image-type venv
+llama stack list-deps starter | xargs -L1 uv pip install
 export FIREWORKS_API_KEY=<SOME_KEY>
 llama stack run starter --port 5050
 ```

docs/docs/distributions/self_hosted_distro/dell.md

@@ -166,10 +166,10 @@ docker run \
 
 ### Via venv
 
-Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
+Install the distribution dependencies before launching:
 
 ```bash
-llama stack build --distro dell --image-type venv
+llama stack list-deps dell | xargs -L1 uv pip install
 INFERENCE_MODEL=$INFERENCE_MODEL \
 DEH_URL=$DEH_URL \
 CHROMA_URL=$CHROMA_URL \

docs/docs/distributions/self_hosted_distro/meta-reference-gpu.md

@@ -81,10 +81,10 @@ docker run \
 
 ### Via venv
 
-Make sure you have done `uv pip install llama-stack` and have the Llama Stack CLI available.
+Make sure you have the Llama Stack CLI available.
 
 ```bash
-llama stack build --distro meta-reference-gpu --image-type venv
+llama stack list-deps meta-reference-gpu | xargs -L1 uv pip install
 INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
 llama stack run distributions/meta-reference-gpu/run.yaml \
   --port 8321

docs/docs/distributions/self_hosted_distro/nvidia.md

@@ -136,11 +136,11 @@ docker run \
 
 ### Via venv
 
-If you've set up your local development environment, you can also build the image using your local virtual environment.
+If you've set up your local development environment, you can also install the distribution dependencies using your local virtual environment.
 
 ```bash
 INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
-llama stack build --distro nvidia --image-type venv
+llama stack list-deps nvidia | xargs -L1 uv pip install
 NVIDIA_API_KEY=$NVIDIA_API_KEY \
 INFERENCE_MODEL=$INFERENCE_MODEL \
 llama stack run ./run.yaml \

docs/docs/distributions/self_hosted_distro/starter.md

@@ -169,7 +169,11 @@ docker run \
 Ensure you have configured the starter distribution using the environment variables explained above.
 
 ```bash
-uv run --with llama-stack llama stack build --distro starter --image-type venv --run
+# Install dependencies for the starter distribution
+uv run --with llama-stack llama stack list-deps starter | xargs -L1 uv pip install
+
+# Run the server
+uv run --with llama-stack llama stack run starter
 ```
 
 ## Example Usage

docs/docs/distributions/starting_llama_stack_server.mdx

@@ -23,6 +23,17 @@ Another simple way to start interacting with Llama Stack is to just spin up a co
 If you have built a container image and want to deploy it in a Kubernetes cluster instead of starting the Llama Stack server locally. See [Kubernetes Deployment Guide](../deploying/kubernetes_deployment) for more details.
 
 
+## Configure logging
+
+Control log output via environment variables before starting the server.
+
+- `LLAMA_STACK_LOGGING` sets per-component levels, e.g. `LLAMA_STACK_LOGGING=server=debug;core=info`.
+- Supported categories: `all`, `core`, `server`, `router`, `inference`, `agents`, `safety`, `eval`, `tools`, `client`.
+- Levels: `debug`, `info`, `warning`, `error`, `critical` (default is `info`). Use `all=<level>` to apply globally.
+- `LLAMA_STACK_LOG_FILE=/path/to/log` mirrors logs to a file while still printing to stdout.
+
+Export these variables prior to running `llama stack run`, launching a container, or starting the server through any other pathway.
+
 ```{toctree}
 :maxdepth: 1
 :hidden:

docs/docs/getting_started/detailed_tutorial.mdx

@@ -58,15 +58,19 @@ Llama Stack is a server that exposes multiple APIs, you connect with it using th
 
 <Tabs>
 <TabItem value="venv" label="Using venv">
-You can use Python to build and run the Llama Stack server, which is useful for testing and development.
+You can use Python to install dependencies and run the Llama Stack server, which is useful for testing and development.
 
 Llama Stack uses a [YAML configuration file](../distributions/configuration) to specify the stack setup,
 which defines the providers and their settings. The generated configuration serves as a starting point that you can [customize for your specific needs](../distributions/customizing_run_yaml).
-Now let's build and run the Llama Stack config for Ollama.
+Now let's install dependencies and run the Llama Stack config for Ollama.
 We use `starter` as template. By default all providers are disabled, this requires enable ollama by passing environment variables.
 
 ```bash
-llama stack build --distro starter --image-type venv --run
+# Install dependencies for the starter distribution
+uv run --with llama-stack llama stack list-deps starter | xargs -L1 uv pip install
+
+# Run the server
+llama stack run starter
 ```
 </TabItem>
 <TabItem value="container" label="Using a Container">
@@ -304,7 +308,7 @@ stream = agent.create_turn(
 for event in AgentEventLogger().log(stream):
     event.print()
 ```
-### ii. Run the Script
+#### ii. Run the Script
 Let's run the script using `uv`
 ```bash
 uv run python agent.py

docs/docs/getting_started/quickstart.mdx

@@ -24,10 +24,13 @@ ollama run llama3.2:3b --keepalive 60m
 
 #### Step 2: Run the Llama Stack server
 
-We will use `uv` to run the Llama Stack server.
+We will use `uv` to install dependencies and run the Llama Stack server.
 ```bash
-OLLAMA_URL=http://localhost:11434 \
+# Install dependencies for the starter distribution
-  uv run --with llama-stack llama stack build --distro starter --image-type venv --run
+uv run --with llama-stack llama stack list-deps starter | xargs -L1 uv pip install
+
+# Run the server
+OLLAMA_URL=http://localhost:11434 uv run --with llama-stack llama stack run starter
 ```
 #### Step 3: Run the demo
 Now open up a new terminal and copy the following script into a file named `demo_script.py`.

docs/docs/providers/agents/inline_meta-reference.mdx

@@ -14,16 +14,18 @@ Meta's reference implementation of an agent system that can use tools, access ve
 
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
-| `persistence_store` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
+| `persistence` | `<class 'inline.agents.meta_reference.config.AgentPersistenceConfig'>` | No |  |  |
-| `responses_store` | `utils.sqlstore.sqlstore.SqliteSqlStoreConfig \| utils.sqlstore.sqlstore.PostgresSqlStoreConfig` | No | sqlite |  |
 
 ## Sample Configuration
 
 ```yaml
-persistence_store:
+persistence:
-  type: sqlite
+  agent_state:
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/agents_store.db
+    namespace: agents
-responses_store:
+    backend: kv_default
-  type: sqlite
+  responses:
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/responses_store.db
+    table_name: responses
+    backend: sql_default
+    max_write_queue_size: 10000
+    num_writers: 4
 ```

docs/docs/providers/batches/inline_reference.mdx

@@ -14,7 +14,7 @@ Reference implementation of batches API with KVStore persistence.
 
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Configuration for the key-value store backend. |
+| `kvstore` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  | Configuration for the key-value store backend. |
 | `max_concurrent_batches` | `<class 'int'>` | No | 1 | Maximum number of concurrent batches to process simultaneously. |
 | `max_concurrent_requests_per_batch` | `<class 'int'>` | No | 10 | Maximum number of concurrent requests to process per batch. |
 
@@ -22,6 +22,6 @@ Reference implementation of batches API with KVStore persistence.
 
 ```yaml
 kvstore:
-  type: sqlite
+  namespace: batches
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/batches.db
+  backend: kv_default
 ```

docs/docs/providers/datasetio/inline_localfs.mdx

@@ -14,12 +14,12 @@ Local filesystem-based dataset I/O provider for reading and writing datasets to
 
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
+| `kvstore` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  |  |
 
 ## Sample Configuration
 
 ```yaml
 kvstore:
-  type: sqlite
+  namespace: datasetio::localfs
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/localfs_datasetio.db
+  backend: kv_default
 ```

docs/docs/providers/datasetio/remote_huggingface.mdx

@@ -14,12 +14,12 @@ HuggingFace datasets provider for accessing and managing datasets from the Huggi
 
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
+| `kvstore` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  |  |
 
 ## Sample Configuration
 
 ```yaml
 kvstore:
-  type: sqlite
+  namespace: datasetio::huggingface
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/huggingface_datasetio.db
+  backend: kv_default
 ```

docs/docs/providers/eval/index.mdx

@@ -1,5 +1,7 @@
 ---
-description: "Llama Stack Evaluation API for running evaluations on model and agent candidates."
+description: "Evaluations
+
+    Llama Stack Evaluation API for running evaluations on model and agent candidates."
 sidebar_label: Eval
 title: Eval
 ---
@@ -8,6 +10,8 @@ title: Eval
 
 ## Overview
 
-Llama Stack Evaluation API for running evaluations on model and agent candidates.
+Evaluations
+
+    Llama Stack Evaluation API for running evaluations on model and agent candidates.
 
 This section contains documentation for all available providers for the **eval** API.

docs/docs/providers/eval/inline_meta-reference.mdx

@@ -14,12 +14,12 @@ Meta's reference implementation of evaluation tasks with support for multiple la
 
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
+| `kvstore` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  |  |
 
 ## Sample Configuration
 
 ```yaml
 kvstore:
-  type: sqlite
+  namespace: eval
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/meta_reference_eval.db
+  backend: kv_default
 ```

docs/docs/providers/external/external-providers-guide.mdx

@@ -240,6 +240,6 @@ additional_pip_packages:
 - sqlalchemy[asyncio]
 ```
 
-No other steps are required other than `llama stack build` and `llama stack run`. The build process will use `module` to install all of the provider dependencies, retrieve the spec, etc.
+No other steps are required beyond installing dependencies with `llama stack list-deps <distro> | xargs -L1 uv pip install` and then running `llama stack run`. The CLI will use `module` to install the provider dependencies, retrieve the spec, etc.
 
 The provider will now be available in Llama Stack with the type `remote::ramalama`.

docs/docs/providers/files/inline_localfs.mdx

@@ -15,7 +15,7 @@ Local filesystem-based file storage provider for managing files and documents lo
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `storage_dir` | `<class 'str'>` | No |  | Directory to store uploaded files |
-| `metadata_store` | `utils.sqlstore.sqlstore.SqliteSqlStoreConfig \| utils.sqlstore.sqlstore.PostgresSqlStoreConfig` | No | sqlite | SQL store configuration for file metadata |
+| `metadata_store` | `<class 'llama_stack.core.storage.datatypes.SqlStoreReference'>` | No |  | SQL store configuration for file metadata |
 | `ttl_secs` | `<class 'int'>` | No | 31536000 |  |
 
 ## Sample Configuration
@@ -23,6 +23,6 @@ Local filesystem-based file storage provider for managing files and documents lo
 ```yaml
 storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/dummy/files}
 metadata_store:
-  type: sqlite
+  table_name: files_metadata
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/files_metadata.db
+  backend: sql_default
 ```

docs/docs/providers/files/remote_s3.mdx

@@ -20,7 +20,7 @@ AWS S3-based file storage provider for scalable cloud file management with metad
 | `aws_secret_access_key` | `str \| None` | No |  | AWS secret access key (optional if using IAM roles) |
 | `endpoint_url` | `str \| None` | No |  | Custom S3 endpoint URL (for MinIO, LocalStack, etc.) |
 | `auto_create_bucket` | `<class 'bool'>` | No | False | Automatically create the S3 bucket if it doesn't exist |
-| `metadata_store` | `utils.sqlstore.sqlstore.SqliteSqlStoreConfig \| utils.sqlstore.sqlstore.PostgresSqlStoreConfig` | No | sqlite | SQL store configuration for file metadata |
+| `metadata_store` | `<class 'llama_stack.core.storage.datatypes.SqlStoreReference'>` | No |  | SQL store configuration for file metadata |
 
 ## Sample Configuration
 
@@ -32,6 +32,6 @@ aws_secret_access_key: ${env.AWS_SECRET_ACCESS_KEY:=}
 endpoint_url: ${env.S3_ENDPOINT_URL:=}
 auto_create_bucket: ${env.S3_AUTO_CREATE_BUCKET:=false}
 metadata_store:
-  type: sqlite
+  table_name: s3_files_metadata
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/s3_files_metadata.db
+  backend: sql_default
 ```

docs/docs/providers/vector_io/inline_chromadb.mdx

@@ -79,13 +79,13 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `db_path` | `<class 'str'>` | No |  |  |
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend |
+| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  | Config for KV store backend |
 
 ## Sample Configuration
 
 ```yaml
 db_path: ${env.CHROMADB_PATH}
-kvstore:
+persistence:
-  type: sqlite
+  namespace: vector_io::chroma
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/chroma_inline_registry.db
+  backend: kv_default
 ```

docs/docs/providers/vector_io/inline_faiss.mdx

@@ -95,12 +95,12 @@ more details about Faiss in general.
 
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
+| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  |  |
 
 ## Sample Configuration
 
 ```yaml
-kvstore:
+persistence:
-  type: sqlite
+  namespace: vector_io::faiss
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/faiss_store.db
+  backend: kv_default
 ```

docs/docs/providers/vector_io/inline_meta-reference.mdx

@@ -14,14 +14,14 @@ Meta's reference implementation of a vector database.
 
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
+| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  |  |
 
 ## Sample Configuration
 
 ```yaml
-kvstore:
+persistence:
-  type: sqlite
+  namespace: vector_io::faiss
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/faiss_store.db
+  backend: kv_default
 ```
 ## Deprecation Notice
 

docs/docs/providers/vector_io/inline_milvus.mdx

@@ -17,14 +17,14 @@ Please refer to the remote provider documentation.
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `db_path` | `<class 'str'>` | No |  |  |
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend (SQLite only for now) |
+| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  | Config for KV store backend (SQLite only for now) |
 | `consistency_level` | `<class 'str'>` | No | Strong | The consistency level of the Milvus server |
 
 ## Sample Configuration
 
 ```yaml
 db_path: ${env.MILVUS_DB_PATH:=~/.llama/dummy}/milvus.db
-kvstore:
+persistence:
-  type: sqlite
+  namespace: vector_io::milvus
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/milvus_registry.db
+  backend: kv_default
 ```

docs/docs/providers/vector_io/inline_qdrant.mdx

@@ -98,13 +98,13 @@ See the [Qdrant documentation](https://qdrant.tech/documentation/) for more deta
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `path` | `<class 'str'>` | No |  |  |
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
+| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  |  |
 
 ## Sample Configuration
 
 ```yaml
 path: ${env.QDRANT_PATH:=~/.llama/~/.llama/dummy}/qdrant.db
-kvstore:
+persistence:
-  type: sqlite
+  namespace: vector_io::qdrant
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/qdrant_registry.db
+  backend: kv_default
 ```

docs/docs/providers/vector_io/inline_sqlite-vec.mdx

@@ -408,13 +408,13 @@ See [sqlite-vec's GitHub repo](https://github.com/asg017/sqlite-vec/tree/main) f
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `db_path` | `<class 'str'>` | No |  | Path to the SQLite database file |
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend (SQLite only for now) |
+| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  | Config for KV store backend (SQLite only for now) |
 
 ## Sample Configuration
 
 ```yaml
 db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/sqlite_vec.db
-kvstore:
+persistence:
-  type: sqlite
+  namespace: vector_io::sqlite_vec
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/sqlite_vec_registry.db
+  backend: kv_default
 ```

docs/docs/providers/vector_io/inline_sqlite_vec.mdx

@@ -17,15 +17,15 @@ Please refer to the sqlite-vec provider documentation.
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `db_path` | `<class 'str'>` | No |  | Path to the SQLite database file |
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend (SQLite only for now) |
+| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  | Config for KV store backend (SQLite only for now) |
 
 ## Sample Configuration
 
 ```yaml
 db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/sqlite_vec.db
-kvstore:
+persistence:
-  type: sqlite
+  namespace: vector_io::sqlite_vec
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/sqlite_vec_registry.db
+  backend: kv_default
 ```
 ## Deprecation Notice
 

docs/docs/providers/vector_io/remote_chromadb.mdx

@@ -78,13 +78,13 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
 | Field | Type | Required | Default | Description |
 |-------|------|----------|---------|-------------|
 | `url` | `str \| None` | No |  |  |
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend |
+| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  | Config for KV store backend |
 
 ## Sample Configuration
 
 ```yaml
 url: ${env.CHROMADB_URL}
-kvstore:
+persistence:
-  type: sqlite
+  namespace: vector_io::chroma_remote
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/chroma_remote_registry.db
+  backend: kv_default
 ```

docs/docs/providers/vector_io/remote_milvus.mdx

@@ -408,7 +408,7 @@ For more details on TLS configuration, refer to the [TLS setup guide](https://mi
 | `uri` | `<class 'str'>` | No |  | The URI of the Milvus server |
 | `token` | `str \| None` | No |  | The token of the Milvus server |
 | `consistency_level` | `<class 'str'>` | No | Strong | The consistency level of the Milvus server |
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend |
+| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  | Config for KV store backend |
 | `config` | `dict` | No | `{}` | This configuration allows additional fields to be passed through to the underlying Milvus client. See the [Milvus](https://milvus.io/docs/install-overview.md) documentation for more details about Milvus in general. |
 
 :::note
@@ -420,7 +420,7 @@ This configuration class accepts additional fields beyond those listed above. Yo
 ```yaml
 uri: ${env.MILVUS_ENDPOINT}
 token: ${env.MILVUS_TOKEN}
-kvstore:
+persistence:
-  type: sqlite
+  namespace: vector_io::milvus_remote
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/milvus_remote_registry.db
+  backend: kv_default
 ```

docs/docs/providers/vector_io/remote_pgvector.mdx

@@ -218,7 +218,7 @@ See [PGVector's documentation](https://github.com/pgvector/pgvector) for more de
 | `db` | `str \| None` | No | postgres |  |
 | `user` | `str \| None` | No | postgres |  |
 | `password` | `str \| None` | No | mysecretpassword |  |
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig, annotation=NoneType, required=False, default='sqlite', discriminator='type'` | No |  | Config for KV store backend (SQLite only for now) |
+| `persistence` | `llama_stack.core.storage.datatypes.KVStoreReference \| None` | No |  | Config for KV store backend (SQLite only for now) |
 
 ## Sample Configuration
 
@@ -228,7 +228,7 @@ port: ${env.PGVECTOR_PORT:=5432}
 db: ${env.PGVECTOR_DB}
 user: ${env.PGVECTOR_USER}
 password: ${env.PGVECTOR_PASSWORD}
-kvstore:
+persistence:
-  type: sqlite
+  namespace: vector_io::pgvector
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/pgvector_registry.db
+  backend: kv_default
 ```

docs/docs/providers/vector_io/remote_qdrant.mdx

@@ -26,13 +26,13 @@ Please refer to the inline provider documentation.
 | `prefix` | `str \| None` | No |  |  |
 | `timeout` | `int \| None` | No |  |  |
 | `host` | `str \| None` | No |  |  |
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite |  |
+| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No |  |  |
 
 ## Sample Configuration
 
 ```yaml
 api_key: ${env.QDRANT_API_KEY:=}
-kvstore:
+persistence:
-  type: sqlite
+  namespace: vector_io::qdrant_remote
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/qdrant_registry.db
+  backend: kv_default
 ```

docs/docs/providers/vector_io/remote_weaviate.mdx

@@ -75,14 +75,14 @@ See [Weaviate's documentation](https://weaviate.io/developers/weaviate) for more
 |-------|------|----------|---------|-------------|
 | `weaviate_api_key` | `str \| None` | No |  | The API key for the Weaviate instance |
 | `weaviate_cluster_url` | `str \| None` | No | localhost:8080 | The URL of the Weaviate cluster |
-| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig, annotation=NoneType, required=False, default='sqlite', discriminator='type'` | No |  | Config for KV store backend (SQLite only for now) |
+| `persistence` | `llama_stack.core.storage.datatypes.KVStoreReference \| None` | No |  | Config for KV store backend (SQLite only for now) |
 
 ## Sample Configuration
 
 ```yaml
 weaviate_api_key: null
 weaviate_cluster_url: ${env.WEAVIATE_CLUSTER_URL:=localhost:8080}
-kvstore:
+persistence:
-  type: sqlite
+  namespace: vector_io::weaviate
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/weaviate_registry.db
+  backend: kv_default
 ```

docs/notebooks/Alpha_Llama_Stack_Post_Training.ipynb

@@ -2864,7 +2864,7 @@
     }
    ],
    "source": [
-    "!llama stack build --distro experimental-post-training --image-type venv --image-name __system__"
+    "!llama stack list-deps experimental-post-training | xargs -L1 uv pip install"
    ]
   },
   {

docs/notebooks/Llama_Stack_Agent_Workflows.ipynb

@@ -38,7 +38,7 @@
    "source": [
     "# NBVAL_SKIP\n",
     "!pip install -U llama-stack\n",
-    "!UV_SYSTEM_PYTHON=1 llama stack build --distro fireworks --image-type venv"
+    "llama stack list-deps fireworks | xargs -L1 uv pip install\n"
    ]
   },
   {

docs/notebooks/crewai/Llama_Stack_CrewAI.ipynb

@@ -136,7 +136,8 @@
     "    \"\"\"Build and run LlamaStack server in one step using --run flag\"\"\"\n",
     "    log_file = open(\"llama_stack_server.log\", \"w\")\n",
     "    process = subprocess.Popen(\n",
-    "        \"uv run --with llama-stack llama stack build --distro starter --image-type venv --run\",\n",
+    "        \"uv run --with llama-stack llama stack list-deps starter | xargs -L1 uv pip install\",\n",
+    "        \"uv run --with llama-stack llama stack run starter\",\n",
     "        shell=True,\n",
     "        stdout=log_file,\n",
     "        stderr=log_file,\n",
@@ -172,7 +173,7 @@
     "\n",
     "def kill_llama_stack_server():\n",
     "    # Kill any existing llama stack server processes using pkill command\n",
-    "    os.system(\"pkill -f llama_stack.core.server.server\")"
+    "    os.system(\"pkill -f llama_stack.core.server.server\")\n"
    ]
   },
   {

docs/notebooks/langchain/Llama_Stack_LangChain.ipynb

@@ -105,7 +105,8 @@
     "    \"\"\"Build and run LlamaStack server in one step using --run flag\"\"\"\n",
     "    log_file = open(\"llama_stack_server.log\", \"w\")\n",
     "    process = subprocess.Popen(\n",
-    "        \"uv run --with llama-stack llama stack build --distro starter --image-type venv --run\",\n",
+    "        \"uv run --with llama-stack llama stack list-deps starter | xargs -L1 uv pip install\",\n",
+    "        \"uv run --with llama-stack llama stack run starter\",\n",
     "        shell=True,\n",
     "        stdout=log_file,\n",
     "        stderr=log_file,\n",

docs/notebooks/nvidia/beginner_e2e/Llama_Stack_NVIDIA_E2E_Flow.ipynb

@@ -92,7 +92,7 @@
    "metadata": {},
    "source": [
     "```bash\n",
-    "LLAMA_STACK_DIR=$(pwd) llama stack build --distro nvidia --image-type venv\n",
+    "uv run --with llama-stack llama stack list-deps nvidia | xargs -L1 uv pip install\n",
     "```"
    ]
   },

docs/notebooks/nvidia/tool_calling/1_data_preparation.ipynb

@@ -81,7 +81,7 @@
    "metadata": {},
    "source": [
     "```bash\n",
-    "LLAMA_STACK_DIR=$(pwd) llama stack build --distro nvidia --image-type venv\n",
+    "uv run --with llama-stack llama stack list-deps nvidia | xargs -L1 uv pip install\n",
     "```"
    ]
   },

docs/quick_start.ipynb

@@ -1,366 +1,366 @@
 {
-  "cells": [
+ "cells": [
-    {
+  {
-      "cell_type": "markdown",
+   "cell_type": "markdown",
-      "id": "c1e7571c",
+   "id": "c1e7571c",
-      "metadata": {
+   "metadata": {
-        "id": "c1e7571c"
+    "id": "c1e7571c"
-      },
+   },
-      "source": [
+   "source": [
-        "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb)\n",
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb)\n",
-        "\n",
+    "\n",
-        "# Llama Stack - Building AI Applications\n",
+    "# Llama Stack - Building AI Applications\n",
-        "\n",
+    "\n",
-        "<img src=\"https://llamastack.github.io/latest/_images/llama-stack.png\" alt=\"drawing\" width=\"500\"/>\n",
+    "<img src=\"https://llamastack.github.io/latest/_images/llama-stack.png\" alt=\"drawing\" width=\"500\"/>\n",
-        "\n",
+    "\n",
-        "Get started with Llama Stack in minutes!\n",
+    "Get started with Llama Stack in minutes!\n",
-        "\n",
+    "\n",
-        "[Llama Stack](https://github.com/meta-llama/llama-stack) is a stateful service with REST APIs to support the seamless transition of AI applications across different environments. You can build and test using a local server first and deploy to a hosted endpoint for production.\n",
+    "[Llama Stack](https://github.com/meta-llama/llama-stack) is a stateful service with REST APIs to support the seamless transition of AI applications across different environments. You can build and test using a local server first and deploy to a hosted endpoint for production.\n",
-        "\n",
+    "\n",
-        "In this guide, we'll walk through how to build a RAG application locally using Llama Stack with [Ollama](https://ollama.com/)\n",
+    "In this guide, we'll walk through how to build a RAG application locally using Llama Stack with [Ollama](https://ollama.com/)\n",
-        "as the inference [provider](docs/source/providers/index.md#inference) for a Llama Model.\n"
+    "as the inference [provider](docs/source/providers/index.md#inference) for a Llama Model.\n"
-      ]
+   ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "4CV1Q19BDMVw",
-      "metadata": {
-        "id": "4CV1Q19BDMVw"
-      },
-      "source": [
-        "## Step 1: Install and setup"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "K4AvfUAJZOeS",
-      "metadata": {
-        "id": "K4AvfUAJZOeS"
-      },
-      "source": [
-        "### 1.1. Install uv and test inference with Ollama\n",
-        "\n",
-        "We'll install [uv](https://docs.astral.sh/uv/) to setup the Python virtual environment, along with [colab-xterm](https://github.com/InfuseAI/colab-xterm) for running command-line tools, and [Ollama](https://ollama.com/download) as the inference provider."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "7a2d7b85",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "%pip install uv llama_stack llama-stack-client\n",
-        "\n",
-        "## If running on Collab:\n",
-        "# !pip install colab-xterm\n",
-        "# %load_ext colabxterm\n",
-        "\n",
-        "!curl https://ollama.ai/install.sh | sh"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "39fa584b",
-      "metadata": {},
-      "source": [
-        "### 1.2. Test inference with Ollama"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "3bf81522",
-      "metadata": {},
-      "source": [
-        "We’ll now launch a terminal and run inference on a Llama model with Ollama to verify that the model is working correctly."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "a7e8e0f1",
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "## If running on Colab:\n",
-        "# %xterm\n",
-        "\n",
-        "## To be ran in the terminal:\n",
-        "# ollama serve &\n",
-        "# ollama run llama3.2:3b --keepalive 60m"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "f3c5f243",
-      "metadata": {},
-      "source": [
-        "If successful, you should see the model respond to a prompt.\n",
-        "\n",
-        "...\n",
-        "```\n",
-        ">>> hi\n",
-        "Hello! How can I assist you today?\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "oDUB7M_qe-Gs",
-      "metadata": {
-        "id": "oDUB7M_qe-Gs"
-      },
-      "source": [
-        "## Step 2: Run the Llama Stack server\n",
-        "\n",
-        "In this showcase, we will start a Llama Stack server that is running locally."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "732eadc6",
-      "metadata": {},
-      "source": [
-        "### 2.1. Setup the Llama Stack Server"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "J2kGed0R5PSf",
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/"
-        },
-        "collapsed": true,
-        "id": "J2kGed0R5PSf",
-        "outputId": "2478ea60-8d35-48a1-b011-f233831740c5"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import subprocess\n",
-        "\n",
-        "if \"UV_SYSTEM_PYTHON\" in os.environ:\n",
-        "  del os.environ[\"UV_SYSTEM_PYTHON\"]\n",
-        "\n",
-        "# this command installs all the dependencies needed for the llama stack server with the ollama inference provider\n",
-        "!uv run --with llama-stack llama stack build --distro starter\n",
-        "\n",
-        "def run_llama_stack_server_background():\n",
-        "    log_file = open(\"llama_stack_server.log\", \"w\")\n",
-        "    process = subprocess.Popen(\n",
-        "        f\"OLLAMA_URL=http://localhost:11434 uv run --with llama-stack llama stack run starter\n",
-        "        shell=True,\n",
-        "        stdout=log_file,\n",
-        "        stderr=log_file,\n",
-        "        text=True\n",
-        "    )\n",
-        "\n",
-        "    print(f\"Starting Llama Stack server with PID: {process.pid}\")\n",
-        "    return process\n",
-        "\n",
-        "def wait_for_server_to_start():\n",
-        "    import requests\n",
-        "    from requests.exceptions import ConnectionError\n",
-        "    import time\n",
-        "\n",
-        "    url = \"http://0.0.0.0:8321/v1/health\"\n",
-        "    max_retries = 30\n",
-        "    retry_interval = 1\n",
-        "\n",
-        "    print(\"Waiting for server to start\", end=\"\")\n",
-        "    for _ in range(max_retries):\n",
-        "        try:\n",
-        "            response = requests.get(url)\n",
-        "            if response.status_code == 200:\n",
-        "                print(\"\\nServer is ready!\")\n",
-        "                return True\n",
-        "        except ConnectionError:\n",
-        "            print(\".\", end=\"\", flush=True)\n",
-        "            time.sleep(retry_interval)\n",
-        "\n",
-        "    print(\"\\nServer failed to start after\", max_retries * retry_interval, \"seconds\")\n",
-        "    return False\n",
-        "\n",
-        "\n",
-        "# use this helper if needed to kill the server\n",
-        "def kill_llama_stack_server():\n",
-        "    # Kill any existing llama stack server processes\n",
-        "    os.system(\"ps aux | grep -v grep | grep llama_stack.core.server.server | awk '{print $2}' | xargs kill -9\")\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "c40e9efd",
-      "metadata": {},
-      "source": [
-        "### 2.2. Start the Llama Stack Server"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 7,
-      "id": "f779283d",
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "Starting Llama Stack server with PID: 787100\n",
-            "Waiting for server to start\n",
-            "Server is ready!\n"
-          ]
-        }
-      ],
-      "source": [
-        "server_process = run_llama_stack_server_background()\n",
-        "assert wait_for_server_to_start()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "28477c03",
-      "metadata": {},
-      "source": [
-        "## Step 3: Run the demo"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 8,
-      "id": "7da71011",
-      "metadata": {},
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "rag_tool> Ingesting document: https://www.paulgraham.com/greatwork.html\n",
-            "prompt> How do you do great work?\n",
-            "\u001b[33minference> \u001b[0m\u001b[33m[k\u001b[0m\u001b[33mnowledge\u001b[0m\u001b[33m_search\u001b[0m\u001b[33m(query\u001b[0m\u001b[33m=\"\u001b[0m\u001b[33mWhat\u001b[0m\u001b[33m is\u001b[0m\u001b[33m the\u001b[0m\u001b[33m key\u001b[0m\u001b[33m to\u001b[0m\u001b[33m doing\u001b[0m\u001b[33m great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m\")]\u001b[0m\u001b[97m\u001b[0m\n",
-            "\u001b[32mtool_execution> Tool:knowledge_search Args:{'query': 'What is the key to doing great work'}\u001b[0m\n",
-            "\u001b[32mtool_execution> Tool:knowledge_search Response:[TextContentItem(text='knowledge_search tool found 5 chunks:\\nBEGIN of knowledge_search tool results.\\n', type='text'), TextContentItem(text=\"Result 1:\\nDocument_id:docum\\nContent:  work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 2:\\nDocument_id:docum\\nContent:  work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 3:\\nDocument_id:docum\\nContent:  work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 4:\\nDocument_id:docum\\nContent:  work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 5:\\nDocument_id:docum\\nContent:  work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text='END of knowledge_search tool results.\\n', type='text'), TextContentItem(text='The above results were retrieved to help answer the user\\'s query: \"What is the key to doing great work\". Use them as supporting information only in answering this query.\\n', type='text')]\u001b[0m\n",
-            "\u001b[33minference> \u001b[0m\u001b[33mDoing\u001b[0m\u001b[33m great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m means\u001b[0m\u001b[33m doing\u001b[0m\u001b[33m something\u001b[0m\u001b[33m important\u001b[0m\u001b[33m so\u001b[0m\u001b[33m well\u001b[0m\u001b[33m that\u001b[0m\u001b[33m you\u001b[0m\u001b[33m expand\u001b[0m\u001b[33m people\u001b[0m\u001b[33m's\u001b[0m\u001b[33m ideas\u001b[0m\u001b[33m of\u001b[0m\u001b[33m what\u001b[0m\u001b[33m's\u001b[0m\u001b[33m possible\u001b[0m\u001b[33m.\u001b[0m\u001b[33m However\u001b[0m\u001b[33m,\u001b[0m\u001b[33m there\u001b[0m\u001b[33m's\u001b[0m\u001b[33m no\u001b[0m\u001b[33m threshold\u001b[0m\u001b[33m for\u001b[0m\u001b[33m importance\u001b[0m\u001b[33m,\u001b[0m\u001b[33m and\u001b[0m\u001b[33m it\u001b[0m\u001b[33m's\u001b[0m\u001b[33m often\u001b[0m\u001b[33m hard\u001b[0m\u001b[33m to\u001b[0m\u001b[33m judge\u001b[0m\u001b[33m at\u001b[0m\u001b[33m the\u001b[0m\u001b[33m time\u001b[0m\u001b[33m anyway\u001b[0m\u001b[33m.\u001b[0m\u001b[33m Great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m is\u001b[0m\u001b[33m a\u001b[0m\u001b[33m matter\u001b[0m\u001b[33m of\u001b[0m\u001b[33m degree\u001b[0m\u001b[33m,\u001b[0m\u001b[33m and\u001b[0m\u001b[33m it\u001b[0m\u001b[33m can\u001b[0m\u001b[33m be\u001b[0m\u001b[33m difficult\u001b[0m\u001b[33m to\u001b[0m\u001b[33m determine\u001b[0m\u001b[33m whether\u001b[0m\u001b[33m someone\u001b[0m\u001b[33m has\u001b[0m\u001b[33m done\u001b[0m\u001b[33m great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m until\u001b[0m\u001b[33m after\u001b[0m\u001b[33m the\u001b[0m\u001b[33m fact\u001b[0m\u001b[33m.\u001b[0m\u001b[97m\u001b[0m\n",
-            "\u001b[30m\u001b[0m"
-          ]
-        }
-      ],
-      "source": [
-        "from llama_stack_client import Agent, AgentEventLogger, RAGDocument, LlamaStackClient\n",
-        "\n",
-        "vector_db_id = \"my_demo_vector_db\"\n",
-        "client = LlamaStackClient(base_url=\"http://0.0.0.0:8321\")\n",
-        "\n",
-        "models = client.models.list()\n",
-        "\n",
-        "# Select the first ollama and first ollama's embedding model\n",
-        "model_id = next(m for m in models if m.model_type == \"llm\" and m.provider_id == \"ollama\").identifier\n",
-        "embedding_model = next(m for m in models if m.model_type == \"embedding\" and m.provider_id == \"ollama\")\n",
-        "embedding_model_id = embedding_model.identifier\n",
-        "embedding_dimension = embedding_model.metadata[\"embedding_dimension\"]\n",
-        "\n",
-        "_ = client.vector_dbs.register(\n",
-        "    vector_db_id=vector_db_id,\n",
-        "    embedding_model=embedding_model_id,\n",
-        "    embedding_dimension=embedding_dimension,\n",
-        "    provider_id=\"faiss\",\n",
-        ")\n",
-        "source = \"https://www.paulgraham.com/greatwork.html\"\n",
-        "print(\"rag_tool> Ingesting document:\", source)\n",
-        "document = RAGDocument(\n",
-        "    document_id=\"document_1\",\n",
-        "    content=source,\n",
-        "    mime_type=\"text/html\",\n",
-        "    metadata={},\n",
-        ")\n",
-        "client.tool_runtime.rag_tool.insert(\n",
-        "    documents=[document],\n",
-        "    vector_db_id=vector_db_id,\n",
-        "    chunk_size_in_tokens=50,\n",
-        ")\n",
-        "agent = Agent(\n",
-        "    client,\n",
-        "    model=model_id,\n",
-        "    instructions=\"You are a helpful assistant\",\n",
-        "    tools=[\n",
-        "        {\n",
-        "            \"name\": \"builtin::rag/knowledge_search\",\n",
-        "            \"args\": {\"vector_db_ids\": [vector_db_id]},\n",
-        "        }\n",
-        "    ],\n",
-        ")\n",
-        "\n",
-        "prompt = \"How do you do great work?\"\n",
-        "print(\"prompt>\", prompt)\n",
-        "\n",
-        "response = agent.create_turn(\n",
-        "    messages=[{\"role\": \"user\", \"content\": prompt}],\n",
-        "    session_id=agent.create_session(\"rag_session\"),\n",
-        "    stream=True,\n",
-        ")\n",
-        "\n",
-        "for log in AgentEventLogger().log(response):\n",
-        "    log.print()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "341aaadf",
-      "metadata": {},
-      "source": [
-        "Congratulations! You've successfully built your first RAG application using Llama Stack! 🎉🥳"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "e88e1185",
-      "metadata": {},
-      "source": [
-        "## Next Steps"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "bcb73600",
-      "metadata": {},
-      "source": [
-        "Now you're ready to dive deeper into Llama Stack!\n",
-        "- Explore the [Detailed Tutorial](./detailed_tutorial.md).\n",
-        "- Try the [Getting Started Notebook](https://github.com/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb).\n",
-        "- Browse more [Notebooks on GitHub](https://github.com/meta-llama/llama-stack/tree/main/docs/notebooks).\n",
-        "- Learn about Llama Stack [Concepts](../concepts/index.md).\n",
-        "- Discover how to [Build Llama Stacks](../distributions/index.md).\n",
-        "- Refer to our [References](../references/index.md) for details on the Llama CLI and Python SDK.\n",
-        "- Check out the [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main/examples) repository for example applications and tutorials."
-      ]
-    }
-  ],
-  "metadata": {
-    "accelerator": "GPU",
-    "colab": {
-      "gpuType": "T4",
-      "provenance": []
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "language": "python",
-      "name": "python3"
-    },
-    "language_info": {
-      "codemirror_mode": {
-        "name": "ipython",
-        "version": 3
-      },
-      "file_extension": ".py",
-      "mimetype": "text/x-python",
-      "name": "python",
-      "nbconvert_exporter": "python",
-      "pygments_lexer": "ipython3",
-      "version": "3.10.6"
-    }
   },
-  "nbformat": 4,
+  {
-  "nbformat_minor": 5
+   "cell_type": "markdown",
+   "id": "4CV1Q19BDMVw",
+   "metadata": {
+    "id": "4CV1Q19BDMVw"
+   },
+   "source": [
+    "## Step 1: Install and setup"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "K4AvfUAJZOeS",
+   "metadata": {
+    "id": "K4AvfUAJZOeS"
+   },
+   "source": [
+    "### 1.1. Install uv and test inference with Ollama\n",
+    "\n",
+    "We'll install [uv](https://docs.astral.sh/uv/) to setup the Python virtual environment, along with [colab-xterm](https://github.com/InfuseAI/colab-xterm) for running command-line tools, and [Ollama](https://ollama.com/download) as the inference provider."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7a2d7b85",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install uv llama_stack llama-stack-client\n",
+    "\n",
+    "## If running on Collab:\n",
+    "# !pip install colab-xterm\n",
+    "# %load_ext colabxterm\n",
+    "\n",
+    "!curl https://ollama.ai/install.sh | sh"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "39fa584b",
+   "metadata": {},
+   "source": [
+    "### 1.2. Test inference with Ollama"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3bf81522",
+   "metadata": {},
+   "source": [
+    "We’ll now launch a terminal and run inference on a Llama model with Ollama to verify that the model is working correctly."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a7e8e0f1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## If running on Colab:\n",
+    "# %xterm\n",
+    "\n",
+    "## To be ran in the terminal:\n",
+    "# ollama serve &\n",
+    "# ollama run llama3.2:3b --keepalive 60m"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f3c5f243",
+   "metadata": {},
+   "source": [
+    "If successful, you should see the model respond to a prompt.\n",
+    "\n",
+    "...\n",
+    "```\n",
+    ">>> hi\n",
+    "Hello! How can I assist you today?\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "oDUB7M_qe-Gs",
+   "metadata": {
+    "id": "oDUB7M_qe-Gs"
+   },
+   "source": [
+    "## Step 2: Run the Llama Stack server\n",
+    "\n",
+    "In this showcase, we will start a Llama Stack server that is running locally."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "732eadc6",
+   "metadata": {},
+   "source": [
+    "### 2.1. Setup the Llama Stack Server"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "J2kGed0R5PSf",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "collapsed": true,
+    "id": "J2kGed0R5PSf",
+    "outputId": "2478ea60-8d35-48a1-b011-f233831740c5"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import subprocess\n",
+    "\n",
+    "if \"UV_SYSTEM_PYTHON\" in os.environ:\n",
+    "  del os.environ[\"UV_SYSTEM_PYTHON\"]\n",
+    "\n",
+    "# this command installs all the dependencies needed for the llama stack server with the ollama inference provider\n",
+    "!uv run --with llama-stack llama stack list-deps starter | xargs -L1 uv pip install\n",
+    "\n",
+    "def run_llama_stack_server_background():\n",
+    "    log_file = open(\"llama_stack_server.log\", \"w\")\n",
+    "    process = subprocess.Popen(\n",
+    "        f\"OLLAMA_URL=http://localhost:11434 uv run --with llama-stack llama stack run starter\n",
+    "        shell=True,\n",
+    "        stdout=log_file,\n",
+    "        stderr=log_file,\n",
+    "        text=True\n",
+    "    )\n",
+    "\n",
+    "    print(f\"Starting Llama Stack server with PID: {process.pid}\")\n",
+    "    return process\n",
+    "\n",
+    "def wait_for_server_to_start():\n",
+    "    import requests\n",
+    "    from requests.exceptions import ConnectionError\n",
+    "    import time\n",
+    "\n",
+    "    url = \"http://0.0.0.0:8321/v1/health\"\n",
+    "    max_retries = 30\n",
+    "    retry_interval = 1\n",
+    "\n",
+    "    print(\"Waiting for server to start\", end=\"\")\n",
+    "    for _ in range(max_retries):\n",
+    "        try:\n",
+    "            response = requests.get(url)\n",
+    "            if response.status_code == 200:\n",
+    "                print(\"\\nServer is ready!\")\n",
+    "                return True\n",
+    "        except ConnectionError:\n",
+    "            print(\".\", end=\"\", flush=True)\n",
+    "            time.sleep(retry_interval)\n",
+    "\n",
+    "    print(\"\\nServer failed to start after\", max_retries * retry_interval, \"seconds\")\n",
+    "    return False\n",
+    "\n",
+    "\n",
+    "# use this helper if needed to kill the server\n",
+    "def kill_llama_stack_server():\n",
+    "    # Kill any existing llama stack server processes\n",
+    "    os.system(\"ps aux | grep -v grep | grep llama_stack.core.server.server | awk '{print $2}' | xargs kill -9\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c40e9efd",
+   "metadata": {},
+   "source": [
+    "### 2.2. Start the Llama Stack Server"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "f779283d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Starting Llama Stack server with PID: 787100\n",
+      "Waiting for server to start\n",
+      "Server is ready!\n"
+     ]
+    }
+   ],
+   "source": [
+    "server_process = run_llama_stack_server_background()\n",
+    "assert wait_for_server_to_start()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "28477c03",
+   "metadata": {},
+   "source": [
+    "## Step 3: Run the demo"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "7da71011",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "rag_tool> Ingesting document: https://www.paulgraham.com/greatwork.html\n",
+      "prompt> How do you do great work?\n",
+      "\u001b[33minference> \u001b[0m\u001b[33m[k\u001b[0m\u001b[33mnowledge\u001b[0m\u001b[33m_search\u001b[0m\u001b[33m(query\u001b[0m\u001b[33m=\"\u001b[0m\u001b[33mWhat\u001b[0m\u001b[33m is\u001b[0m\u001b[33m the\u001b[0m\u001b[33m key\u001b[0m\u001b[33m to\u001b[0m\u001b[33m doing\u001b[0m\u001b[33m great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m\")]\u001b[0m\u001b[97m\u001b[0m\n",
+      "\u001b[32mtool_execution> Tool:knowledge_search Args:{'query': 'What is the key to doing great work'}\u001b[0m\n",
+      "\u001b[32mtool_execution> Tool:knowledge_search Response:[TextContentItem(text='knowledge_search tool found 5 chunks:\\nBEGIN of knowledge_search tool results.\\n', type='text'), TextContentItem(text=\"Result 1:\\nDocument_id:docum\\nContent:  work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 2:\\nDocument_id:docum\\nContent:  work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 3:\\nDocument_id:docum\\nContent:  work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 4:\\nDocument_id:docum\\nContent:  work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 5:\\nDocument_id:docum\\nContent:  work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text='END of knowledge_search tool results.\\n', type='text'), TextContentItem(text='The above results were retrieved to help answer the user\\'s query: \"What is the key to doing great work\". Use them as supporting information only in answering this query.\\n', type='text')]\u001b[0m\n",
+      "\u001b[33minference> \u001b[0m\u001b[33mDoing\u001b[0m\u001b[33m great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m means\u001b[0m\u001b[33m doing\u001b[0m\u001b[33m something\u001b[0m\u001b[33m important\u001b[0m\u001b[33m so\u001b[0m\u001b[33m well\u001b[0m\u001b[33m that\u001b[0m\u001b[33m you\u001b[0m\u001b[33m expand\u001b[0m\u001b[33m people\u001b[0m\u001b[33m's\u001b[0m\u001b[33m ideas\u001b[0m\u001b[33m of\u001b[0m\u001b[33m what\u001b[0m\u001b[33m's\u001b[0m\u001b[33m possible\u001b[0m\u001b[33m.\u001b[0m\u001b[33m However\u001b[0m\u001b[33m,\u001b[0m\u001b[33m there\u001b[0m\u001b[33m's\u001b[0m\u001b[33m no\u001b[0m\u001b[33m threshold\u001b[0m\u001b[33m for\u001b[0m\u001b[33m importance\u001b[0m\u001b[33m,\u001b[0m\u001b[33m and\u001b[0m\u001b[33m it\u001b[0m\u001b[33m's\u001b[0m\u001b[33m often\u001b[0m\u001b[33m hard\u001b[0m\u001b[33m to\u001b[0m\u001b[33m judge\u001b[0m\u001b[33m at\u001b[0m\u001b[33m the\u001b[0m\u001b[33m time\u001b[0m\u001b[33m anyway\u001b[0m\u001b[33m.\u001b[0m\u001b[33m Great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m is\u001b[0m\u001b[33m a\u001b[0m\u001b[33m matter\u001b[0m\u001b[33m of\u001b[0m\u001b[33m degree\u001b[0m\u001b[33m,\u001b[0m\u001b[33m and\u001b[0m\u001b[33m it\u001b[0m\u001b[33m can\u001b[0m\u001b[33m be\u001b[0m\u001b[33m difficult\u001b[0m\u001b[33m to\u001b[0m\u001b[33m determine\u001b[0m\u001b[33m whether\u001b[0m\u001b[33m someone\u001b[0m\u001b[33m has\u001b[0m\u001b[33m done\u001b[0m\u001b[33m great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m until\u001b[0m\u001b[33m after\u001b[0m\u001b[33m the\u001b[0m\u001b[33m fact\u001b[0m\u001b[33m.\u001b[0m\u001b[97m\u001b[0m\n",
+      "\u001b[30m\u001b[0m"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_stack_client import Agent, AgentEventLogger, RAGDocument, LlamaStackClient\n",
+    "\n",
+    "vector_db_id = \"my_demo_vector_db\"\n",
+    "client = LlamaStackClient(base_url=\"http://0.0.0.0:8321\")\n",
+    "\n",
+    "models = client.models.list()\n",
+    "\n",
+    "# Select the first ollama and first ollama's embedding model\n",
+    "model_id = next(m for m in models if m.model_type == \"llm\" and m.provider_id == \"ollama\").identifier\n",
+    "embedding_model = next(m for m in models if m.model_type == \"embedding\" and m.provider_id == \"ollama\")\n",
+    "embedding_model_id = embedding_model.identifier\n",
+    "embedding_dimension = embedding_model.metadata[\"embedding_dimension\"]\n",
+    "\n",
+    "_ = client.vector_dbs.register(\n",
+    "    vector_db_id=vector_db_id,\n",
+    "    embedding_model=embedding_model_id,\n",
+    "    embedding_dimension=embedding_dimension,\n",
+    "    provider_id=\"faiss\",\n",
+    ")\n",
+    "source = \"https://www.paulgraham.com/greatwork.html\"\n",
+    "print(\"rag_tool> Ingesting document:\", source)\n",
+    "document = RAGDocument(\n",
+    "    document_id=\"document_1\",\n",
+    "    content=source,\n",
+    "    mime_type=\"text/html\",\n",
+    "    metadata={},\n",
+    ")\n",
+    "client.tool_runtime.rag_tool.insert(\n",
+    "    documents=[document],\n",
+    "    vector_db_id=vector_db_id,\n",
+    "    chunk_size_in_tokens=50,\n",
+    ")\n",
+    "agent = Agent(\n",
+    "    client,\n",
+    "    model=model_id,\n",
+    "    instructions=\"You are a helpful assistant\",\n",
+    "    tools=[\n",
+    "        {\n",
+    "            \"name\": \"builtin::rag/knowledge_search\",\n",
+    "            \"args\": {\"vector_db_ids\": [vector_db_id]},\n",
+    "        }\n",
+    "    ],\n",
+    ")\n",
+    "\n",
+    "prompt = \"How do you do great work?\"\n",
+    "print(\"prompt>\", prompt)\n",
+    "\n",
+    "response = agent.create_turn(\n",
+    "    messages=[{\"role\": \"user\", \"content\": prompt}],\n",
+    "    session_id=agent.create_session(\"rag_session\"),\n",
+    "    stream=True,\n",
+    ")\n",
+    "\n",
+    "for log in AgentEventLogger().log(response):\n",
+    "    log.print()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "341aaadf",
+   "metadata": {},
+   "source": [
+    "Congratulations! You've successfully built your first RAG application using Llama Stack! 🎉🥳"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e88e1185",
+   "metadata": {},
+   "source": [
+    "## Next Steps"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bcb73600",
+   "metadata": {},
+   "source": [
+    "Now you're ready to dive deeper into Llama Stack!\n",
+    "- Explore the [Detailed Tutorial](./detailed_tutorial.md).\n",
+    "- Try the [Getting Started Notebook](https://github.com/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb).\n",
+    "- Browse more [Notebooks on GitHub](https://github.com/meta-llama/llama-stack/tree/main/docs/notebooks).\n",
+    "- Learn about Llama Stack [Concepts](../concepts/index.md).\n",
+    "- Discover how to [Build Llama Stacks](../distributions/index.md).\n",
+    "- Refer to our [References](../references/index.md) for details on the Llama CLI and Python SDK.\n",
+    "- Check out the [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main/examples) repository for example applications and tutorials."
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "gpuType": "T4",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
 }

docs/src/pages/index.js

@@ -47,11 +47,11 @@ function QuickStart() {
               <pre><code>{`# Install uv and start Ollama
 ollama run llama3.2:3b --keepalive 60m
 
+# Install server dependencies
+uv run --with llama-stack llama stack list-deps starter | xargs -L1 uv pip install
+
 # Run Llama Stack server
-OLLAMA_URL=http://localhost:11434 \\
+OLLAMA_URL=http://localhost:11434 uv run --with llama-stack llama stack run starter
-  uv run --with llama-stack \\
-  llama stack build --distro starter \\
-  --image-type venv --run
 
 # Try the Python SDK
 from llama_stack_client import LlamaStackClient

docs/static/deprecated-llama-stack-spec.html

@@ -9024,6 +9024,10 @@
                         "$ref": "#/components/schemas/OpenAIResponseUsage",
                         "description": "(Optional) Token usage information for the response"
                     },
+                    "instructions": {
+                        "type": "string",
+                        "description": "(Optional) System message inserted into the model's context"
+                    },
                     "input": {
                         "type": "array",
                         "items": {
@@ -9901,6 +9905,10 @@
                     "usage": {
                         "$ref": "#/components/schemas/OpenAIResponseUsage",
                         "description": "(Optional) Token usage information for the response"
+                    },
+                    "instructions": {
+                        "type": "string",
+                        "description": "(Optional) System message inserted into the model's context"
                     }
                 },
                 "additionalProperties": false,
@@ -13449,8 +13457,8 @@
         },
         {
             "name": "Eval",
-            "description": "",
+            "description": "Llama Stack Evaluation API for running evaluations on model and agent candidates.",
-            "x-displayName": "Llama Stack Evaluation API for running evaluations on model and agent candidates."
+            "x-displayName": "Evaluations"
         },
         {
             "name": "Files",

docs/static/deprecated-llama-stack-spec.yaml

@@ -6734,6 +6734,10 @@ components:
           $ref: '#/components/schemas/OpenAIResponseUsage'
           description: >-
             (Optional) Token usage information for the response
+        instructions:
+          type: string
+          description: >-
+            (Optional) System message inserted into the model's context
         input:
           type: array
           items:
@@ -7403,6 +7407,10 @@ components:
           $ref: '#/components/schemas/OpenAIResponseUsage'
           description: >-
             (Optional) Token usage information for the response
+        instructions:
+          type: string
+          description: >-
+            (Optional) System message inserted into the model's context
       additionalProperties: false
       required:
         - created_at
@@ -10196,9 +10204,9 @@ tags:
   - name: Datasets
     description: ''
   - name: Eval
-    description: ''
+    description: >-
-    x-displayName: >-
       Llama Stack Evaluation API for running evaluations on model and agent candidates.
+    x-displayName: Evaluations
   - name: Files
     description: >-
       This API is used to upload documents that can be used with other Llama Stack

docs/static/experimental-llama-stack-spec.html

@@ -5518,8 +5518,8 @@
         },
         {
             "name": "Eval",
-            "description": "",
+            "description": "Llama Stack Evaluation API for running evaluations on model and agent candidates.",
-            "x-displayName": "Llama Stack Evaluation API for running evaluations on model and agent candidates."
+            "x-displayName": "Evaluations"
         },
         {
             "name": "PostTraining (Coming Soon)",

docs/static/experimental-llama-stack-spec.yaml

@@ -4119,9 +4119,9 @@ tags:
   - name: Datasets
     description: ''
   - name: Eval
-    description: ''
+    description: >-
-    x-displayName: >-
       Llama Stack Evaluation API for running evaluations on model and agent candidates.
+    x-displayName: Evaluations
   - name: PostTraining (Coming Soon)
     description: ''
 x-tagGroups:

docs/static/llama-stack-spec.html

@@ -282,7 +282,7 @@
                     "Conversations"
                 ],
                 "summary": "Create a conversation.",
-                "description": "Create a conversation.",
+                "description": "Create a conversation.\nCreate a conversation.",
                 "parameters": [],
                 "requestBody": {
                     "content": {
@@ -326,8 +326,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "Get a conversation with the given ID.",
+                "summary": "Retrieve a conversation.",
-                "description": "Get a conversation with the given ID.",
+                "description": "Retrieve a conversation.\nGet a conversation with the given ID.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -369,8 +369,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "Update a conversation's metadata with the given ID.",
+                "summary": "Update a conversation.",
-                "description": "Update a conversation's metadata with the given ID.",
+                "description": "Update a conversation.\nUpdate a conversation's metadata with the given ID.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -422,8 +422,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "Delete a conversation with the given ID.",
+                "summary": "Delete a conversation.",
-                "description": "Delete a conversation with the given ID.",
+                "description": "Delete a conversation.\nDelete a conversation with the given ID.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -467,8 +467,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "List items in the conversation.",
+                "summary": "List items.",
-                "description": "List items in the conversation.",
+                "description": "List items.\nList items in the conversation.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -597,8 +597,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "Create items in the conversation.",
+                "summary": "Create items.",
-                "description": "Create items in the conversation.",
+                "description": "Create items.\nCreate items in the conversation.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -652,8 +652,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "Retrieve a conversation item.",
+                "summary": "Retrieve an item.",
-                "description": "Retrieve a conversation item.",
+                "description": "Retrieve an item.\nRetrieve a conversation item.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -704,8 +704,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "Delete a conversation item.",
+                "summary": "Delete an item.",
-                "description": "Delete a conversation item.",
+                "description": "Delete an item.\nDelete a conversation item.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -7600,6 +7600,10 @@
                         "$ref": "#/components/schemas/OpenAIResponseUsage",
                         "description": "(Optional) Token usage information for the response"
                     },
+                    "instructions": {
+                        "type": "string",
+                        "description": "(Optional) System message inserted into the model's context"
+                    },
                     "input": {
                         "type": "array",
                         "items": {
@@ -8148,6 +8152,10 @@
                     "usage": {
                         "$ref": "#/components/schemas/OpenAIResponseUsage",
                         "description": "(Optional) Token usage information for the response"
+                    },
+                    "instructions": {
+                        "type": "string",
+                        "description": "(Optional) System message inserted into the model's context"
                     }
                 },
                 "additionalProperties": false,
@@ -13251,8 +13259,8 @@
         },
         {
             "name": "Conversations",
-            "description": "",
+            "description": "Protocol for conversation management operations.",
-            "x-displayName": "Protocol for conversation management operations."
+            "x-displayName": "Conversations"
         },
         {
             "name": "Files",

docs/static/llama-stack-spec.yaml

@@ -192,7 +192,10 @@ paths:
       tags:
         - Conversations
       summary: Create a conversation.
-      description: Create a conversation.
+      description: >-
+        Create a conversation.
+
+        Create a conversation.
       parameters: []
       requestBody:
         content:
@@ -222,8 +225,11 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: Get a conversation with the given ID.
+      summary: Retrieve a conversation.
-      description: Get a conversation with the given ID.
+      description: >-
+        Retrieve a conversation.
+
+        Get a conversation with the given ID.
       parameters:
         - name: conversation_id
           in: path
@@ -252,9 +258,10 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: >-
+      summary: Update a conversation.
-        Update a conversation's metadata with the given ID.
       description: >-
+        Update a conversation.
+
         Update a conversation's metadata with the given ID.
       parameters:
         - name: conversation_id
@@ -290,8 +297,11 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: Delete a conversation with the given ID.
+      summary: Delete a conversation.
-      description: Delete a conversation with the given ID.
+      description: >-
+        Delete a conversation.
+
+        Delete a conversation with the given ID.
       parameters:
         - name: conversation_id
           in: path
@@ -321,8 +331,11 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: List items in the conversation.
+      summary: List items.
-      description: List items in the conversation.
+      description: >-
+        List items.
+
+        List items in the conversation.
       parameters:
         - name: conversation_id
           in: path
@@ -495,8 +508,11 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: Create items in the conversation.
+      summary: Create items.
-      description: Create items in the conversation.
+      description: >-
+        Create items.
+
+        Create items in the conversation.
       parameters:
         - name: conversation_id
           in: path
@@ -532,8 +548,11 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: Retrieve a conversation item.
+      summary: Retrieve an item.
-      description: Retrieve a conversation item.
+      description: >-
+        Retrieve an item.
+
+        Retrieve a conversation item.
       parameters:
         - name: conversation_id
           in: path
@@ -568,8 +587,11 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: Delete a conversation item.
+      summary: Delete an item.
-      description: Delete a conversation item.
+      description: >-
+        Delete an item.
+
+        Delete a conversation item.
       parameters:
         - name: conversation_id
           in: path
@@ -5793,6 +5815,10 @@ components:
           $ref: '#/components/schemas/OpenAIResponseUsage'
           description: >-
             (Optional) Token usage information for the response
+        instructions:
+          type: string
+          description: >-
+            (Optional) System message inserted into the model's context
         input:
           type: array
           items:
@@ -6196,6 +6222,10 @@ components:
           $ref: '#/components/schemas/OpenAIResponseUsage'
           description: >-
             (Optional) Token usage information for the response
+        instructions:
+          type: string
+          description: >-
+            (Optional) System message inserted into the model's context
       additionalProperties: false
       required:
         - created_at
@@ -10146,9 +10176,9 @@ tags:
       - `background`
     x-displayName: Agents
   - name: Conversations
-    description: ''
+    description: >-
-    x-displayName: >-
       Protocol for conversation management operations.
+    x-displayName: Conversations
   - name: Files
     description: >-
       This API is used to upload documents that can be used with other Llama Stack

docs/static/stainless-llama-stack-spec.html

@@ -282,7 +282,7 @@
                     "Conversations"
                 ],
                 "summary": "Create a conversation.",
-                "description": "Create a conversation.",
+                "description": "Create a conversation.\nCreate a conversation.",
                 "parameters": [],
                 "requestBody": {
                     "content": {
@@ -326,8 +326,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "Get a conversation with the given ID.",
+                "summary": "Retrieve a conversation.",
-                "description": "Get a conversation with the given ID.",
+                "description": "Retrieve a conversation.\nGet a conversation with the given ID.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -369,8 +369,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "Update a conversation's metadata with the given ID.",
+                "summary": "Update a conversation.",
-                "description": "Update a conversation's metadata with the given ID.",
+                "description": "Update a conversation.\nUpdate a conversation's metadata with the given ID.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -422,8 +422,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "Delete a conversation with the given ID.",
+                "summary": "Delete a conversation.",
-                "description": "Delete a conversation with the given ID.",
+                "description": "Delete a conversation.\nDelete a conversation with the given ID.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -467,8 +467,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "List items in the conversation.",
+                "summary": "List items.",
-                "description": "List items in the conversation.",
+                "description": "List items.\nList items in the conversation.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -597,8 +597,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "Create items in the conversation.",
+                "summary": "Create items.",
-                "description": "Create items in the conversation.",
+                "description": "Create items.\nCreate items in the conversation.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -652,8 +652,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "Retrieve a conversation item.",
+                "summary": "Retrieve an item.",
-                "description": "Retrieve a conversation item.",
+                "description": "Retrieve an item.\nRetrieve a conversation item.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -704,8 +704,8 @@
                 "tags": [
                     "Conversations"
                 ],
-                "summary": "Delete a conversation item.",
+                "summary": "Delete an item.",
-                "description": "Delete a conversation item.",
+                "description": "Delete an item.\nDelete a conversation item.",
                 "parameters": [
                     {
                         "name": "conversation_id",
@@ -9272,6 +9272,10 @@
                         "$ref": "#/components/schemas/OpenAIResponseUsage",
                         "description": "(Optional) Token usage information for the response"
                     },
+                    "instructions": {
+                        "type": "string",
+                        "description": "(Optional) System message inserted into the model's context"
+                    },
                     "input": {
                         "type": "array",
                         "items": {
@@ -9820,6 +9824,10 @@
                     "usage": {
                         "$ref": "#/components/schemas/OpenAIResponseUsage",
                         "description": "(Optional) Token usage information for the response"
+                    },
+                    "instructions": {
+                        "type": "string",
+                        "description": "(Optional) System message inserted into the model's context"
                     }
                 },
                 "additionalProperties": false,
@@ -17928,8 +17936,8 @@
         },
         {
             "name": "Conversations",
-            "description": "",
+            "description": "Protocol for conversation management operations.",
-            "x-displayName": "Protocol for conversation management operations."
+            "x-displayName": "Conversations"
         },
         {
             "name": "DatasetIO",
@@ -17941,8 +17949,8 @@
         },
         {
             "name": "Eval",
-            "description": "",
+            "description": "Llama Stack Evaluation API for running evaluations on model and agent candidates.",
-            "x-displayName": "Llama Stack Evaluation API for running evaluations on model and agent candidates."
+            "x-displayName": "Evaluations"
         },
         {
             "name": "Files",

docs/static/stainless-llama-stack-spec.yaml

@@ -195,7 +195,10 @@ paths:
       tags:
         - Conversations
       summary: Create a conversation.
-      description: Create a conversation.
+      description: >-
+        Create a conversation.
+
+        Create a conversation.
       parameters: []
       requestBody:
         content:
@@ -225,8 +228,11 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: Get a conversation with the given ID.
+      summary: Retrieve a conversation.
-      description: Get a conversation with the given ID.
+      description: >-
+        Retrieve a conversation.
+
+        Get a conversation with the given ID.
       parameters:
         - name: conversation_id
           in: path
@@ -255,9 +261,10 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: >-
+      summary: Update a conversation.
-        Update a conversation's metadata with the given ID.
       description: >-
+        Update a conversation.
+
         Update a conversation's metadata with the given ID.
       parameters:
         - name: conversation_id
@@ -293,8 +300,11 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: Delete a conversation with the given ID.
+      summary: Delete a conversation.
-      description: Delete a conversation with the given ID.
+      description: >-
+        Delete a conversation.
+
+        Delete a conversation with the given ID.
       parameters:
         - name: conversation_id
           in: path
@@ -324,8 +334,11 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: List items in the conversation.
+      summary: List items.
-      description: List items in the conversation.
+      description: >-
+        List items.
+
+        List items in the conversation.
       parameters:
         - name: conversation_id
           in: path
@@ -498,8 +511,11 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: Create items in the conversation.
+      summary: Create items.
-      description: Create items in the conversation.
+      description: >-
+        Create items.
+
+        Create items in the conversation.
       parameters:
         - name: conversation_id
           in: path
@@ -535,8 +551,11 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: Retrieve a conversation item.
+      summary: Retrieve an item.
-      description: Retrieve a conversation item.
+      description: >-
+        Retrieve an item.
+
+        Retrieve a conversation item.
       parameters:
         - name: conversation_id
           in: path
@@ -571,8 +590,11 @@ paths:
           $ref: '#/components/responses/DefaultError'
       tags:
         - Conversations
-      summary: Delete a conversation item.
+      summary: Delete an item.
-      description: Delete a conversation item.
+      description: >-
+        Delete an item.
+
+        Delete a conversation item.
       parameters:
         - name: conversation_id
           in: path
@@ -7006,6 +7028,10 @@ components:
           $ref: '#/components/schemas/OpenAIResponseUsage'
           description: >-
             (Optional) Token usage information for the response
+        instructions:
+          type: string
+          description: >-
+            (Optional) System message inserted into the model's context
         input:
           type: array
           items:
@@ -7409,6 +7435,10 @@ components:
           $ref: '#/components/schemas/OpenAIResponseUsage'
           description: >-
             (Optional) Token usage information for the response
+        instructions:
+          type: string
+          description: >-
+            (Optional) System message inserted into the model's context
       additionalProperties: false
       required:
         - created_at
@@ -13533,17 +13563,17 @@ tags:
   - name: Benchmarks
     description: ''
   - name: Conversations
-    description: ''
+    description: >-
-    x-displayName: >-
       Protocol for conversation management operations.
+    x-displayName: Conversations
   - name: DatasetIO
     description: ''
   - name: Datasets
     description: ''
   - name: Eval
-    description: ''
+    description: >-
-    x-displayName: >-
       Llama Stack Evaluation API for running evaluations on model and agent candidates.
+    x-displayName: Evaluations
   - name: Files
     description: >-
       This API is used to upload documents that can be used with other Llama Stack

docs/zero_to_hero_guide/README.md

@@ -78,17 +78,14 @@ If you're looking for more specific topics, we have a [Zero to Hero Guide](#next
 
 ## Build, Configure, and Run Llama Stack
 
-1. **Build the Llama Stack**:
+1. **Install dependencies**:
-   Build the Llama Stack using the `starter` template:
    ```bash
-   uv run --with llama-stack llama stack build --distro starter --image-type venv
+   llama stack list-deps starter | xargs -L1 uv pip install
    ```
-   **Expected Output:**
+
+2. **Start the distribution**:
    ```bash
-   ...
+   llama stack run starter
-   Build Successful!
-   You can find the newly-built template here: ~/.llama/distributions/starter/starter-run.yaml
-   You can run the new Llama Stack Distro via: uv run --with llama-stack llama stack run starter
    ```
 
 3. **Set the ENV variables by exporting them to the terminal**:

llama_stack/apis/agents/openai_responses.py

@@ -545,6 +545,7 @@ class OpenAIResponseObject(BaseModel):
     :param tools: (Optional) An array of tools the model may call while generating a response.
     :param truncation: (Optional) Truncation strategy applied to the response
     :param usage: (Optional) Token usage information for the response
+    :param instructions: (Optional) System message inserted into the model's context
     """
 
     created_at: int
@@ -564,6 +565,7 @@ class OpenAIResponseObject(BaseModel):
     tools: list[OpenAIResponseTool] | None = None
     truncation: str | None = None
     usage: OpenAIResponseUsage | None = None
+    instructions: str | None = None
 
 
 @json_schema_type

llama_stack/apis/conversations/conversations.py

@@ -173,7 +173,9 @@ class ConversationItemDeletedResource(BaseModel):
 @runtime_checkable
 @trace_protocol
 class Conversations(Protocol):
-    """Protocol for conversation management operations."""
+    """Conversations
+
+    Protocol for conversation management operations."""
 
     @webmethod(route="/conversations", method="POST", level=LLAMA_STACK_API_V1)
     async def create_conversation(
@@ -181,6 +183,8 @@ class Conversations(Protocol):
     ) -> Conversation:
         """Create a conversation.
 
+        Create a conversation.
+
         :param items: Initial items to include in the conversation context.
         :param metadata: Set of key-value pairs that can be attached to an object.
         :returns: The created conversation object.
@@ -189,7 +193,9 @@ class Conversations(Protocol):
 
     @webmethod(route="/conversations/{conversation_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def get_conversation(self, conversation_id: str) -> Conversation:
-        """Get a conversation with the given ID.
+        """Retrieve a conversation.
+
+        Get a conversation with the given ID.
 
         :param conversation_id: The conversation identifier.
         :returns: The conversation object.
@@ -198,7 +204,9 @@ class Conversations(Protocol):
 
     @webmethod(route="/conversations/{conversation_id}", method="POST", level=LLAMA_STACK_API_V1)
     async def update_conversation(self, conversation_id: str, metadata: Metadata) -> Conversation:
-        """Update a conversation's metadata with the given ID.
+        """Update a conversation.
+
+        Update a conversation's metadata with the given ID.
 
         :param conversation_id: The conversation identifier.
         :param metadata: Set of key-value pairs that can be attached to an object.
@@ -208,7 +216,9 @@ class Conversations(Protocol):
 
     @webmethod(route="/conversations/{conversation_id}", method="DELETE", level=LLAMA_STACK_API_V1)
     async def openai_delete_conversation(self, conversation_id: str) -> ConversationDeletedResource:
-        """Delete a conversation with the given ID.
+        """Delete a conversation.
+
+        Delete a conversation with the given ID.
 
         :param conversation_id: The conversation identifier.
         :returns: The deleted conversation resource.
@@ -217,7 +227,9 @@ class Conversations(Protocol):
 
     @webmethod(route="/conversations/{conversation_id}/items", method="POST", level=LLAMA_STACK_API_V1)
     async def add_items(self, conversation_id: str, items: list[ConversationItem]) -> ConversationItemList:
-        """Create items in the conversation.
+        """Create items.
+
+        Create items in the conversation.
 
         :param conversation_id: The conversation identifier.
         :param items: Items to include in the conversation context.
@@ -227,7 +239,9 @@ class Conversations(Protocol):
 
     @webmethod(route="/conversations/{conversation_id}/items/{item_id}", method="GET", level=LLAMA_STACK_API_V1)
     async def retrieve(self, conversation_id: str, item_id: str) -> ConversationItem:
-        """Retrieve a conversation item.
+        """Retrieve an item.
+
+        Retrieve a conversation item.
 
         :param conversation_id: The conversation identifier.
         :param item_id: The item identifier.
@@ -244,7 +258,9 @@ class Conversations(Protocol):
         limit: int | NotGiven = NOT_GIVEN,
         order: Literal["asc", "desc"] | NotGiven = NOT_GIVEN,
     ) -> ConversationItemList:
-        """List items in the conversation.
+        """List items.
+
+        List items in the conversation.
 
         :param conversation_id: The conversation identifier.
         :param after: An item ID to list items after, used in pagination.
@@ -259,7 +275,9 @@ class Conversations(Protocol):
     async def openai_delete_conversation_item(
         self, conversation_id: str, item_id: str
     ) -> ConversationItemDeletedResource:
-        """Delete a conversation item.
+        """Delete an item.
+
+        Delete a conversation item.
 
         :param conversation_id: The conversation identifier.
         :param item_id: The item identifier.

llama_stack/apis/eval/eval.py

@@ -82,7 +82,9 @@ class EvaluateResponse(BaseModel):
 
 
 class Eval(Protocol):
-    """Llama Stack Evaluation API for running evaluations on model and agent candidates."""
+    """Evaluations
+
+    Llama Stack Evaluation API for running evaluations on model and agent candidates."""
 
     @webmethod(route="/eval/benchmarks/{benchmark_id}/jobs", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
     @webmethod(route="/eval/benchmarks/{benchmark_id}/jobs", method="POST", level=LLAMA_STACK_API_V1ALPHA)

llama_stack/cli/stack/_build.py

@@ -40,12 +40,20 @@ from llama_stack.core.distribution import get_provider_registry
 from llama_stack.core.external import load_external_apis
 from llama_stack.core.resolver import InvalidProviderError
 from llama_stack.core.stack import replace_env_vars
+from llama_stack.core.storage.datatypes import (
+    InferenceStoreReference,
+    KVStoreReference,
+    ServerStoresConfig,
+    SqliteKVStoreConfig,
+    SqliteSqlStoreConfig,
+    SqlStoreReference,
+    StorageConfig,
+)
 from llama_stack.core.utils.config_dirs import DISTRIBS_BASE_DIR, EXTERNAL_PROVIDERS_DIR
 from llama_stack.core.utils.dynamic import instantiate_class_type
 from llama_stack.core.utils.exec import formulate_run_args, run_command
 from llama_stack.core.utils.image_types import LlamaStackImageType
 from llama_stack.providers.datatypes import Api
-from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
 
 DISTRIBS_PATH = Path(__file__).parent.parent.parent / "distributions"
 
@@ -286,21 +294,42 @@ def _generate_run_config(
     Generate a run.yaml template file for user to edit from a build.yaml file
     """
     apis = list(build_config.distribution_spec.providers.keys())
+    distro_dir = DISTRIBS_BASE_DIR / image_name
+    storage = StorageConfig(
+        backends={
+            "kv_default": SqliteKVStoreConfig(
+                db_path=f"${{env.SQLITE_STORE_DIR:={distro_dir}}}/kvstore.db",
+            ),
+            "sql_default": SqliteSqlStoreConfig(
+                db_path=f"${{env.SQLITE_STORE_DIR:={distro_dir}}}/sql_store.db",
+            ),
+        },
+        stores=ServerStoresConfig(
+            metadata=KVStoreReference(
+                backend="kv_default",
+                namespace="registry",
+            ),
+            inference=InferenceStoreReference(
+                backend="sql_default",
+                table_name="inference_store",
+            ),
+            conversations=SqlStoreReference(
+                backend="sql_default",
+                table_name="openai_conversations",
+            ),
+        ),
+    )
+
     run_config = StackRunConfig(
         container_image=(image_name if build_config.image_type == LlamaStackImageType.CONTAINER.value else None),
         image_name=image_name,
         apis=apis,
         providers={},
+        storage=storage,
         external_providers_dir=build_config.external_providers_dir
         if build_config.external_providers_dir
         else EXTERNAL_PROVIDERS_DIR,
     )
-    if not run_config.inference_store:
-        run_config.inference_store = SqliteSqlStoreConfig(
-            **SqliteSqlStoreConfig.sample_run_config(
-                __distro_dir__=(DISTRIBS_BASE_DIR / image_name).as_posix(), db_name="inference_store.db"
-            )
-        )
     # build providers dict
     provider_registry = get_provider_registry(build_config)
     for api in apis:

llama_stack/cli/stack/_list_deps.py

@@ -0,0 +1,182 @@
+# 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.
+
+import argparse
+import sys
+from pathlib import Path
+
+import yaml
+from termcolor import cprint
+
+from llama_stack.cli.stack.utils import ImageType
+from llama_stack.core.build import get_provider_dependencies
+from llama_stack.core.datatypes import (
+    BuildConfig,
+    BuildProvider,
+    DistributionSpec,
+)
+from llama_stack.core.distribution import get_provider_registry
+from llama_stack.core.stack import replace_env_vars
+from llama_stack.log import get_logger
+from llama_stack.providers.datatypes import Api
+
+TEMPLATES_PATH = Path(__file__).parent.parent.parent / "templates"
+
+logger = get_logger(name=__name__, category="cli")
+
+
+# These are the dependencies needed by the distribution server.
+# `llama-stack` is automatically installed by the installation script.
+SERVER_DEPENDENCIES = [
+    "aiosqlite",
+    "fastapi",
+    "fire",
+    "httpx",
+    "uvicorn",
+    "opentelemetry-sdk",
+    "opentelemetry-exporter-otlp-proto-http",
+]
+
+
+def format_output_deps_only(
+    normal_deps: list[str],
+    special_deps: list[str],
+    external_deps: list[str],
+    uv: bool = False,
+) -> str:
+    """Format dependencies as a list."""
+    lines = []
+
+    uv_str = ""
+    if uv:
+        uv_str = "uv pip install "
+
+    # Quote deps with commas
+    quoted_normal_deps = [quote_if_needed(dep) for dep in normal_deps]
+    lines.append(f"{uv_str}{' '.join(quoted_normal_deps)}")
+
+    for special_dep in special_deps:
+        lines.append(f"{uv_str}{quote_special_dep(special_dep)}")
+
+    for external_dep in external_deps:
+        lines.append(f"{uv_str}{quote_special_dep(external_dep)}")
+
+    return "\n".join(lines)
+
+
+def run_stack_list_deps_command(args: argparse.Namespace) -> None:
+    if args.config:
+        try:
+            from llama_stack.core.utils.config_resolution import Mode, resolve_config_or_distro
+
+            config_file = resolve_config_or_distro(args.config, Mode.BUILD)
+        except ValueError as e:
+            cprint(
+                f"Could not parse config file {args.config}: {e}",
+                color="red",
+                file=sys.stderr,
+            )
+            sys.exit(1)
+        if config_file:
+            with open(config_file) as f:
+                try:
+                    contents = yaml.safe_load(f)
+                    contents = replace_env_vars(contents)
+                    build_config = BuildConfig(**contents)
+                    build_config.image_type = "venv"
+                except Exception as e:
+                    cprint(
+                        f"Could not parse config file {config_file}: {e}",
+                        color="red",
+                        file=sys.stderr,
+                    )
+                    sys.exit(1)
+    elif args.providers:
+        provider_list: dict[str, list[BuildProvider]] = dict()
+        for api_provider in args.providers.split(","):
+            if "=" not in api_provider:
+                cprint(
+                    "Could not parse `--providers`. Please ensure the list is in the format api1=provider1,api2=provider2",
+                    color="red",
+                    file=sys.stderr,
+                )
+                sys.exit(1)
+            api, provider_type = api_provider.split("=")
+            providers_for_api = get_provider_registry().get(Api(api), None)
+            if providers_for_api is None:
+                cprint(
+                    f"{api} is not a valid API.",
+                    color="red",
+                    file=sys.stderr,
+                )
+                sys.exit(1)
+            if provider_type in providers_for_api:
+                provider = BuildProvider(
+                    provider_type=provider_type,
+                    module=None,
+                )
+                provider_list.setdefault(api, []).append(provider)
+            else:
+                cprint(
+                    f"{provider_type} is not a valid provider for the {api} API.",
+                    color="red",
+                    file=sys.stderr,
+                )
+                sys.exit(1)
+        distribution_spec = DistributionSpec(
+            providers=provider_list,
+            description=",".join(args.providers),
+        )
+        build_config = BuildConfig(image_type=ImageType.VENV.value, distribution_spec=distribution_spec)
+
+    normal_deps, special_deps, external_provider_dependencies = get_provider_dependencies(build_config)
+    normal_deps += SERVER_DEPENDENCIES
+
+    # Add external API dependencies
+    if build_config.external_apis_dir:
+        from llama_stack.core.external import load_external_apis
+
+        external_apis = load_external_apis(build_config)
+        if external_apis:
+            for _, api_spec in external_apis.items():
+                normal_deps.extend(api_spec.pip_packages)
+
+    # Format and output based on requested format
+    output = format_output_deps_only(
+        normal_deps=normal_deps,
+        special_deps=special_deps,
+        external_deps=external_provider_dependencies,
+        uv=args.format == "uv",
+    )
+
+    print(output)
+
+
+def quote_if_needed(dep):
+    # Add quotes if the dependency contains special characters that need escaping in shell
+    # This includes: commas, comparison operators (<, >, <=, >=, ==, !=)
+    needs_quoting = any(char in dep for char in [",", "<", ">", "="])
+    return f"'{dep}'" if needs_quoting else dep
+
+
+def quote_special_dep(dep_string):
+    """
+    Quote individual packages in a special dependency string.
+    Special deps may contain multiple packages and flags like --extra-index-url.
+    We need to quote only the package specs that contain special characters.
+    """
+    parts = dep_string.split()
+    quoted_parts = []
+
+    for part in parts:
+        # Don't quote flags (they start with -)
+        if part.startswith("-"):
+            quoted_parts.append(part)
+        else:
+            # Quote package specs that need it
+            quoted_parts.append(quote_if_needed(part))
+
+    return " ".join(quoted_parts)

llama_stack/cli/stack/build.py

@@ -8,6 +8,9 @@ import textwrap
 
 from llama_stack.cli.stack.utils import ImageType
 from llama_stack.cli.subcommand import Subcommand
+from llama_stack.log import get_logger
+
+logger = get_logger(__name__, category="cli")
 
 
 class StackBuild(Subcommand):
@@ -16,7 +19,7 @@ class StackBuild(Subcommand):
         self.parser = subparsers.add_parser(
             "build",
             prog="llama stack build",
-            description="Build a Llama stack container",
+            description="[DEPRECATED] Build a Llama stack container. This command is deprecated and will be removed in a future release. Use `llama stack list-deps <distro>' instead.",
             formatter_class=argparse.ArgumentDefaultsHelpFormatter,
         )
         self._add_arguments()
@@ -93,6 +96,9 @@ the build. If not specified, currently active environment will be used if found.
         )
 
     def _run_stack_build_command(self, args: argparse.Namespace) -> None:
+        logger.warning(
+            "The 'llama stack build' command is deprecated and will be removed in a future release. Please use 'llama stack list-deps'"
+        )
         # always keep implementation completely silo-ed away from CLI so CLI
         # can be fast to load and reduces dependencies
         from ._build import run_stack_build_command

llama_stack/cli/stack/list_deps.py

@@ -0,0 +1,51 @@
+# 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.
+import argparse
+
+from llama_stack.cli.subcommand import Subcommand
+
+
+class StackListDeps(Subcommand):
+    def __init__(self, subparsers: argparse._SubParsersAction):
+        super().__init__()
+        self.parser = subparsers.add_parser(
+            "list-deps",
+            prog="llama stack list-deps",
+            description="list the dependencies for a llama stack distribution",
+            formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+        )
+        self._add_arguments()
+        self.parser.set_defaults(func=self._run_stack_list_deps_command)
+
+    def _add_arguments(self):
+        self.parser.add_argument(
+            "config",
+            type=str,
+            nargs="?",  # Make it optional
+            metavar="config | distro",
+            help="Path to config file to use or name of known distro (llama stack list for a list).",
+        )
+
+        self.parser.add_argument(
+            "--providers",
+            type=str,
+            default=None,
+            help="sync dependencies for a list of providers and only those providers. This list is formatted like: api1=provider1,api2=provider2. Where there can be multiple providers per API.",
+        )
+        self.parser.add_argument(
+            "--format",
+            type=str,
+            choices=["uv", "deps-only"],
+            default="deps-only",
+            help="Output format: 'uv' shows shell commands, 'deps-only' shows just the list of dependencies without `uv` (default)",
+        )
+
+    def _run_stack_list_deps_command(self, args: argparse.Namespace) -> None:
+        # always keep implementation completely silo-ed away from CLI so CLI
+        # can be fast to load and reduces dependencies
+        from ._list_deps import run_stack_list_deps_command
+
+        return run_stack_list_deps_command(args)

llama_stack/cli/stack/stack.py

@@ -13,6 +13,7 @@ from llama_stack.cli.subcommand import Subcommand
 
 from .build import StackBuild
 from .list_apis import StackListApis
+from .list_deps import StackListDeps
 from .list_providers import StackListProviders
 from .remove import StackRemove
 from .run import StackRun
@@ -39,6 +40,7 @@ class StackParser(Subcommand):
         subparsers = self.parser.add_subparsers(title="stack_subcommands")
 
         # Add sub-commands
+        StackListDeps.create(subparsers)
         StackBuild.create(subparsers)
         StackListApis.create(subparsers)
         StackListProviders.create(subparsers)

llama_stack/cli/stack/utils.py

@@ -4,7 +4,37 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+import json
+import sys
 from enum import Enum
+from functools import lru_cache
+from pathlib import Path
+
+import yaml
+from termcolor import cprint
+
+from llama_stack.core.datatypes import (
+    BuildConfig,
+    Provider,
+    StackRunConfig,
+    StorageConfig,
+)
+from llama_stack.core.distribution import get_provider_registry
+from llama_stack.core.resolver import InvalidProviderError
+from llama_stack.core.storage.datatypes import (
+    InferenceStoreReference,
+    KVStoreReference,
+    ServerStoresConfig,
+    SqliteKVStoreConfig,
+    SqliteSqlStoreConfig,
+    SqlStoreReference,
+)
+from llama_stack.core.utils.config_dirs import DISTRIBS_BASE_DIR, EXTERNAL_PROVIDERS_DIR
+from llama_stack.core.utils.dynamic import instantiate_class_type
+from llama_stack.core.utils.image_types import LlamaStackImageType
+from llama_stack.providers.datatypes import Api
+
+TEMPLATES_PATH = Path(__file__).parent.parent.parent / "distributions"
 
 
 class ImageType(Enum):
@@ -19,3 +49,103 @@ def print_subcommand_description(parser, subparsers):
         description = subcommand.description
         description_text += f"  {name:<21} {description}\n"
     parser.epilog = description_text
+
+
+def generate_run_config(
+    build_config: BuildConfig,
+    build_dir: Path,
+    image_name: str,
+) -> Path:
+    """
+    Generate a run.yaml template file for user to edit from a build.yaml file
+    """
+    apis = list(build_config.distribution_spec.providers.keys())
+    distro_dir = DISTRIBS_BASE_DIR / image_name
+    run_config = StackRunConfig(
+        container_image=(image_name if build_config.image_type == LlamaStackImageType.CONTAINER.value else None),
+        image_name=image_name,
+        apis=apis,
+        providers={},
+        storage=StorageConfig(
+            backends={
+                "kv_default": SqliteKVStoreConfig(db_path=str(distro_dir / "kvstore.db")),
+                "sql_default": SqliteSqlStoreConfig(db_path=str(distro_dir / "sql_store.db")),
+            },
+            stores=ServerStoresConfig(
+                metadata=KVStoreReference(backend="kv_default", namespace="registry"),
+                inference=InferenceStoreReference(backend="sql_default", table_name="inference_store"),
+                conversations=SqlStoreReference(backend="sql_default", table_name="openai_conversations"),
+            ),
+        ),
+        external_providers_dir=build_config.external_providers_dir
+        if build_config.external_providers_dir
+        else EXTERNAL_PROVIDERS_DIR,
+    )
+    # build providers dict
+    provider_registry = get_provider_registry(build_config)
+    for api in apis:
+        run_config.providers[api] = []
+        providers = build_config.distribution_spec.providers[api]
+
+        for provider in providers:
+            pid = provider.provider_type.split("::")[-1]
+
+            p = provider_registry[Api(api)][provider.provider_type]
+            if p.deprecation_error:
+                raise InvalidProviderError(p.deprecation_error)
+
+            try:
+                config_type = instantiate_class_type(provider_registry[Api(api)][provider.provider_type].config_class)
+            except (ModuleNotFoundError, ValueError) as exc:
+                # HACK ALERT:
+                # This code executes after building is done, the import cannot work since the
+                # package is either available in the venv or container - not available on the host.
+                # TODO: use a "is_external" flag in ProviderSpec to check if the provider is
+                # external
+                cprint(
+                    f"Failed to import provider {provider.provider_type} for API {api} - assuming it's external, skipping: {exc}",
+                    color="yellow",
+                    file=sys.stderr,
+                )
+                # Set config_type to None to avoid UnboundLocalError
+                config_type = None
+
+            if config_type is not None and hasattr(config_type, "sample_run_config"):
+                config = config_type.sample_run_config(__distro_dir__=f"~/.llama/distributions/{image_name}")
+            else:
+                config = {}
+
+            p_spec = Provider(
+                provider_id=pid,
+                provider_type=provider.provider_type,
+                config=config,
+                module=provider.module,
+            )
+            run_config.providers[api].append(p_spec)
+
+    run_config_file = build_dir / f"{image_name}-run.yaml"
+
+    with open(run_config_file, "w") as f:
+        to_write = json.loads(run_config.model_dump_json())
+        f.write(yaml.dump(to_write, sort_keys=False))
+
+    # Only print this message for non-container builds since it will be displayed before the
+    # container is built
+    # For non-container builds, the run.yaml is generated at the very end of the build process so it
+    # makes sense to display this message
+    if build_config.image_type != LlamaStackImageType.CONTAINER.value:
+        cprint(f"You can now run your stack with `llama stack run {run_config_file}`", color="green", file=sys.stderr)
+    return run_config_file
+
+
+@lru_cache
+def available_templates_specs() -> dict[str, BuildConfig]:
+    import yaml
+
+    template_specs = {}
+    for p in TEMPLATES_PATH.rglob("*build.yaml"):
+        template_name = p.parent.name
+        with open(p) as f:
+            build_config = BuildConfig(**yaml.safe_load(f))
+            template_specs[template_name] = build_config
+    return template_specs

llama_stack/core/configure.py

@@ -159,6 +159,37 @@ def upgrade_from_routing_table(
     config_dict["apis"] = config_dict["apis_to_serve"]
     config_dict.pop("apis_to_serve", None)
 
+    # Add default storage config if not present
+    if "storage" not in config_dict:
+        config_dict["storage"] = {
+            "backends": {
+                "kv_default": {
+                    "type": "kv_sqlite",
+                    "db_path": "~/.llama/kvstore.db",
+                },
+                "sql_default": {
+                    "type": "sql_sqlite",
+                    "db_path": "~/.llama/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",
+                },
+            },
+        }
+
     return config_dict
 
 

llama_stack/core/conversations/conversations.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.
 
-import os
 import secrets
 import time
 from typing import Any
@@ -21,16 +20,11 @@ from llama_stack.apis.conversations.conversations import (
     Conversations,
     Metadata,
 )
-from llama_stack.core.datatypes import AccessRule
+from llama_stack.core.datatypes import AccessRule, StackRunConfig
-from llama_stack.core.utils.config_dirs import DISTRIBS_BASE_DIR
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType
 from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore
-from llama_stack.providers.utils.sqlstore.sqlstore import (
+from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl
-    SqliteSqlStoreConfig,
-    SqlStoreConfig,
-    sqlstore_impl,
-)
 
 logger = get_logger(name=__name__, category="openai_conversations")
 
@@ -38,13 +32,11 @@ logger = get_logger(name=__name__, category="openai_conversations")
 class ConversationServiceConfig(BaseModel):
     """Configuration for the built-in conversation service.
 
-    :param conversations_store: SQL store configuration for conversations (defaults to SQLite)
+    :param run_config: Stack run configuration for resolving persistence
     :param policy: Access control rules
     """
 
-    conversations_store: SqlStoreConfig = SqliteSqlStoreConfig(
+    run_config: StackRunConfig
-        db_path=(DISTRIBS_BASE_DIR / "conversations.db").as_posix()
-    )
     policy: list[AccessRule] = []
 
 
@@ -63,14 +55,16 @@ class ConversationServiceImpl(Conversations):
         self.deps = deps
         self.policy = config.policy
 
-        base_sql_store = sqlstore_impl(config.conversations_store)
+        # Use conversations store reference from run config
+        conversations_ref = config.run_config.storage.stores.conversations
+        if not conversations_ref:
+            raise ValueError("storage.stores.conversations must be configured in run config")
+
+        base_sql_store = sqlstore_impl(conversations_ref)
         self.sql_store = AuthorizedSqlStore(base_sql_store, self.policy)
 
     async def initialize(self) -> None:
         """Initialize the store and create tables."""
-        if isinstance(self.config.conversations_store, SqliteSqlStoreConfig):
-            os.makedirs(os.path.dirname(self.config.conversations_store.db_path), exist_ok=True)
-
         await self.sql_store.create_table(
             "openai_conversations",
             {

llama_stack/core/datatypes.py

@@ -26,9 +26,12 @@ from llama_stack.apis.tools import ToolGroup, ToolGroupInput, ToolRuntime
 from llama_stack.apis.vector_dbs import VectorDB, VectorDBInput
 from llama_stack.apis.vector_io import VectorIO
 from llama_stack.core.access_control.datatypes import AccessRule
+from llama_stack.core.storage.datatypes import (
+    KVStoreReference,
+    StorageBackendType,
+    StorageConfig,
+)
 from llama_stack.providers.datatypes import Api, ProviderSpec
-from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
-from llama_stack.providers.utils.sqlstore.sqlstore import SqlStoreConfig
 
 LLAMA_STACK_BUILD_CONFIG_VERSION = 2
 LLAMA_STACK_RUN_CONFIG_VERSION = 2
@@ -382,7 +385,7 @@ class QuotaPeriod(StrEnum):
 
 
 class QuotaConfig(BaseModel):
-    kvstore: SqliteKVStoreConfig = Field(description="Config for KV store backend (SQLite only for now)")
+    kvstore: KVStoreReference = Field(description="Config for KV store backend (SQLite only for now)")
     anonymous_max_requests: int = Field(default=100, description="Max requests for unauthenticated clients per period")
     authenticated_max_requests: int = Field(
         default=1000, description="Max requests for authenticated clients per period"
@@ -464,18 +467,6 @@ class ServerConfig(BaseModel):
     )
 
 
-class InferenceStoreConfig(BaseModel):
-    sql_store_config: SqlStoreConfig
-    max_write_queue_size: int = Field(default=10000, description="Max queued writes for inference store")
-    num_writers: int = Field(default=4, description="Number of concurrent background writers")
-
-
-class ResponsesStoreConfig(BaseModel):
-    sql_store_config: SqlStoreConfig
-    max_write_queue_size: int = Field(default=10000, description="Max queued writes for responses store")
-    num_writers: int = Field(default=4, description="Number of concurrent background writers")
-
-
 class StackRunConfig(BaseModel):
     version: int = LLAMA_STACK_RUN_CONFIG_VERSION
 
@@ -502,26 +493,8 @@ One or more providers to use for each API. The same provider_type (e.g., meta-re
 can be instantiated multiple times (with different configs) if necessary.
 """,
     )
-    metadata_store: KVStoreConfig | None = Field(
+    storage: StorageConfig = Field(
-        default=None,
+        description="Catalog of named storage backends and references available to the stack",
-        description="""
-Configuration for the persistence store used by the distribution registry. If not specified,
-a default SQLite store will be used.""",
-    )
-
-    inference_store: InferenceStoreConfig | SqlStoreConfig | None = Field(
-        default=None,
-        description="""
-Configuration for the persistence store used by the inference API. Can be either a
-InferenceStoreConfig (with queue tuning parameters) or a SqlStoreConfig (deprecated).
-If not specified, a default SQLite store will be used.""",
-    )
-
-    conversations_store: SqlStoreConfig | None = Field(
-        default=None,
-        description="""
-Configuration for the persistence store used by the conversations API.
-If not specified, a default SQLite store will be used.""",
     )
 
     # registry of "resources" in the distribution
@@ -566,6 +539,49 @@ If not specified, a default SQLite store will be used.""",
             return Path(v)
         return v
 
+    @model_validator(mode="after")
+    def validate_server_stores(self) -> "StackRunConfig":
+        backend_map = self.storage.backends
+        stores = self.storage.stores
+        kv_backends = {
+            name
+            for name, cfg in backend_map.items()
+            if cfg.type
+            in {
+                StorageBackendType.KV_REDIS,
+                StorageBackendType.KV_SQLITE,
+                StorageBackendType.KV_POSTGRES,
+                StorageBackendType.KV_MONGODB,
+            }
+        }
+        sql_backends = {
+            name
+            for name, cfg in backend_map.items()
+            if cfg.type in {StorageBackendType.SQL_SQLITE, StorageBackendType.SQL_POSTGRES}
+        }
+
+        def _ensure_backend(reference, expected_set, store_name: str) -> None:
+            if reference is None:
+                return
+            backend_name = reference.backend
+            if backend_name not in backend_map:
+                raise ValueError(
+                    f"{store_name} references unknown backend '{backend_name}'. "
+                    f"Available backends: {sorted(backend_map)}"
+                )
+            if backend_name not in expected_set:
+                raise ValueError(
+                    f"{store_name} references backend '{backend_name}' of type "
+                    f"'{backend_map[backend_name].type.value}', but a backend of type "
+                    f"{'kv_*' if expected_set is kv_backends else 'sql_*'} is required."
+                )
+
+        _ensure_backend(stores.metadata, kv_backends, "storage.stores.metadata")
+        _ensure_backend(stores.inference, sql_backends, "storage.stores.inference")
+        _ensure_backend(stores.conversations, sql_backends, "storage.stores.conversations")
+        _ensure_backend(stores.responses, sql_backends, "storage.stores.responses")
+        return self
+
 
 class BuildConfig(BaseModel):
     version: int = LLAMA_STACK_BUILD_CONFIG_VERSION

llama_stack/core/prompts/prompts.py

@@ -11,9 +11,8 @@ from pydantic import BaseModel
 
 from llama_stack.apis.prompts import ListPromptsResponse, Prompt, Prompts
 from llama_stack.core.datatypes import StackRunConfig
-from llama_stack.core.utils.config_dirs import DISTRIBS_BASE_DIR
+from llama_stack.core.storage.datatypes import KVStoreReference
 from llama_stack.providers.utils.kvstore import KVStore, kvstore_impl
-from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
 
 
 class PromptServiceConfig(BaseModel):
@@ -41,10 +40,12 @@ class PromptServiceImpl(Prompts):
         self.kvstore: KVStore
 
     async def initialize(self) -> None:
-        kvstore_config = SqliteKVStoreConfig(
+        # Use metadata store backend with prompts-specific namespace
-            db_path=(DISTRIBS_BASE_DIR / self.config.run_config.image_name / "prompts.db").as_posix()
+        metadata_ref = self.config.run_config.storage.stores.metadata
-        )
+        if not metadata_ref:
-        self.kvstore = await kvstore_impl(kvstore_config)
+            raise ValueError("storage.stores.metadata must be configured in run config")
+        prompts_ref = KVStoreReference(namespace="prompts", backend=metadata_ref.backend)
+        self.kvstore = await kvstore_impl(prompts_ref)
 
     def _get_default_key(self, prompt_id: str) -> str:
         """Get the KVStore key that stores the default version number."""

llama_stack/core/resolver.py

@@ -4,6 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 import importlib
+import importlib.metadata
 import inspect
 from typing import Any
 

llama_stack/core/routers/__init__.py

@@ -6,7 +6,10 @@
 
 from typing import Any
 
-from llama_stack.core.datatypes import AccessRule, RoutedProtocol
+from llama_stack.core.datatypes import (
+    AccessRule,
+    RoutedProtocol,
+)
 from llama_stack.core.stack import StackRunConfig
 from llama_stack.core.store import DistributionRegistry
 from llama_stack.providers.datatypes import Api, RoutingTable
@@ -78,9 +81,13 @@ async def get_auto_router_impl(
                 api_to_dep_impl[dep_name] = deps[dep_api]
 
     # TODO: move pass configs to routers instead
-    if api == Api.inference and run_config.inference_store:
+    if api == Api.inference:
+        inference_ref = run_config.storage.stores.inference
+        if not inference_ref:
+            raise ValueError("storage.stores.inference must be configured in run config")
+
         inference_store = InferenceStore(
-            config=run_config.inference_store,
+            reference=inference_ref,
             policy=policy,
         )
         await inference_store.initialize()

llama_stack/core/server/auth_providers.py

@@ -72,13 +72,30 @@ class AuthProvider(ABC):
 def get_attributes_from_claims(claims: dict[str, str], mapping: dict[str, str]) -> dict[str, list[str]]:
     attributes: dict[str, list[str]] = {}
     for claim_key, attribute_key in mapping.items():
-        if claim_key not in claims:
+        # First try dot notation for nested traversal (e.g., "resource_access.llamastack.roles")
+        # Then fall back to literal key with dots (e.g., "my.dotted.key")
+        claim: object = claims
+        keys = claim_key.split(".")
+        for key in keys:
+            if isinstance(claim, dict) and key in claim:
+                claim = claim[key]
+            else:
+                claim = None
+                break
+
+        if claim is None and claim_key in claims:
+            # Fall back to checking if claim_key exists as a literal key
+            claim = claims[claim_key]
+
+        if claim is None:
             continue
-        claim = claims[claim_key]
+
         if isinstance(claim, list):
             values = claim
-        else:
+        elif isinstance(claim, str):
             values = claim.split()
+        else:
+            continue
 
         if attribute_key in attributes:
             attributes[attribute_key].extend(values)

llama_stack/core/server/quota.py

@@ -10,10 +10,10 @@ from datetime import UTC, datetime, timedelta
 
 from starlette.types import ASGIApp, Receive, Scope, Send
 
+from llama_stack.core.storage.datatypes import KVStoreReference, StorageBackendType
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.kvstore.api import KVStore
-from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
+from llama_stack.providers.utils.kvstore.kvstore import _KVSTORE_BACKENDS, kvstore_impl
-from llama_stack.providers.utils.kvstore.kvstore import kvstore_impl
 
 logger = get_logger(name=__name__, category="core::server")
 
@@ -33,7 +33,7 @@ class QuotaMiddleware:
     def __init__(
         self,
         app: ASGIApp,
-        kv_config: KVStoreConfig,
+        kv_config: KVStoreReference,
         anonymous_max_requests: int,
         authenticated_max_requests: int,
         window_seconds: int = 86400,
@@ -45,15 +45,15 @@ class QuotaMiddleware:
         self.authenticated_max_requests = authenticated_max_requests
         self.window_seconds = window_seconds
 
-        if isinstance(self.kv_config, SqliteKVStoreConfig):
-            logger.warning(
-                "QuotaMiddleware: Using SQLite backend. Expiry/TTL is not enforced; cleanup is manual. "
-                f"window_seconds={self.window_seconds}"
-            )
-
     async def _get_kv(self) -> KVStore:
         if self.kv is None:
             self.kv = await kvstore_impl(self.kv_config)
+            backend_config = _KVSTORE_BACKENDS.get(self.kv_config.backend)
+            if backend_config and backend_config.type == StorageBackendType.KV_SQLITE:
+                logger.warning(
+                    "QuotaMiddleware: Using SQLite backend. Expiry/TTL is not enforced; cleanup is manual. "
+                    f"window_seconds={self.window_seconds}"
+                )
         return self.kv
 
     async def __call__(self, scope: Scope, receive: Receive, send: Send):

llama_stack/core/stack.py

@@ -42,6 +42,16 @@ from llama_stack.core.prompts.prompts import PromptServiceConfig, PromptServiceI
 from llama_stack.core.providers import ProviderImpl, ProviderImplConfig
 from llama_stack.core.resolver import ProviderRegistry, resolve_impls
 from llama_stack.core.routing_tables.common import CommonRoutingTableImpl
+from llama_stack.core.storage.datatypes import (
+    InferenceStoreReference,
+    KVStoreReference,
+    ServerStoresConfig,
+    SqliteKVStoreConfig,
+    SqliteSqlStoreConfig,
+    SqlStoreReference,
+    StorageBackendConfig,
+    StorageConfig,
+)
 from llama_stack.core.store.registry import create_dist_registry
 from llama_stack.core.utils.dynamic import instantiate_class_type
 from llama_stack.log import get_logger
@@ -357,6 +367,25 @@ def add_internal_implementations(impls: dict[Api, Any], run_config: StackRunConf
     impls[Api.conversations] = conversations_impl
 
 
+def _initialize_storage(run_config: StackRunConfig):
+    kv_backends: dict[str, StorageBackendConfig] = {}
+    sql_backends: dict[str, StorageBackendConfig] = {}
+    for backend_name, backend_config in run_config.storage.backends.items():
+        type = backend_config.type.value
+        if type.startswith("kv_"):
+            kv_backends[backend_name] = backend_config
+        elif type.startswith("sql_"):
+            sql_backends[backend_name] = backend_config
+        else:
+            raise ValueError(f"Unknown storage backend type: {type}")
+
+    from llama_stack.providers.utils.kvstore.kvstore import register_kvstore_backends
+    from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends
+
+    register_kvstore_backends(kv_backends)
+    register_sqlstore_backends(sql_backends)
+
+
 class Stack:
     def __init__(self, run_config: StackRunConfig, provider_registry: ProviderRegistry | None = None):
         self.run_config = run_config
@@ -375,7 +404,11 @@ class Stack:
                 TEST_RECORDING_CONTEXT.__enter__()
                 logger.info(f"API recording enabled: mode={os.environ.get('LLAMA_STACK_TEST_INFERENCE_MODE')}")
 
-        dist_registry, _ = await create_dist_registry(self.run_config.metadata_store, self.run_config.image_name)
+        _initialize_storage(self.run_config)
+        stores = self.run_config.storage.stores
+        if not stores.metadata:
+            raise ValueError("storage.stores.metadata must be configured with a kv_* backend")
+        dist_registry, _ = await create_dist_registry(stores.metadata, self.run_config.image_name)
         policy = self.run_config.server.auth.access_policy if self.run_config.server.auth else []
 
         internal_impls = {}
@@ -516,5 +549,16 @@ def run_config_from_adhoc_config_spec(
         image_name="distro-test",
         apis=list(provider_configs_by_api.keys()),
         providers=provider_configs_by_api,
+        storage=StorageConfig(
+            backends={
+                "kv_default": SqliteKVStoreConfig(db_path=f"{distro_dir}/kvstore.db"),
+                "sql_default": SqliteSqlStoreConfig(db_path=f"{distro_dir}/sql_store.db"),
+            },
+            stores=ServerStoresConfig(
+                metadata=KVStoreReference(backend="kv_default", namespace="registry"),
+                inference=InferenceStoreReference(backend="sql_default", table_name="inference_store"),
+                conversations=SqlStoreReference(backend="sql_default", table_name="openai_conversations"),
+            ),
+        ),
     )
     return config

llama_stack/core/storage/__init__.py

@@ -0,0 +1,5 @@
+# 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.

llama_stack/core/storage/datatypes.py

@@ -0,0 +1,283 @@
+# 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.
+
+import re
+from abc import abstractmethod
+from enum import StrEnum
+from pathlib import Path
+from typing import Annotated, Literal
+
+from pydantic import BaseModel, Field, field_validator
+
+
+class StorageBackendType(StrEnum):
+    KV_REDIS = "kv_redis"
+    KV_SQLITE = "kv_sqlite"
+    KV_POSTGRES = "kv_postgres"
+    KV_MONGODB = "kv_mongodb"
+    SQL_SQLITE = "sql_sqlite"
+    SQL_POSTGRES = "sql_postgres"
+
+
+class CommonConfig(BaseModel):
+    namespace: str | None = Field(
+        default=None,
+        description="All keys will be prefixed with this namespace",
+    )
+
+
+class RedisKVStoreConfig(CommonConfig):
+    type: Literal[StorageBackendType.KV_REDIS] = StorageBackendType.KV_REDIS
+    host: str = "localhost"
+    port: int = 6379
+
+    @property
+    def url(self) -> str:
+        return f"redis://{self.host}:{self.port}"
+
+    @classmethod
+    def pip_packages(cls) -> list[str]:
+        return ["redis"]
+
+    @classmethod
+    def sample_run_config(cls):
+        return {
+            "type": StorageBackendType.KV_REDIS.value,
+            "host": "${env.REDIS_HOST:=localhost}",
+            "port": "${env.REDIS_PORT:=6379}",
+        }
+
+
+class SqliteKVStoreConfig(CommonConfig):
+    type: Literal[StorageBackendType.KV_SQLITE] = StorageBackendType.KV_SQLITE
+    db_path: str = Field(
+        description="File path for the sqlite database",
+    )
+
+    @classmethod
+    def pip_packages(cls) -> list[str]:
+        return ["aiosqlite"]
+
+    @classmethod
+    def sample_run_config(cls, __distro_dir__: str, db_name: str = "kvstore.db"):
+        return {
+            "type": StorageBackendType.KV_SQLITE.value,
+            "db_path": "${env.SQLITE_STORE_DIR:=" + __distro_dir__ + "}/" + db_name,
+        }
+
+
+class PostgresKVStoreConfig(CommonConfig):
+    type: Literal[StorageBackendType.KV_POSTGRES] = StorageBackendType.KV_POSTGRES
+    host: str = "localhost"
+    port: int | str = 5432
+    db: str = "llamastack"
+    user: str
+    password: str | None = None
+    ssl_mode: str | None = None
+    ca_cert_path: str | None = None
+    table_name: str = "llamastack_kvstore"
+
+    @classmethod
+    def sample_run_config(cls, table_name: str = "llamastack_kvstore", **kwargs):
+        return {
+            "type": StorageBackendType.KV_POSTGRES.value,
+            "host": "${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": "${env.POSTGRES_TABLE_NAME:=" + table_name + "}",
+        }
+
+    @classmethod
+    @field_validator("table_name")
+    def validate_table_name(cls, v: str) -> str:
+        # PostgreSQL identifiers rules:
+        # - Must start with a letter or underscore
+        # - Can contain letters, numbers, and underscores
+        # - Maximum length is 63 bytes
+        pattern = r"^[a-zA-Z_][a-zA-Z0-9_]*$"
+        if not re.match(pattern, v):
+            raise ValueError(
+                "Invalid table name. Must start with letter or underscore and contain only letters, numbers, and underscores"
+            )
+        if len(v) > 63:
+            raise ValueError("Table name must be less than 63 characters")
+        return v
+
+    @classmethod
+    def pip_packages(cls) -> list[str]:
+        return ["psycopg2-binary"]
+
+
+class MongoDBKVStoreConfig(CommonConfig):
+    type: Literal[StorageBackendType.KV_MONGODB] = StorageBackendType.KV_MONGODB
+    host: str = "localhost"
+    port: int = 27017
+    db: str = "llamastack"
+    user: str | None = None
+    password: str | None = None
+    collection_name: str = "llamastack_kvstore"
+
+    @classmethod
+    def pip_packages(cls) -> list[str]:
+        return ["pymongo"]
+
+    @classmethod
+    def sample_run_config(cls, collection_name: str = "llamastack_kvstore"):
+        return {
+            "type": StorageBackendType.KV_MONGODB.value,
+            "host": "${env.MONGODB_HOST:=localhost}",
+            "port": "${env.MONGODB_PORT:=5432}",
+            "db": "${env.MONGODB_DB}",
+            "user": "${env.MONGODB_USER}",
+            "password": "${env.MONGODB_PASSWORD}",
+            "collection_name": "${env.MONGODB_COLLECTION_NAME:=" + collection_name + "}",
+        }
+
+
+class SqlAlchemySqlStoreConfig(BaseModel):
+    @property
+    @abstractmethod
+    def engine_str(self) -> str: ...
+
+    # TODO: move this when we have a better way to specify dependencies with internal APIs
+    @classmethod
+    def pip_packages(cls) -> list[str]:
+        return ["sqlalchemy[asyncio]"]
+
+
+class SqliteSqlStoreConfig(SqlAlchemySqlStoreConfig):
+    type: Literal[StorageBackendType.SQL_SQLITE] = StorageBackendType.SQL_SQLITE
+    db_path: str = Field(
+        description="Database path, e.g. ~/.llama/distributions/ollama/sqlstore.db",
+    )
+
+    @property
+    def engine_str(self) -> str:
+        return "sqlite+aiosqlite:///" + Path(self.db_path).expanduser().as_posix()
+
+    @classmethod
+    def sample_run_config(cls, __distro_dir__: str, db_name: str = "sqlstore.db"):
+        return {
+            "type": StorageBackendType.SQL_SQLITE.value,
+            "db_path": "${env.SQLITE_STORE_DIR:=" + __distro_dir__ + "}/" + db_name,
+        }
+
+    @classmethod
+    def pip_packages(cls) -> list[str]:
+        return super().pip_packages() + ["aiosqlite"]
+
+
+class PostgresSqlStoreConfig(SqlAlchemySqlStoreConfig):
+    type: Literal[StorageBackendType.SQL_POSTGRES] = StorageBackendType.SQL_POSTGRES
+    host: str = "localhost"
+    port: int | str = 5432
+    db: str = "llamastack"
+    user: str
+    password: str | None = None
+
+    @property
+    def engine_str(self) -> str:
+        return f"postgresql+asyncpg://{self.user}:{self.password}@{self.host}:{self.port}/{self.db}"
+
+    @classmethod
+    def pip_packages(cls) -> list[str]:
+        return super().pip_packages() + ["asyncpg"]
+
+    @classmethod
+    def sample_run_config(cls, **kwargs):
+        return {
+            "type": StorageBackendType.SQL_POSTGRES.value,
+            "host": "${env.POSTGRES_HOST:=localhost}",
+            "port": "${env.POSTGRES_PORT:=5432}",
+            "db": "${env.POSTGRES_DB:=llamastack}",
+            "user": "${env.POSTGRES_USER:=llamastack}",
+            "password": "${env.POSTGRES_PASSWORD:=llamastack}",
+        }
+
+
+# reference = (backend_name, table_name)
+class SqlStoreReference(BaseModel):
+    """A reference to a 'SQL-like' persistent store. A table name must be provided."""
+
+    table_name: str = Field(
+        description="Name of the table to use for the SqlStore",
+    )
+
+    backend: str = Field(
+        description="Name of backend from storage.backends",
+    )
+
+
+# reference = (backend_name, namespace)
+class KVStoreReference(BaseModel):
+    """A reference to a 'key-value' persistent store. A namespace must be provided."""
+
+    namespace: str = Field(
+        description="Key prefix for KVStore backends",
+    )
+
+    backend: str = Field(
+        description="Name of backend from storage.backends",
+    )
+
+
+StorageBackendConfig = Annotated[
+    RedisKVStoreConfig
+    | SqliteKVStoreConfig
+    | PostgresKVStoreConfig
+    | MongoDBKVStoreConfig
+    | SqliteSqlStoreConfig
+    | PostgresSqlStoreConfig,
+    Field(discriminator="type"),
+]
+
+
+class InferenceStoreReference(SqlStoreReference):
+    """Inference store configuration with queue tuning."""
+
+    max_write_queue_size: int = Field(
+        default=10000,
+        description="Max queued writes for inference store",
+    )
+    num_writers: int = Field(
+        default=4,
+        description="Number of concurrent background writers",
+    )
+
+
+class ResponsesStoreReference(InferenceStoreReference):
+    """Responses store configuration with queue tuning."""
+
+
+class ServerStoresConfig(BaseModel):
+    metadata: KVStoreReference | None = Field(
+        default=None,
+        description="Metadata store configuration (uses KV backend)",
+    )
+    inference: InferenceStoreReference | None = Field(
+        default=None,
+        description="Inference store configuration (uses SQL backend)",
+    )
+    conversations: SqlStoreReference | None = Field(
+        default=None,
+        description="Conversations store configuration (uses SQL backend)",
+    )
+    responses: ResponsesStoreReference | None = Field(
+        default=None,
+        description="Responses store configuration (uses SQL backend)",
+    )
+
+
+class StorageConfig(BaseModel):
+    backends: dict[str, StorageBackendConfig] = Field(
+        description="Named backend configurations (e.g., 'default', 'cache')",
+    )
+    stores: ServerStoresConfig = Field(
+        default_factory=lambda: ServerStoresConfig(),
+        description="Named references to storage backends used by the stack core",
+    )

llama_stack/core/store/registry.py

@@ -11,10 +11,9 @@ from typing import Protocol
 import pydantic
 
 from llama_stack.core.datatypes import RoutableObjectWithProvider
-from llama_stack.core.utils.config_dirs import DISTRIBS_BASE_DIR
+from llama_stack.core.storage.datatypes import KVStoreReference
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.kvstore import KVStore, kvstore_impl
-from llama_stack.providers.utils.kvstore.config import KVStoreConfig, SqliteKVStoreConfig
 
 logger = get_logger(__name__, category="core::registry")
 
@@ -191,16 +190,10 @@ class CachedDiskDistributionRegistry(DiskDistributionRegistry):
 
 
 async def create_dist_registry(
-    metadata_store: KVStoreConfig | None,
+    metadata_store: KVStoreReference, image_name: str
-    image_name: str,
 ) -> tuple[CachedDiskDistributionRegistry, KVStore]:
     # instantiate kvstore for storing and retrieving distribution metadata
-    if metadata_store:
+    dist_kvstore = await kvstore_impl(metadata_store)
-        dist_kvstore = await kvstore_impl(metadata_store)
-    else:
-        dist_kvstore = await kvstore_impl(
-            SqliteKVStoreConfig(db_path=(DISTRIBS_BASE_DIR / image_name / "kvstore.db").as_posix())
-        )
     dist_registry = CachedDiskDistributionRegistry(dist_kvstore)
     await dist_registry.initialize()
     return dist_registry, dist_kvstore

llama_stack/core/utils/config_resolution.py

@@ -42,25 +42,25 @@ def resolve_config_or_distro(
     # Strategy 1: Try as file path first
     config_path = Path(config_or_distro)
     if config_path.exists() and config_path.is_file():
-        logger.info(f"Using file path: {config_path}")
+        logger.debug(f"Using file path: {config_path}")
         return config_path.resolve()
 
     # Strategy 2: Try as distribution name (if no .yaml extension)
     if not config_or_distro.endswith(".yaml"):
         distro_config = _get_distro_config_path(config_or_distro, mode)
         if distro_config.exists():
-            logger.info(f"Using distribution: {distro_config}")
+            logger.debug(f"Using distribution: {distro_config}")
             return distro_config
 
     # Strategy 3: Try as built distribution name
     distrib_config = DISTRIBS_BASE_DIR / f"llamastack-{config_or_distro}" / f"{config_or_distro}-{mode}.yaml"
     if distrib_config.exists():
-        logger.info(f"Using built distribution: {distrib_config}")
+        logger.debug(f"Using built distribution: {distrib_config}")
         return distrib_config
 
     distrib_config = DISTRIBS_BASE_DIR / f"{config_or_distro}" / f"{config_or_distro}-{mode}.yaml"
     if distrib_config.exists():
-        logger.info(f"Using built distribution: {distrib_config}")
+        logger.debug(f"Using built distribution: {distrib_config}")
         return distrib_config
 
     # Strategy 4: Failed - provide helpful error