fix security update

.github/workflows/Dockerfile

@@ -0,0 +1 @@
+FROM localhost:5000/distribution-kvant:dev

.github/workflows/ci-playground.yaml

@@ -0,0 +1,73 @@
+name: Build and Push playground container
+run-name: Build and Push playground container
+on:
+  workflow_dispatch:
+  #schedule:
+  #  - cron: "0 10 * * *"
+  push:
+    branches:
+      - main
+      - kvant
+    tags:
+      - 'v*'
+  pull_request:
+    branches:
+      - main
+      - kvant
+env:
+  IMAGE: git.kvant.cloud/${{github.repository}}-playground
+jobs:
+  build-playground:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set current time
+        uses: https://github.com/gerred/actions/current-time@master
+        id: current_time
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to git.kvant.cloud registry
+        uses: docker/login-action@v3
+        with:
+          registry: git.kvant.cloud
+          username: ${{ vars.ORG_PACKAGE_WRITER_USERNAME }}
+          password: ${{ secrets.ORG_PACKAGE_WRITER_TOKEN }}
+      
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          # list of Docker images to use as base name for tags
+          images: |
+            ${{env.IMAGE}}
+          # generate Docker tags based on the following events/attributes
+          tags: |
+            type=schedule
+            type=ref,event=branch
+            type=ref,event=pr
+            type=ref,event=tag
+            type=semver,pattern={{version}}
+
+      - name: Build and push to gitea registry
+        uses: docker/build-push-action@v6
+        with:
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          context: .
+          file: llama_stack/distribution/ui/Containerfile
+          provenance: mode=max
+          sbom: true
+          build-args: |
+            BUILD_DATE=${{ steps.current_time.outputs.time }}
+          cache-from: |
+            type=registry,ref=${{ env.IMAGE }}:buildcache
+            type=registry,ref=${{ env.IMAGE }}:${{ github.ref_name }}
+            type=registry,ref=${{ env.IMAGE }}:main
+          cache-to: type=registry,ref=${{ env.IMAGE }}:buildcache,mode=max,image-manifest=true

.github/workflows/ci.yaml

@@ -0,0 +1,98 @@
+name: Build and Push container
+run-name: Build and Push container
+on:
+  workflow_dispatch:
+  #schedule:
+  #  - cron: "0 10 * * *"
+  push:
+    branches:
+      - main
+      - kvant
+    tags:
+      - 'v*'
+  pull_request:
+    branches:
+      - main
+      - kvant
+env:
+  IMAGE: git.kvant.cloud/${{github.repository}}
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    services:
+      registry:
+        image: registry:2
+        ports:
+          - 5000:5000
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set current time
+        uses: https://github.com/gerred/actions/current-time@master
+        id: current_time
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          driver-opts: network=host
+
+      - name: Login to git.kvant.cloud registry
+        uses: docker/login-action@v3
+        with:
+          registry: git.kvant.cloud
+          username: ${{ vars.ORG_PACKAGE_WRITER_USERNAME }}
+          password: ${{ secrets.ORG_PACKAGE_WRITER_TOKEN }}
+      
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          # list of Docker images to use as base name for tags
+          images: |
+            ${{env.IMAGE}}
+          # generate Docker tags based on the following events/attributes
+          tags: |
+            type=schedule
+            type=ref,event=branch
+            type=ref,event=pr
+            type=ref,event=tag
+            type=semver,pattern={{version}}
+
+      - name: Install uv
+        uses: https://github.com/astral-sh/setup-uv@v5
+        with:
+          # Install a specific version of uv.
+          version: "0.7.8"
+            
+      - name: Build
+        env:
+          USE_COPY_NOT_MOUNT: true
+          LLAMA_STACK_DIR: .
+        run: |
+          uvx --from . llama stack build --template kvant --image-type container
+
+          # docker tag distribution-kvant:dev ${{env.IMAGE}}:kvant
+          # docker push ${{env.IMAGE}}:kvant
+
+          docker tag distribution-kvant:dev localhost:5000/distribution-kvant:dev
+          docker push localhost:5000/distribution-kvant:dev
+
+      - name: Build and push to gitea registry
+        uses: docker/build-push-action@v6
+        with:
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          context: .github/workflows
+          provenance: mode=max
+          sbom: true
+          build-args: |
+            BUILD_DATE=${{ steps.current_time.outputs.time }}
+          cache-from: |
+            type=registry,ref=${{ env.IMAGE }}:buildcache
+            type=registry,ref=${{ env.IMAGE }}:${{ github.ref_name }}
+            type=registry,ref=${{ env.IMAGE }}:main
+          cache-to: type=registry,ref=${{ env.IMAGE }}:buildcache,mode=max,image-manifest=true

.gitignore

@@ -24,3 +24,4 @@ venv/
 pytest-report.xml
 .coverage
 .python-version
+data

kvant_build_local.sh

@@ -0,0 +1,6 @@
+#!/usr/bin/env bash
+
+export USE_COPY_NOT_MOUNT=true
+export LLAMA_STACK_DIR=.
+
+uvx --from . llama stack build --template kvant --image-type container  --image-name kvant

kvant_start_local.sh

@@ -0,0 +1,17 @@
+#!/usr/bin/env bash
+
+export LLAMA_STACK_PORT=8321
+# VLLM_API_TOKEN= env file
+# KEYCLOAK_CLIENT_SECRET= env file
+
+
+docker run -it \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v $(pwd)/data:/root/.llama \
+  --mount type=bind,source="$(pwd)"/llama_stack/templates/kvant/run.yaml,target=/root/.llama/config.yaml,readonly \
+  --entrypoint python \
+  --env-file ./.env \
+  distribution-kvant:dev \
+  -m llama_stack.distribution.server.server  --config /root/.llama/config.yaml \
+  --port $LLAMA_STACK_PORT \
+

llama_stack/distribution/ui/Containerfile

@@ -5,7 +5,8 @@ FROM python:3.12-slim
 WORKDIR /app
 COPY . /app/
 RUN /usr/local/bin/python -m pip install --upgrade pip && \
-    /usr/local/bin/pip3 install -r requirements.txt
+    /usr/local/bin/pip3 install -r requirements.txt && \
+    /usr/local/bin/pip3 install -r llama_stack/distribution/ui/requirements.txt
 EXPOSE 8501
 
-ENTRYPOINT ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+ENTRYPOINT ["streamlit", "run", "llama_stack/distribution/ui/app.py", "--server.port=8501", "--server.address=0.0.0.0"]

llama_stack/distribution/ui/README.md

@@ -48,3 +48,6 @@ uv run --with ".[ui]" streamlit run llama_stack/distribution/ui/app.py
 | TOGETHER_API_KEY           | API key for Together provider      | (empty string)            |
 | SAMBANOVA_API_KEY          | API key for SambaNova provider     | (empty string)            |
 | OPENAI_API_KEY             | API key for OpenAI provider        | (empty string)            |
+| KEYCLOAK_URL               | URL for keycloak authentication    | (empty string)            |
+| KEYCLOAK_REALM             | Keycloak realm                     | default                   |
+| KEYCLOAK_CLIENT_ID         | Client ID for keycloak auth        | (empty string)            |

llama_stack/distribution/ui/app.py

@@ -50,6 +50,42 @@ def main():
     )
     pg.run()
 
+def main2():
+    from dataclasses import asdict
+    st.subheader(f"Welcome {keycloak.user_info['preferred_username']}!")
+    st.write(f"Here is your user information:")
+    st.write(asdict(keycloak))
+
+def get_access_token() -> str|None:
+    return st.session_state.get('access_token')
 
 if __name__ == "__main__":
-    main()
+    
+    from streamlit_keycloak import login
+    import os
+    
+    keycloak_url = os.environ.get("KEYCLOAK_URL")
+    keycloak_realm = os.environ.get("KEYCLOAK_REALM", "default")
+    keycloak_client_id = os.environ.get("KEYCLOAK_CLIENT_ID")
+    
+    if keycloak_url and keycloak_client_id:
+        keycloak = login(
+            url=keycloak_url,
+            realm=keycloak_realm,
+            client_id=keycloak_client_id,
+            custom_labels={
+                "labelButton": "Sign in to kvant",
+                "labelLogin": "Please sign in to your kvant account.",
+                "errorNoPopup": "Unable to open the authentication popup. Allow popups and refresh the page to proceed.",
+                "errorPopupClosed": "Authentication popup was closed manually.",
+                "errorFatal": "Unable to connect to Keycloak using the current configuration."   
+            },
+            auto_refresh=True,
+        )
+
+        if keycloak.authenticated:
+            st.session_state['access_token'] = keycloak.access_token
+            main()
+    # TBD - add other authentications
+    else:
+        main()

llama_stack/distribution/ui/modules/api.py

@@ -7,11 +7,13 @@
 import os
 
 from llama_stack_client import LlamaStackClient
+from llama_stack.distribution.ui.app import get_access_token
 
 
 class LlamaStackApi:
     def __init__(self):
         self.client = LlamaStackClient(
+            api_key=get_access_token(),
             base_url=os.environ.get("LLAMA_STACK_ENDPOINT", "http://localhost:8321"),
             provider_data={
                 "fireworks_api_key": os.environ.get("FIREWORKS_API_KEY", ""),
@@ -28,5 +30,3 @@ class LlamaStackApi:
             scoring_params = {fn_id: None for fn_id in scoring_function_ids}
         return self.client.scoring.score(input_rows=[row], scoring_functions=scoring_params)
 
-
-llama_stack_api = LlamaStackApi()

llama_stack/distribution/ui/page/distribution/datasets.py

@@ -6,13 +6,13 @@
 
 import streamlit as st
 
-from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.api import LlamaStackApi
 
 
 def datasets():
     st.header("Datasets")
 
-    datasets_info = {d.identifier: d.to_dict() for d in llama_stack_api.client.datasets.list()}
+    datasets_info = {d.identifier: d.to_dict() for d in LlamaStackApi().client.datasets.list()}
     if len(datasets_info) > 0:
         selected_dataset = st.selectbox("Select a dataset", list(datasets_info.keys()))
         st.json(datasets_info[selected_dataset], expanded=True)

llama_stack/distribution/ui/page/distribution/eval_tasks.py

@@ -6,14 +6,14 @@
 
 import streamlit as st
 
-from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.api import LlamaStackApi
 
 
 def benchmarks():
     # Benchmarks Section
     st.header("Benchmarks")
 
-    benchmarks_info = {d.identifier: d.to_dict() for d in llama_stack_api.client.benchmarks.list()}
+    benchmarks_info = {d.identifier: d.to_dict() for d in LlamaStackApi().client.benchmarks.list()}
 
     if len(benchmarks_info) > 0:
         selected_benchmark = st.selectbox("Select an eval task", list(benchmarks_info.keys()), key="benchmark_inspect")

llama_stack/distribution/ui/page/distribution/models.py

@@ -6,13 +6,13 @@
 
 import streamlit as st
 
-from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.api import LlamaStackApi
 
 
 def models():
     # Models Section
     st.header("Models")
-    models_info = {m.identifier: m.to_dict() for m in llama_stack_api.client.models.list()}
+    models_info = {m.identifier: m.to_dict() for m in LlamaStackApi().client.models.list()}
 
     selected_model = st.selectbox("Select a model", list(models_info.keys()))
     st.json(models_info[selected_model])

llama_stack/distribution/ui/page/distribution/providers.py

@@ -6,12 +6,12 @@
 
 import streamlit as st
 
-from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.api import LlamaStackApi
 
 
 def providers():
     st.header("🔍 API Providers")
-    apis_providers_lst = llama_stack_api.client.providers.list()
+    apis_providers_lst = LlamaStackApi().client.providers.list()
     api_to_providers = {}
     for api_provider in apis_providers_lst:
         if api_provider.api in api_to_providers:

llama_stack/distribution/ui/page/distribution/scoring_functions.py

@@ -6,13 +6,13 @@
 
 import streamlit as st
 
-from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.api import LlamaStackApi
 
 
 def scoring_functions():
     st.header("Scoring Functions")
 
-    scoring_functions_info = {s.identifier: s.to_dict() for s in llama_stack_api.client.scoring_functions.list()}
+    scoring_functions_info = {s.identifier: s.to_dict() for s in LlamaStackApi().client.scoring_functions.list()}
 
     selected_scoring_function = st.selectbox("Select a scoring function", list(scoring_functions_info.keys()))
     st.json(scoring_functions_info[selected_scoring_function], expanded=True)

llama_stack/distribution/ui/page/distribution/shields.py

@@ -6,14 +6,14 @@
 
 import streamlit as st
 
-from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.api import LlamaStackApi
 
 
 def shields():
     # Shields Section
     st.header("Shields")
 
-    shields_info = {s.identifier: s.to_dict() for s in llama_stack_api.client.shields.list()}
+    shields_info = {s.identifier: s.to_dict() for s in LlamaStackApi().client.shields.list()}
 
     selected_shield = st.selectbox("Select a shield", list(shields_info.keys()))
     st.json(shields_info[selected_shield])

llama_stack/distribution/ui/page/distribution/vector_dbs.py

@@ -6,12 +6,12 @@
 
 import streamlit as st
 
-from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.api import LlamaStackApi
 
 
 def vector_dbs():
     st.header("Vector Databases")
-    vector_dbs_info = {v.identifier: v.to_dict() for v in llama_stack_api.client.vector_dbs.list()}
+    vector_dbs_info = {v.identifier: v.to_dict() for v in LlamaStackApi().client.vector_dbs.list()}
 
     if len(vector_dbs_info) > 0:
         selected_vector_db = st.selectbox("Select a vector database", list(vector_dbs_info.keys()))

llama_stack/distribution/ui/page/evaluations/app_eval.py

@@ -9,7 +9,7 @@ import json
 import pandas as pd
 import streamlit as st
 
-from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.api import LlamaStackApi
 from llama_stack.distribution.ui.modules.utils import process_dataset
 
 
@@ -39,7 +39,7 @@ def application_evaluation_page():
 
     # Select Scoring Functions to Run Evaluation On
     st.subheader("Select Scoring Functions")
-    scoring_functions = llama_stack_api.client.scoring_functions.list()
+    scoring_functions = LlamaStackApi().client.scoring_functions.list()
     scoring_functions = {sf.identifier: sf for sf in scoring_functions}
     scoring_functions_names = list(scoring_functions.keys())
     selected_scoring_functions = st.multiselect(
@@ -48,7 +48,7 @@ def application_evaluation_page():
         help="Choose one or more scoring functions.",
     )
 
-    available_models = llama_stack_api.client.models.list()
+    available_models = LlamaStackApi().client.models.list()
     available_models = [m.identifier for m in available_models]
 
     scoring_params = {}
@@ -108,7 +108,7 @@ def application_evaluation_page():
                 progress_bar.progress(progress, text=progress_text)
 
                 # Run evaluation for current row
-                score_res = llama_stack_api.run_scoring(
+                score_res = LlamaStackApi().run_scoring(
                     r,
                     scoring_function_ids=selected_scoring_functions,
                     scoring_params=scoring_params,

llama_stack/distribution/ui/page/evaluations/native_eval.py

@@ -9,13 +9,13 @@ import json
 import pandas as pd
 import streamlit as st
 
-from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.api import LlamaStackApi
 
 
 def select_benchmark_1():
     # Select Benchmarks
     st.subheader("1. Choose An Eval Task")
-    benchmarks = llama_stack_api.client.benchmarks.list()
+    benchmarks = LlamaStackApi().client.benchmarks.list()
     benchmarks = {et.identifier: et for et in benchmarks}
     benchmarks_names = list(benchmarks.keys())
     selected_benchmark = st.selectbox(
@@ -47,7 +47,7 @@ def define_eval_candidate_2():
         # Define Eval Candidate
         candidate_type = st.radio("Candidate Type", ["model", "agent"])
 
-        available_models = llama_stack_api.client.models.list()
+        available_models = LlamaStackApi().client.models.list()
         available_models = [model.identifier for model in available_models]
         selected_model = st.selectbox(
             "Choose a model",
@@ -167,7 +167,7 @@ def run_evaluation_3():
     eval_candidate = st.session_state["eval_candidate"]
 
     dataset_id = benchmarks[selected_benchmark].dataset_id
-    rows = llama_stack_api.client.datasets.iterrows(
+    rows = LlamaStackApi().client.datasets.iterrows(
         dataset_id=dataset_id,
     )
     total_rows = len(rows.data)
@@ -208,7 +208,7 @@ def run_evaluation_3():
             progress = i / len(rows)
             progress_bar.progress(progress, text=progress_text)
             # Run evaluation for current row
-            eval_res = llama_stack_api.client.eval.evaluate_rows(
+            eval_res = LlamaStackApi().client.eval.evaluate_rows(
                 benchmark_id=selected_benchmark,
                 input_rows=[r],
                 scoring_functions=benchmarks[selected_benchmark].scoring_functions,

llama_stack/distribution/ui/page/playground/chat.py

@@ -6,12 +6,12 @@
 
 import streamlit as st
 
-from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.api import LlamaStackApi
 
 # Sidebar configurations
 with st.sidebar:
     st.header("Configuration")
-    available_models = llama_stack_api.client.models.list()
+    available_models = LlamaStackApi().client.models.list()
     available_models = [model.identifier for model in available_models if model.model_type == "llm"]
     selected_model = st.selectbox(
         "Choose a model",
@@ -103,7 +103,7 @@ if prompt := st.chat_input("Example: What is Llama Stack?"):
         else:
             strategy = {"type": "greedy"}
 
-        response = llama_stack_api.client.inference.chat_completion(
+        response = LlamaStackApi().client.inference.chat_completion(
             messages=[
                 {"role": "system", "content": system_prompt},
                 {"role": "user", "content": prompt},

llama_stack/distribution/ui/page/playground/rag.py

@@ -10,7 +10,7 @@ import streamlit as st
 from llama_stack_client import Agent, AgentEventLogger, RAGDocument
 
 from llama_stack.apis.common.content_types import ToolCallDelta
-from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.api import LlamaStackApi
 from llama_stack.distribution.ui.modules.utils import data_url_from_file
 
 
@@ -57,14 +57,14 @@ def rag_chat_page():
                     for i, uploaded_file in enumerate(uploaded_files)
                 ]
 
-                providers = llama_stack_api.client.providers.list()
+                providers = LlamaStackApi().client.providers.list()
                 vector_io_provider = None
 
                 for x in providers:
                     if x.api == "vector_io":
                         vector_io_provider = x.provider_id
 
-                llama_stack_api.client.vector_dbs.register(
+                LlamaStackApi().client.vector_dbs.register(
                     vector_db_id=vector_db_name,  # Use the user-provided name
                     embedding_dimension=384,
                     embedding_model="all-MiniLM-L6-v2",
@@ -72,7 +72,7 @@ def rag_chat_page():
                 )
 
                 # insert documents using the custom vector db name
-                llama_stack_api.client.tool_runtime.rag_tool.insert(
+                LlamaStackApi().client.tool_runtime.rag_tool.insert(
                     vector_db_id=vector_db_name,  # Use the user-provided name
                     documents=documents,
                     chunk_size_in_tokens=512,
@@ -93,7 +93,7 @@ def rag_chat_page():
         )
 
         # select memory banks
-        vector_dbs = llama_stack_api.client.vector_dbs.list()
+        vector_dbs = LlamaStackApi().client.vector_dbs.list()
         vector_dbs = [vector_db.identifier for vector_db in vector_dbs]
         selected_vector_dbs = st.multiselect(
             label="Select Document Collections to use in RAG queries",
@@ -103,7 +103,7 @@ def rag_chat_page():
         )
 
         st.subheader("Inference Parameters", divider=True)
-        available_models = llama_stack_api.client.models.list()
+        available_models = LlamaStackApi().client.models.list()
         available_models = [model.identifier for model in available_models if model.model_type == "llm"]
         selected_model = st.selectbox(
             label="Choose a model",
@@ -167,7 +167,7 @@ def rag_chat_page():
     @st.cache_resource
     def create_agent():
         return Agent(
-            llama_stack_api.client,
+            LlamaStackApi().client,
             model=selected_model,
             instructions=system_prompt,
             sampling_params={
@@ -232,7 +232,7 @@ def rag_chat_page():
             st.session_state.messages.append({"role": "system", "content": system_prompt})
 
         # Query the vector DB
-        rag_response = llama_stack_api.client.tool_runtime.rag_tool.query(
+        rag_response = LlamaStackApi().client.tool_runtime.rag_tool.query(
             content=prompt, vector_db_ids=list(selected_vector_dbs)
         )
         prompt_context = rag_response.content
@@ -251,7 +251,7 @@ def rag_chat_page():
 
             # Run inference directly
             st.session_state.messages.append({"role": "user", "content": extended_prompt})
-            response = llama_stack_api.client.inference.chat_completion(
+            response = LlamaStackApi().client.inference.chat_completion(
                 messages=st.session_state.messages,
                 model_id=selected_model,
                 sampling_params={

llama_stack/distribution/ui/page/playground/tools.py

@@ -13,7 +13,7 @@ from llama_stack_client import Agent
 from llama_stack_client.lib.agents.react.agent import ReActAgent
 from llama_stack_client.lib.agents.react.tool_parser import ReActOutput
 
-from llama_stack.distribution.ui.modules.api import llama_stack_api
+from llama_stack.distribution.ui.modules.api import LlamaStackApi
 
 
 class AgentType(enum.Enum):
@@ -24,7 +24,7 @@ class AgentType(enum.Enum):
 def tool_chat_page():
     st.title("🛠 Tools")
 
-    client = llama_stack_api.client
+    client = LlamaStackApi().client
     models = client.models.list()
     model_list = [model.identifier for model in models if model.api_model_type == "llm"]
 
@@ -55,7 +55,7 @@ def tool_chat_page():
         )
 
         if "builtin::rag" in toolgroup_selection:
-            vector_dbs = llama_stack_api.client.vector_dbs.list() or []
+            vector_dbs = LlamaStackApi().client.vector_dbs.list() or []
             if not vector_dbs:
                 st.info("No vector databases available for selection.")
             vector_dbs = [vector_db.identifier for vector_db in vector_dbs]

llama_stack/distribution/ui/requirements.txt

@@ -1,5 +1,5 @@
-llama-stack>=0.2.1
+llama-stack-client>=0.2.9
-llama-stack-client>=0.2.1
 pandas
 streamlit
 streamlit-option-menu
+streamlit-keycloak

llama_stack/templates/dependencies.json

@@ -0,0 +1,904 @@
+{
+  "bedrock": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "boto3",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn"
+  ],
+  "cerebras": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "cerebras_cloud_sdk",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "ci-tests": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "fastapi",
+    "fire",
+    "fireworks-ai",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "sqlite-vec",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "dell": [
+    "aiohttp",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "huggingface_hub",
+    "langdetect",
+    "matplotlib",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "fireworks": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "fireworks-ai",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "groq": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "litellm",
+    "matplotlib",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn"
+  ],
+  "hf-endpoint": [
+    "aiohttp",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "huggingface_hub",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn"
+  ],
+  "hf-serverless": [
+    "aiohttp",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "huggingface_hub",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "kvant": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "llama_api": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "litellm",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "sqlite-vec",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "meta-reference-gpu": [
+    "accelerate",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "fairscale",
+    "faiss-cpu",
+    "fastapi",
+    "fbgemm-gpu-genai==1.1.2",
+    "fire",
+    "httpx",
+    "langdetect",
+    "lm-format-enforcer",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentence-transformers",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "torch",
+    "torchao==0.8.0",
+    "torchvision",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "zmq"
+  ],
+  "nvidia": [
+    "aiohttp",
+    "aiosqlite",
+    "blobfile",
+    "chardet",
+    "datasets",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "matplotlib",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "uvicorn"
+  ],
+  "ollama": [
+    "aiohttp",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "ollama",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "peft",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "torch",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "trl",
+    "uvicorn"
+  ],
+  "open-benchmark": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "litellm",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "sqlite-vec",
+    "together",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn"
+  ],
+  "passthrough": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "remote-vllm": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "sambanova": [
+    "aiosqlite",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "litellm",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "starter": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "fastapi",
+    "fire",
+    "fireworks-ai",
+    "httpx",
+    "langdetect",
+    "litellm",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "sqlite-vec",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "tgi": [
+    "aiohttp",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "huggingface_hub",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "together": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "together",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "verification": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "litellm",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "sqlite-vec",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "vllm-gpu": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "vllm",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "watsonx": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "ibm_watson_machine_learning",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlalchemy[asyncio]",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ]
+}

llama_stack/templates/kvant/__init__.py

@@ -0,0 +1,7 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from .kvant import get_distribution_template  # noqa: F401

llama_stack/templates/kvant/build.yaml

@@ -0,0 +1,35 @@
+version: '2'
+distribution_spec:
+  description: distribution for kvant cloud
+  providers:
+    inference:
+    - remote::vllm
+    - inline::sentence-transformers
+    vector_io:
+    - inline::faiss
+    - remote::chromadb
+    - remote::pgvector
+    safety:
+    - inline::llama-guard
+    agents:
+    - inline::meta-reference
+    telemetry:
+    - inline::meta-reference
+    eval:
+    - inline::meta-reference
+    datasetio:
+    - remote::huggingface
+    - inline::localfs
+    scoring:
+    - inline::basic
+    - inline::llm-as-judge
+    - inline::braintrust
+    tool_runtime:
+    - remote::brave-search
+    - remote::tavily-search
+    - remote::wolfram-alpha
+    - inline::rag-runtime
+    - remote::model-context-protocol
+image_type: conda
+additional_pip_packages:
+- sqlalchemy[asyncio]

llama_stack/templates/kvant/kvant.py

@@ -0,0 +1,136 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from pathlib import Path
+
+from llama_stack.apis.models.models import ModelType
+from llama_stack.distribution.datatypes import (
+    ModelInput,
+    Provider,
+    ShieldInput,
+    ToolGroupInput,
+)
+from llama_stack.providers.inline.inference.sentence_transformers import (
+    SentenceTransformersInferenceConfig,
+)
+from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
+from llama_stack.providers.remote.inference.passthrough.config import (
+    PassthroughImplConfig,
+)
+from llama_stack.providers.utils.inference.model_registry import ProviderModelEntry
+from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
+
+
+def get_distribution_template() -> DistributionTemplate:
+    providers = {
+        "inference": ["remote::openai", "inline::sentence-transformers"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "safety": ["inline::llama-guard"],
+        "agents": ["inline::meta-reference"],
+        "telemetry": ["inline::meta-reference"],
+        "eval": ["inline::meta-reference"],
+        "datasetio": ["remote::huggingface", "inline::localfs"],
+        "scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
+        "tool_runtime": [
+            "remote::brave-search",
+            "remote::tavily-search",
+            "remote::wolfram-alpha",
+            "inline::rag-runtime",
+            "remote::model-context-protocol",
+        ],
+    }
+
+    name = "kvant"
+
+    inference_provider = Provider(
+        provider_id="openai",
+        provider_type="remote::openai",
+        config=PassthroughImplConfig.sample_run_config(),
+    )
+    embedding_provider = Provider(
+        provider_id="sentence-transformers",
+        provider_type="inline::sentence-transformers",
+        config=SentenceTransformersInferenceConfig.sample_run_config(),
+    )
+    vector_io_provider = Provider(
+        provider_id="faiss",
+        provider_type="inline::faiss",
+        config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
+    )
+
+    default_models = [
+        ModelInput(
+            metadata={},
+            model_id="inference-llama4-maverick",
+            provider_id="openai",
+            provider_model_id="inference-llama4-maverick",
+            model_type=ModelType.llm,
+        ),
+    ]
+
+    embedding_model = ModelInput(
+        model_id="all-MiniLM-L6-v2",
+        provider_id="sentence-transformers",
+        model_type=ModelType.embedding,
+        metadata={
+            "embedding_dimension": 384,
+        },
+    )
+    default_tool_groups = [
+        ToolGroupInput(
+            toolgroup_id="builtin::websearch",
+            provider_id="tavily-search",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::wolfram_alpha",
+            provider_id="wolfram-alpha",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::rag",
+            provider_id="rag-runtime",
+        ),
+    ]
+
+    return DistributionTemplate(
+        name=name,
+        distro_type="self_hosted",
+        description="Use Passthrough hosted llama-stack endpoint for LLM inference",
+        container_image=None,
+        providers=providers,
+        available_models_by_provider={
+            "openai": [
+                ProviderModelEntry(
+                    provider_model_id="inference-llama4-maverick",
+                    model_type=ModelType.llm,
+                ),
+            ],
+        },
+        run_configs={
+            "run.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": [inference_provider, embedding_provider],
+                    "vector_io": [vector_io_provider],
+                },
+                default_models=default_models + [embedding_model],
+                default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
+                default_tool_groups=default_tool_groups,
+            ),
+        },
+        run_config_env_vars={
+            "LLAMA_STACK_PORT": (
+                "8321",
+                "Port for the Llama Stack distribution server",
+            ),
+            "OPENAI_API_KEY": (
+                "",
+                "kvant maas API Key",
+            ),
+            "OPENAI_BASE_URL": (
+                "https://maas.kvant.cloud",
+                "kvant maas URL",
+            ),
+        },
+    )

llama_stack/templates/kvant/run.yaml

@@ -0,0 +1,170 @@
+version: '2'
+image_name: kvant
+apis:
+- agents
+- datasetio
+- eval
+- inference
+- safety
+- scoring
+- telemetry
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: kvant
+    provider_type: remote::vllm
+    config:
+      url: ${env.VLLM_URL:https://maas.ai-2.kvant.cloud/v1}
+      max_tokens: ${env.VLLM_MAX_TOKENS:400000}
+      api_token: ${env.VLLM_API_TOKEN:fake}
+      tls_verify: ${env.VLLM_TLS_VERIFY:true}
+  - provider_id: sentence-transformers
+    provider_type: inline::sentence-transformers
+    config: {}
+  vector_io:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/faiss_store.db
+  safety:
+  - provider_id: llama-guard
+    provider_type: inline::llama-guard
+    config:
+      excluded_categories: []
+  agents:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      persistence_store:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/agents_store.db
+      responses_store:
+        type: sqlite
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/responses_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/trace_store.db
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/meta_reference_eval.db
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/huggingface_datasetio.db
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/localfs_datasetio.db
+  scoring:
+  - provider_id: basic
+    provider_type: inline::basic
+    config: {}
+  - provider_id: llm-as-judge
+    provider_type: inline::llm-as-judge
+    config: {}
+  - provider_id: braintrust
+    provider_type: inline::braintrust
+    config:
+      openai_api_key: ${env.OPENAI_API_KEY:}
+  tool_runtime:
+  - provider_id: brave-search
+    provider_type: remote::brave-search
+    config:
+      api_key: ${env.BRAVE_SEARCH_API_KEY:}
+      max_results: 3
+  - provider_id: tavily-search
+    provider_type: remote::tavily-search
+    config:
+      api_key: ${env.TAVILY_SEARCH_API_KEY:}
+      max_results: 3
+  - provider_id: wolfram-alpha
+    provider_type: remote::wolfram-alpha
+    config:
+      api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
+  - provider_id: rag-runtime
+    provider_type: inline::rag-runtime
+    config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
+metadata_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/registry.db
+inference_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/kvant}/inference_store.db
+models:
+- metadata: {}
+  model_id: Llama-4-Maverick-17B-128E-Instruct-FP8
+  provider_id: kvant
+  provider_model_id: inference-llama4-maverick
+  model_type: llm
+- metadata:
+    embedding_dimension: 1024
+    context_length: 8192
+  model_id: inference-bge-m3
+  provider_id: kvant
+  model_type: embedding
+- metadata:
+    embedding_dimension: 384
+  model_id: all-MiniLM-L6-v2
+  provider_id: sentence-transformers
+  model_type: embedding
+shields:
+- shield_id: meta-llama/Llama-Guard-3-8B
+vector_dbs: []
+# - vector_db_id: test-bge
+#   embedding_model: inference-bge-m3
+#   embedding_dimension: 1024
+#   provider_id: faiss
+# - vector_db_id: test-MiniLM-L6-v2
+#   embedding_model: all-MiniLM-L6-v2
+#   embedding_dimension: 384
+#   provider_id: faiss
+datasets: []
+scoring_fns: []
+benchmarks: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::wolfram_alpha
+  provider_id: wolfram-alpha
+- toolgroup_id: builtin::rag
+  provider_id: rag-runtime
+server:
+  port: 8321
+  auth:
+    provider_type: "oauth2_token"
+    config:
+      jwks:
+      introspection:
+        url: ${env.KEYCLOAK_INSTROSPECT:https://iam.phoenix-systems.ch/realms/kvant/protocol/openid-connect/token/introspect} 
+        client_id: ${env.KEYCLOAK_CLIENT_ID:llama-stack}
+        client_secret: ${env.KEYCLOAK_CLIENT_SECRET}
+      claims_mapping:
+        sub: projects
+        scope: roles
+        #groups: teams
+        customer/id: teams
+        aud: namespaces

playground_start_local.sh

@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+
+export KEYCLOAK_URL="https://iam.phoenix-systems.ch"
+export KEYCLOAK_REALM="kvant"
+export KEYCLOAK_CLIENT_ID="llama-stack-playground"
+
+uv run --with ".[ui]" streamlit run llama_stack/distribution/ui/app.py

pyproject.toml

@@ -49,6 +49,7 @@ ui = [
     "pandas",
     "llama-stack-client>=0.2.9",
     "streamlit-option-menu",
+    "streamlit-keycloak",
 ]
 
 [dependency-groups]