feat: consolidate most distros into "starter" (#2516)

# What does this PR do? * Removes a bunch of distros * Removed distros were added into the "starter" distribution * Doc for "starter" has been added * Partially reverts https://github.com/meta-llama/llama-stack/pull/2482 since inference providers are disabled by default and can be turned on manually via env variable. * Disables safety in starter distro Closes: https://github.com/meta-llama/llama-stack/issues/2502. ~Needs: https://github.com/meta-llama/llama-stack/pull/2482 for Ollama to work properly in the CI.~ TODO: - [ ] We can only update `install.sh` when we get a new release. - [x] Update providers documentation - [ ] Update notebooks to reference starter instead of ollama Signed-off-by: Sébastien Han <seb@redhat.com>
2025-07-27 14:38:49 +00:00 · 2025-07-04 15:58:03 +02:00 · 2025-07-04 15:58:03 +02:00 · c4349f532b
commit c4349f532b
parent f77d4d91f5
132 changed files with 1009 additions and 10845 deletions
--- a/llama_stack/templates/sambanova/init.py
+++ b/llama_stack/templates/sambanova/init.py
@ -1,7 +0,0 @@
-# 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 .sambanova import get_distribution_template  # noqa: F401
--- a/llama_stack/templates/sambanova/build.yaml
+++ b/llama_stack/templates/sambanova/build.yaml
@ -1,27 +0,0 @@
-version: 2
-distribution_spec:
-  description: Use SambaNova for running LLM inference and safety
-  providers:
-    inference:
-    - remote::sambanova
-    - inline::sentence-transformers
-    vector_io:
-    - inline::faiss
-    - remote::chromadb
-    - remote::pgvector
-    safety:
-    - remote::sambanova
-    agents:
-    - inline::meta-reference
-    telemetry:
-    - inline::meta-reference
-    tool_runtime:
-    - remote::brave-search
-    - remote::tavily-search
-    - inline::rag-runtime
-    - remote::model-context-protocol
-    - remote::wolfram-alpha
-image_type: conda
-additional_pip_packages:
- aiosqlite
- sqlalchemy[asyncio]
--- a/llama_stack/templates/sambanova/doc_template.md
+++ b/llama_stack/templates/sambanova/doc_template.md
@ -1,80 +0,0 @@
---
-orphan: true
---
-# SambaNova Distribution
-
-```{toctree}
-:maxdepth: 2
-:hidden:
-
-self
-```
-
-The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
-
-{{ providers_table }}
-
-{% if run_config_env_vars %}
-### Environment Variables
-
-The following environment variables can be configured:
-
-{% for var, (default_value, description) in run_config_env_vars.items() %}
- `{{ var }}`: {{ description }} (default: `{{ default_value }}`)
-{% endfor %}
-{% endif %}
-
-{% if default_models %}
-### Models
-
-The following models are available by default:
-
-{% for model in default_models %}
- `{{ model.model_id }} {{ model.doc_string }}`
-{% endfor %}
-{% endif %}
-
-
-### Prerequisite: API Keys
-
-Make sure you have access to a SambaNova API Key. You can get one by visiting [SambaNova.ai](http://cloud.sambanova.ai?utm_source=llamastack&utm_medium=external&utm_campaign=cloud_signup).
-
-
-## Running Llama Stack with SambaNova
-
-You can do this via Conda (build code) or Docker which has a pre-built image.
-
-
-### Via Docker
-
-```bash
-LLAMA_STACK_PORT=8321
-llama stack build --template sambanova --image-type container
-docker run \
-  -it \
-  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-  -v ~/.llama:/root/.llama \
-  distribution-{{ name }} \
-  --port $LLAMA_STACK_PORT \
-  --env SAMBANOVA_API_KEY=$SAMBANOVA_API_KEY
-```
-
-
-### Via Venv
-
-```bash
-llama stack build --template sambanova --image-type venv
-llama stack run --image-type venv ~/.llama/distributions/sambanova/sambanova-run.yaml \
-  --port $LLAMA_STACK_PORT \
-  --env SAMBANOVA_API_KEY=$SAMBANOVA_API_KEY
-```
-
-
-### Via Conda
-
-```bash
-llama stack build --template sambanova --image-type conda
-llama stack run --image-type conda ~/.llama/distributions/sambanova/sambanova-run.yaml \
-  --port $LLAMA_STACK_PORT \
-  --env SAMBANOVA_API_KEY=$SAMBANOVA_API_KEY
-```
--- a/llama_stack/templates/sambanova/run.yaml
+++ b/llama_stack/templates/sambanova/run.yaml
@ -1,212 +0,0 @@
-version: 2
-image_name: sambanova
-apis:
- agents
- inference
- safety
- telemetry
- tool_runtime
- vector_io
-providers:
-  inference:
-  - provider_id: sambanova
-    provider_type: remote::sambanova
-    config:
-      url: https://api.sambanova.ai/v1
-      api_key: ${env.SAMBANOVA_API_KEY}
-  - provider_id: sentence-transformers
-    provider_type: inline::sentence-transformers
-    config: {}
-  vector_io:
-  - provider_id: faiss
-    provider_type: inline::faiss
-    config:
-      kvstore:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/sambanova}/faiss_store.db
-  - provider_id: ${env.ENABLE_CHROMADB:+chromadb}
-    provider_type: remote::chromadb
-    config:
-      url: ${env.CHROMADB_URL:=}
-  - provider_id: ${env.ENABLE_PGVECTOR:+pgvector}
-    provider_type: remote::pgvector
-    config:
-      host: ${env.PGVECTOR_HOST:=localhost}
-      port: ${env.PGVECTOR_PORT:=5432}
-      db: ${env.PGVECTOR_DB:=}
-      user: ${env.PGVECTOR_USER:=}
-      password: ${env.PGVECTOR_PASSWORD:=}
-  safety:
-  - provider_id: sambanova
-    provider_type: remote::sambanova
-    config:
-      url: https://api.sambanova.ai/v1
-      api_key: ${env.SAMBANOVA_API_KEY}
-  agents:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      persistence_store:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/sambanova}/agents_store.db
-      responses_store:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/sambanova}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
-      sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/sambanova}/trace_store.db
-  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: {}
-  - provider_id: wolfram-alpha
-    provider_type: remote::wolfram-alpha
-    config:
-      api_key: ${env.WOLFRAM_ALPHA_API_KEY:=}
-metadata_store:
-  type: sqlite
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/sambanova}/registry.db
-inference_store:
-  type: sqlite
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/sambanova}/inference_store.db
-models:
- metadata: {}
-  model_id: sambanova/Meta-Llama-3.1-8B-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-8B-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Meta-Llama-3.1-8B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Meta-Llama-3.1-405B-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
-  provider_id: sambanova
-  provider_model_id: sambanova/Meta-Llama-3.1-405B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Meta-Llama-3.2-1B-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-1B-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Meta-Llama-3.2-1B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Meta-Llama-3.2-3B-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Meta-Llama-3.2-3B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Meta-Llama-3.3-70B-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Meta-Llama-3.3-70B-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Llama-3.2-11B-Vision-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Llama-3.2-11B-Vision-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Llama-3.2-90B-Vision-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Llama-3.2-90B-Vision-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Llama-4-Scout-17B-16E-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
-  provider_id: sambanova
-  provider_model_id: sambanova/Llama-4-Maverick-17B-128E-Instruct
-  model_type: llm
- metadata: {}
-  model_id: sambanova/Meta-Llama-Guard-3-8B
-  provider_id: sambanova
-  provider_model_id: sambanova/Meta-Llama-Guard-3-8B
-  model_type: llm
- metadata: {}
-  model_id: meta-llama/Llama-Guard-3-8B
-  provider_id: sambanova
-  provider_model_id: sambanova/Meta-Llama-Guard-3-8B
-  model_type: llm
- 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
-  provider_shield_id: sambanova/Meta-Llama-Guard-3-8B
- shield_id: sambanova/Meta-Llama-Guard-3-8B
-  provider_shield_id: sambanova/Meta-Llama-Guard-3-8B
-vector_dbs: []
-datasets: []
-scoring_fns: []
-benchmarks: []
-tool_groups:
- toolgroup_id: builtin::websearch
-  provider_id: tavily-search
- toolgroup_id: builtin::rag
-  provider_id: rag-runtime
- toolgroup_id: builtin::wolfram_alpha
-  provider_id: wolfram-alpha
-server:
-  port: 8321
--- a/llama_stack/templates/sambanova/sambanova.py
+++ b/llama_stack/templates/sambanova/sambanova.py
@ -1,147 +0,0 @@
-# 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 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.sambanova import SambaNovaImplConfig
-from llama_stack.providers.remote.inference.sambanova.models import MODEL_ENTRIES
-from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig
-from llama_stack.providers.remote.vector_io.pgvector.config import (
-    PGVectorVectorIOConfig,
-)
-from llama_stack.templates.template import (
-    DistributionTemplate,
-    RunConfigSettings,
-    get_model_registry,
-)
-
-
-def get_distribution_template() -> DistributionTemplate:
-    providers = {
-        "inference": ["remote::sambanova", "inline::sentence-transformers"],
-        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["remote::sambanova"],
-        "agents": ["inline::meta-reference"],
-        "telemetry": ["inline::meta-reference"],
-        "tool_runtime": [
-            "remote::brave-search",
-            "remote::tavily-search",
-            "inline::rag-runtime",
-            "remote::model-context-protocol",
-            "remote::wolfram-alpha",
-        ],
-    }
-    name = "sambanova"
-    inference_provider = Provider(
-        provider_id=name,
-        provider_type=f"remote::{name}",
-        config=SambaNovaImplConfig.sample_run_config(),
-    )
-    embedding_provider = Provider(
-        provider_id="sentence-transformers",
-        provider_type="inline::sentence-transformers",
-        config=SentenceTransformersInferenceConfig.sample_run_config(),
-    )
-    embedding_model = ModelInput(
-        model_id="all-MiniLM-L6-v2",
-        provider_id="sentence-transformers",
-        model_type=ModelType.embedding,
-        metadata={
-            "embedding_dimension": 384,
-        },
-    )
-    vector_io_providers = [
-        Provider(
-            provider_id="faiss",
-            provider_type="inline::faiss",
-            config=FaissVectorIOConfig.sample_run_config(
-                __distro_dir__=f"~/.llama/distributions/{name}",
-            ),
-        ),
-        Provider(
-            provider_id="${env.ENABLE_CHROMADB:+chromadb}",
-            provider_type="remote::chromadb",
-            config=ChromaVectorIOConfig.sample_run_config(url="${env.CHROMADB_URL:=}"),
-        ),
-        Provider(
-            provider_id="${env.ENABLE_PGVECTOR:+pgvector}",
-            provider_type="remote::pgvector",
-            config=PGVectorVectorIOConfig.sample_run_config(
-                db="${env.PGVECTOR_DB:=}",
-                user="${env.PGVECTOR_USER:=}",
-                password="${env.PGVECTOR_PASSWORD:=}",
-            ),
-        ),
-    ]
-
-    available_models = {
-        name: MODEL_ENTRIES,
-    }
-    default_models = get_model_registry(available_models)
-    default_tool_groups = [
-        ToolGroupInput(
-            toolgroup_id="builtin::websearch",
-            provider_id="tavily-search",
-        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::rag",
-            provider_id="rag-runtime",
-        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::wolfram_alpha",
-            provider_id="wolfram-alpha",
-        ),
-    ]
-
-    return DistributionTemplate(
-        name=name,
-        distro_type="self_hosted",
-        description="Use SambaNova for running LLM inference and safety",
-        container_image=None,
-        template_path=Path(__file__).parent / "doc_template.md",
-        providers=providers,
-        available_models_by_provider=available_models,
-        run_configs={
-            "run.yaml": RunConfigSettings(
-                provider_overrides={
-                    "inference": [inference_provider, embedding_provider],
-                    "vector_io": vector_io_providers,
-                },
-                default_models=default_models + [embedding_model],
-                default_shields=[
-                    ShieldInput(
-                        shield_id="meta-llama/Llama-Guard-3-8B", provider_shield_id="sambanova/Meta-Llama-Guard-3-8B"
-                    ),
-                    ShieldInput(
-                        shield_id="sambanova/Meta-Llama-Guard-3-8B",
-                        provider_shield_id="sambanova/Meta-Llama-Guard-3-8B",
-                    ),
-                ],
-                default_tool_groups=default_tool_groups,
-            ),
-        },
-        run_config_env_vars={
-            "LLAMASTACK_PORT": (
-                "8321",
-                "Port for the Llama Stack distribution server",
-            ),
-            "SAMBANOVA_API_KEY": (
-                "",
-                "SambaNova API Key",
-            ),
-        },
-    )