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>

llama_stack/templates/fireworks/__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 .fireworks import get_distribution_template  # noqa: F401

llama_stack/templates/fireworks/build.yaml

@@ -1,38 +0,0 @@
-version: 2
-distribution_spec:
-  description: Use Fireworks.AI for running LLM inference
-  providers:
-    inference:
-    - remote::fireworks
-    - 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
-    files:
-    - inline::localfs
-    tool_runtime:
-    - remote::brave-search
-    - remote::tavily-search
-    - remote::wolfram-alpha
-    - inline::rag-runtime
-    - remote::model-context-protocol
-image_type: conda
-additional_pip_packages:
-- aiosqlite
-- sqlalchemy[asyncio]

llama_stack/templates/fireworks/doc_template.md

@@ -1,69 +0,0 @@
----
-orphan: true
----
-# Fireworks 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 Fireworks API Key. You can get one by visiting [fireworks.ai](https://fireworks.ai/).
-
-
-## Running Llama Stack with Fireworks
-
-You can do this via Conda (build code) or Docker which has a pre-built image.
-
-### Via Docker
-
-This method allows you to get started quickly without having to build the distribution code.
-
-```bash
-LLAMA_STACK_PORT=8321
-docker run \
-  -it \
-  --pull always \
-  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-  llamastack/distribution-{{ name }} \
-  --port $LLAMA_STACK_PORT \
-  --env FIREWORKS_API_KEY=$FIREWORKS_API_KEY
-```
-
-### Via Conda
-
-```bash
-llama stack build --template fireworks --image-type conda
-llama stack run ./run.yaml \
-  --port $LLAMA_STACK_PORT \
-  --env FIREWORKS_API_KEY=$FIREWORKS_API_KEY
-```

llama_stack/templates/fireworks/fireworks.py

@@ -1,177 +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.files.localfs.config import LocalfsFilesImplConfig
-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.fireworks.config import FireworksImplConfig
-from llama_stack.providers.remote.inference.fireworks.models import MODEL_ENTRIES
-from llama_stack.templates.template import (
-    DistributionTemplate,
-    RunConfigSettings,
-    get_model_registry,
-)
-
-
-def get_distribution_template() -> DistributionTemplate:
-    providers = {
-        "inference": ["remote::fireworks", "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"],
-        "files": ["inline::localfs"],
-        "tool_runtime": [
-            "remote::brave-search",
-            "remote::tavily-search",
-            "remote::wolfram-alpha",
-            "inline::rag-runtime",
-            "remote::model-context-protocol",
-        ],
-    }
-
-    name = "fireworks"
-
-    inference_provider = Provider(
-        provider_id="fireworks",
-        provider_type="remote::fireworks",
-        config=FireworksImplConfig.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}"),
-    )
-    files_provider = Provider(
-        provider_id="meta-reference-files",
-        provider_type="inline::localfs",
-        config=LocalfsFilesImplConfig.sample_run_config(f"~/.llama/distributions/{name}"),
-    )
-
-    available_models = {
-        "fireworks": MODEL_ENTRIES,
-    }
-    default_models = get_model_registry(available_models)
-
-    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 Fireworks.AI for running LLM inference",
-        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_provider],
-                    "files": [files_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-with-safety.yaml": RunConfigSettings(
-                provider_overrides={
-                    "inference": [
-                        inference_provider,
-                        embedding_provider,
-                    ],
-                    "vector_io": [vector_io_provider],
-                    "files": [files_provider],
-                    "safety": [
-                        Provider(
-                            provider_id="llama-guard",
-                            provider_type="inline::llama-guard",
-                            config={},
-                        ),
-                        Provider(
-                            provider_id="llama-guard-vision",
-                            provider_type="inline::llama-guard",
-                            config={},
-                        ),
-                        Provider(
-                            provider_id="code-scanner",
-                            provider_type="inline::code-scanner",
-                            config={},
-                        ),
-                    ],
-                },
-                default_models=[
-                    *default_models,
-                    embedding_model,
-                ],
-                default_shields=[
-                    ShieldInput(
-                        shield_id="meta-llama/Llama-Guard-3-8B",
-                        provider_id="llama-guard",
-                    ),
-                    ShieldInput(
-                        shield_id="meta-llama/Llama-Guard-3-11B-Vision",
-                        provider_id="llama-guard-vision",
-                    ),
-                    ShieldInput(
-                        shield_id="CodeScanner",
-                        provider_id="code-scanner",
-                    ),
-                ],
-                default_tool_groups=default_tool_groups,
-            ),
-        },
-        run_config_env_vars={
-            "LLAMA_STACK_PORT": (
-                "8321",
-                "Port for the Llama Stack distribution server",
-            ),
-            "FIREWORKS_API_KEY": (
-                "",
-                "Fireworks.AI API Key",
-            ),
-        },
-    )

llama_stack/templates/fireworks/remote-hosted-report.md

@@ -1,45 +0,0 @@
-# Report for fireworks distribution
-
-## Supported Models
-| Model Descriptor | fireworks |
-|:---|:---|
-| meta-llama/Llama-3-8B-Instruct | ❌ |
-| meta-llama/Llama-3-70B-Instruct | ❌ |
-| meta-llama/Llama-3.1-8B-Instruct | ❌ |
-| meta-llama/Llama-3.1-70B-Instruct | ❌ |
-| meta-llama/Llama-3.1-405B-Instruct-FP8 | ❌ |
-| meta-llama/Llama-3.2-1B-Instruct | ❌ |
-| meta-llama/Llama-3.2-3B-Instruct | ❌ |
-| meta-llama/Llama-3.2-11B-Vision-Instruct | ❌ |
-| meta-llama/Llama-3.2-90B-Vision-Instruct | ❌ |
-| meta-llama/Llama-3.3-70B-Instruct | ❌ |
-| meta-llama/Llama-Guard-3-11B-Vision | ❌ |
-| meta-llama/Llama-Guard-3-1B | ❌ |
-| meta-llama/Llama-Guard-3-8B | ❌ |
-| meta-llama/Llama-Guard-2-8B | ❌ |
-
-## Inference
-| Model | API | Capability | Test | Status |
-|:----- |:-----|:-----|:-----|:-----|
-| Text | /chat_completion | streaming | test_text_chat_completion_streaming | ❌ |
-| Vision | /chat_completion | streaming | test_image_chat_completion_streaming | ❌ |
-| Vision | /chat_completion | non_streaming | test_image_chat_completion_non_streaming | ❌ |
-| Text | /chat_completion | non_streaming | test_text_chat_completion_non_streaming | ❌ |
-| Text | /chat_completion | tool_calling | test_text_chat_completion_with_tool_calling_and_streaming | ❌ |
-| Text | /chat_completion | tool_calling | test_text_chat_completion_with_tool_calling_and_non_streaming | ❌ |
-| Text | /completion | streaming | test_text_completion_streaming | ❌ |
-| Text | /completion | non_streaming | test_text_completion_non_streaming | ❌ |
-| Text | /completion | structured_output | test_text_completion_structured_output | ❌ |
-
-## Memory:
-| API | Capability | Test | Status |
-|:-----|:-----|:-----|:-----|
-| /insert, /query | inline | test_memory_bank_insert_inline_and_query | ❌ |
-| /insert, /query | url | test_memory_bank_insert_from_url_and_query | ❌ |
-
-## Agents
-| API | Capability | Test | Status |
-|:-----|:-----|:-----|:-----|
-| create_agent_turn | rag | test_rag_agent | ❌ |
-| create_agent_turn | custom_tool | test_custom_tool | ❌ |
-| create_agent_turn | code_execution | test_code_execution | ❌ |

llama_stack/templates/fireworks/run-with-safety.yaml

@@ -1,266 +0,0 @@
-version: 2
-image_name: fireworks
-apis:
-- agents
-- datasetio
-- eval
-- files
-- inference
-- safety
-- scoring
-- telemetry
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: fireworks
-    provider_type: remote::fireworks
-    config:
-      url: https://api.fireworks.ai/inference/v1
-      api_key: ${env.FIREWORKS_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/fireworks}/faiss_store.db
-  safety:
-  - provider_id: llama-guard
-    provider_type: inline::llama-guard
-    config: {}
-  - provider_id: llama-guard-vision
-    provider_type: inline::llama-guard
-    config: {}
-  - provider_id: code-scanner
-    provider_type: inline::code-scanner
-    config: {}
-  agents:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      persistence_store:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/agents_store.db
-      responses_store:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
-      sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/trace_store.db
-  eval:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      kvstore:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/meta_reference_eval.db
-  datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config:
-      kvstore:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/huggingface_datasetio.db
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/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:=}
-  files:
-  - provider_id: meta-reference-files
-    provider_type: inline::localfs
-    config:
-      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/fireworks/files}
-      metadata_store:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/files_metadata.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: 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/fireworks}/registry.db
-inference_store:
-  type: sqlite
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/inference_store.db
-models:
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.1-8B-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.1-70B-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-guard-3-8b
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-guard-3-8b
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-Guard-3-8B
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-guard-3-8b
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-guard-3-11b-vision
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-Guard-3-11B-Vision
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama4-scout-instruct-basic
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
-  model_type: llm
-- metadata:
-    embedding_dimension: 768
-    context_length: 8192
-  model_id: nomic-ai/nomic-embed-text-v1.5
-  provider_id: fireworks
-  provider_model_id: nomic-ai/nomic-embed-text-v1.5
-  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
-  provider_id: llama-guard
-- shield_id: meta-llama/Llama-Guard-3-11B-Vision
-  provider_id: llama-guard-vision
-- shield_id: CodeScanner
-  provider_id: code-scanner
-vector_dbs: []
-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

llama_stack/templates/fireworks/run.yaml

@@ -1,256 +0,0 @@
-version: 2
-image_name: fireworks
-apis:
-- agents
-- datasetio
-- eval
-- files
-- inference
-- safety
-- scoring
-- telemetry
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: fireworks
-    provider_type: remote::fireworks
-    config:
-      url: https://api.fireworks.ai/inference/v1
-      api_key: ${env.FIREWORKS_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/fireworks}/faiss_store.db
-  safety:
-  - provider_id: llama-guard
-    provider_type: inline::llama-guard
-    config:
-      excluded_categories: []
-  agents:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      persistence_store:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/agents_store.db
-      responses_store:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/responses_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
-      sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
-      sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/trace_store.db
-  eval:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      kvstore:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/meta_reference_eval.db
-  datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config:
-      kvstore:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/huggingface_datasetio.db
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/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:=}
-  files:
-  - provider_id: meta-reference-files
-    provider_type: inline::localfs
-    config:
-      storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/fireworks/files}
-      metadata_store:
-        type: sqlite
-        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/files_metadata.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: 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/fireworks}/registry.db
-inference_store:
-  type: sqlite
-  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/fireworks}/inference_store.db
-models:
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.1-8B-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.1-70B-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.2-3B-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-3.3-70B-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-guard-3-8b
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-guard-3-8b
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-Guard-3-8B
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-guard-3-8b
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama-guard-3-11b-vision
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-Guard-3-11B-Vision
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama4-scout-instruct-basic
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
-  model_type: llm
-- metadata: {}
-  model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
-  model_type: llm
-- metadata: {}
-  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
-  provider_id: fireworks
-  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
-  model_type: llm
-- metadata:
-    embedding_dimension: 768
-    context_length: 8192
-  model_id: nomic-ai/nomic-embed-text-v1.5
-  provider_id: fireworks
-  provider_model_id: nomic-ai/nomic-embed-text-v1.5
-  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: []
-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