Auto-generate distro yamls + docs (#468)

# What does this PR do?

Automatically generates
- build.yaml
- run.yaml
- run-with-safety.yaml
- parts of markdown docs

for the distributions.

## Test Plan

At this point, this only updates the YAMLs and the docs. Some testing
(especially with ollama and vllm) has been performed but needs to be
much more tested.

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

llama_stack/templates/fireworks/build.yaml

@@ -1,11 +1,19 @@
+version: '2'
 name: fireworks
 distribution_spec:
-  description: Use Fireworks.ai for running LLM inference
+  description: Use Fireworks.AI for running LLM inference
+  docker_image: null
   providers:
-    inference: remote::fireworks
+    inference:
+    - remote::fireworks
     memory:
     - inline::faiss
-    - remote::weaviate
-    safety: inline::llama-guard
-    agents: inline::meta-reference
-    telemetry: inline::meta-reference
+    - remote::chromadb
+    - remote::pgvector
+    safety:
+    - inline::llama-guard
+    agents:
+    - inline::meta-reference
+    telemetry:
+    - inline::meta-reference
+image_type: conda

llama_stack/templates/fireworks/doc_template.md

@@ -0,0 +1,60 @@
+# Fireworks Distribution
+
+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 }}`
+{% 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=5001
+docker run \
+  -it \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v ./run.yaml:/root/my-run.yaml \
+  llamastack/distribution-{{ name }} \
+  /root/my-run.yaml \
+  --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 5001 \
+  --env FIREWORKS_API_KEY=$FIREWORKS_API_KEY
+```

llama_stack/templates/fireworks/fireworks.py

@@ -0,0 +1,60 @@
+# 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.distribution.datatypes import ModelInput, Provider, ShieldInput
+from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig
+from llama_stack.providers.remote.inference.fireworks.fireworks import MODEL_ALIASES
+
+from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
+
+
+def get_distribution_template() -> DistributionTemplate:
+    providers = {
+        "inference": ["remote::fireworks"],
+        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "safety": ["inline::llama-guard"],
+        "agents": ["inline::meta-reference"],
+        "telemetry": ["inline::meta-reference"],
+    }
+
+    inference_provider = Provider(
+        provider_id="fireworks",
+        provider_type="remote::fireworks",
+        config=FireworksImplConfig.sample_run_config(),
+    )
+
+    default_models = [ModelInput(model_id=m.provider_model_id) for m in MODEL_ALIASES]
+
+    return DistributionTemplate(
+        name="fireworks",
+        distro_type="self_hosted",
+        description="Use Fireworks.AI for running LLM inference",
+        docker_image=None,
+        template_path=Path(__file__).parent / "doc_template.md",
+        providers=providers,
+        default_models=default_models,
+        run_configs={
+            "run.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": [inference_provider],
+                },
+                default_models=default_models,
+                default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
+            ),
+        },
+        run_config_env_vars={
+            "LLAMASTACK_PORT": (
+                "5001",
+                "Port for the Llama Stack distribution server",
+            ),
+            "FIREWORKS_API_KEY": (
+                "",
+                "Fireworks.AI API Key",
+            ),
+        },
+    )

llama_stack/templates/fireworks/run.yaml

@@ -0,0 +1,91 @@
+version: '2'
+image_name: fireworks
+docker_image: null
+conda_env: null
+apis:
+- agents
+- inference
+- memory
+- safety
+- telemetry
+providers:
+  inference:
+  - provider_id: fireworks
+    provider_type: remote::fireworks
+    config:
+      url: https://api.fireworks.ai/inference
+      api_key: ${env.FIREWORKS_API_KEY}
+  memory:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/faiss_store.db
+  safety:
+  - provider_id: llama-guard
+    provider_type: inline::llama-guard
+    config: {}
+  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/fireworks}/agents_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config: {}
+metadata_store:
+  namespace: null
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/registry.db
+models:
+- metadata: {}
+  model_id: fireworks/llama-v3p1-8b-instruct
+  provider_id: null
+  provider_model_id: null
+- metadata: {}
+  model_id: fireworks/llama-v3p1-70b-instruct
+  provider_id: null
+  provider_model_id: null
+- metadata: {}
+  model_id: fireworks/llama-v3p1-405b-instruct
+  provider_id: null
+  provider_model_id: null
+- metadata: {}
+  model_id: fireworks/llama-v3p2-1b-instruct
+  provider_id: null
+  provider_model_id: null
+- metadata: {}
+  model_id: fireworks/llama-v3p2-3b-instruct
+  provider_id: null
+  provider_model_id: null
+- metadata: {}
+  model_id: fireworks/llama-v3p2-11b-vision-instruct
+  provider_id: null
+  provider_model_id: null
+- metadata: {}
+  model_id: fireworks/llama-v3p2-90b-vision-instruct
+  provider_id: null
+  provider_model_id: null
+- metadata: {}
+  model_id: fireworks/llama-guard-3-8b
+  provider_id: null
+  provider_model_id: null
+- metadata: {}
+  model_id: fireworks/llama-guard-3-11b-vision
+  provider_id: null
+  provider_model_id: null
+shields:
+- params: null
+  shield_id: meta-llama/Llama-Guard-3-8B
+  provider_id: null
+  provider_shield_id: null
+memory_banks: []
+datasets: []
+scoring_fns: []
+eval_tasks: []