fix: Gaps in doc codegen (#1035)

# What does this PR do?
Catches docs up to source with:
```
python llama_stack/scripts/distro_codegen.py
```

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
[Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.*]
Manually checked
```
sphinx-autobuild docs/source build/html
```

[//]: # (## Documentation)
[//]: # (- [ ] Added a Changelog entry if the change is significant)

distributions/dependencies.json

@@ -66,6 +66,40 @@
     "sentence-transformers --no-deps",
     "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
   ],
+  "dell": [
+    "aiohttp",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "huggingface_hub",
+    "matplotlib",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pypdf",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
   "fireworks": [
     "aiosqlite",
     "autoevals",
@@ -252,6 +286,38 @@
     "sentence-transformers --no-deps",
     "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
   ],
+  "nvidia": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "datasets",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pypdf",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
   "ollama": [
     "aiohttp",
     "aiosqlite",
@@ -319,6 +385,36 @@
     "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",
+    "matplotlib",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pypdf",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
   "tgi": [
     "aiohttp",
     "aiosqlite",
@@ -421,101 +517,5 @@
     "vllm",
     "sentence-transformers --no-deps",
     "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
-  ],
-  "nvidia": [
-    "aiosqlite",
-    "autoevals",
-    "blobfile",
-    "chardet",
-    "datasets",
-    "faiss-cpu",
-    "fastapi",
-    "fire",
-    "httpx",
-    "matplotlib",
-    "mcp",
-    "nltk",
-    "numpy",
-    "openai",
-    "opentelemetry-exporter-otlp-proto-http",
-    "opentelemetry-sdk",
-    "pandas",
-    "pillow",
-    "psycopg2-binary",
-    "pypdf",
-    "redis",
-    "requests",
-    "scikit-learn",
-    "scipy",
-    "sentencepiece",
-    "tqdm",
-    "transformers",
-    "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",
-    "matplotlib",
-    "nltk",
-    "numpy",
-    "openai",
-    "opentelemetry-exporter-otlp-proto-http",
-    "opentelemetry-sdk",
-    "pandas",
-    "pillow",
-    "psycopg2-binary",
-    "pypdf",
-    "redis",
-    "requests",
-    "scikit-learn",
-    "scipy",
-    "sentencepiece",
-    "tqdm",
-    "transformers",
-    "uvicorn",
-    "sentence-transformers --no-deps",
-    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
-  ],
-  "dell": [
-    "aiohttp",
-    "aiosqlite",
-    "autoevals",
-    "blobfile",
-    "chardet",
-    "chromadb-client",
-    "datasets",
-    "faiss-cpu",
-    "fastapi",
-    "fire",
-    "httpx",
-    "huggingface_hub",
-    "matplotlib",
-    "nltk",
-    "numpy",
-    "openai",
-    "opentelemetry-exporter-otlp-proto-http",
-    "opentelemetry-sdk",
-    "pandas",
-    "pillow",
-    "psycopg2-binary",
-    "pypdf",
-    "redis",
-    "requests",
-    "scikit-learn",
-    "scipy",
-    "sentencepiece",
-    "tqdm",
-    "transformers",
-    "uvicorn",
-    "sentence-transformers --no-deps",
-    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
   ]
 }

docs/source/distributions/self_hosted_distro/ollama.md

@@ -26,9 +26,7 @@ The `llamastack/distribution-ollama` distribution consists of the following prov
 | vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
 
 
-You should use this distribution if you have a regular desktop machine without very powerful GPUs. Of course, if you have powerful GPUs, you can still continue using this distribution since Ollama supports GPU acceleration.
-
-### Environment Variables
+You should use this distribution if you have a regular desktop machine without very powerful GPUs. Of course, if you have powerful GPUs, you can still continue using this distribution since Ollama supports GPU acceleration.### Environment Variables
 
 The following environment variables can be configured:
 

llama_stack/scripts/distro_codegen.py

@@ -29,7 +29,7 @@ def find_template_dirs(templates_dir: Path) -> Iterator[Path]:
     if not templates_dir.exists():
         raise FileNotFoundError(f"Templates directory not found: {templates_dir}")
 
-    return (d for d in templates_dir.iterdir() if d.is_dir() and d.name != "__pycache__")
+    return sorted(d for d in templates_dir.iterdir() if d.is_dir() and d.name != "__pycache__")
 
 
 def process_template(template_dir: Path, progress) -> None:

llama_stack/templates/bedrock/run.yaml

@@ -115,3 +115,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/cerebras/run.yaml

@@ -117,3 +117,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

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

@@ -116,3 +116,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/dell/run.yaml

@@ -107,3 +107,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

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

@@ -172,3 +172,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/fireworks/run.yaml

@@ -161,3 +161,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/hf-endpoint/run-with-safety.yaml

@@ -124,3 +124,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/hf-endpoint/run.yaml

@@ -114,3 +114,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/hf-serverless/run-with-safety.yaml

@@ -124,3 +124,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/hf-serverless/run.yaml

@@ -114,3 +114,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/meta-reference-gpu/run-with-safety.yaml

@@ -126,3 +126,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/meta-reference-gpu/run.yaml

@@ -115,3 +115,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/meta-reference-quantized-gpu/run.yaml

@@ -117,3 +117,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/nvidia/run.yaml

@@ -147,3 +147,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

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

@@ -121,3 +121,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/ollama/run.yaml

@@ -110,3 +110,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/remote-vllm/run-with-safety.yaml

@@ -126,3 +126,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/remote-vllm/run.yaml

@@ -115,3 +115,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/sambanova/run.yaml

@@ -126,3 +126,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

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

@@ -114,3 +114,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/tgi/run.yaml

@@ -113,3 +113,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

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

@@ -167,3 +167,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/together/run.yaml

@@ -156,3 +156,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/vllm-gpu/run.yaml

@@ -117,3 +117,5 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
+server:
+  port: 8321