From adbb605a50ccc51c1864aeaf0a678d7c674a27d1 Mon Sep 17 00:00:00 2001
From: Ashwin Bharambe <ashwin.bharambe@gmail.com>
Date: Wed, 20 Nov 2024 11:56:08 -0800
Subject: [PATCH] Make run yaml optional so dockers can start with just --env

---
 llama_stack/distribution/build_container.sh |  2 +-
 llama_stack/distribution/server/server.py   | 29 +++++++++++++++++++--
 2 files changed, 28 insertions(+), 3 deletions(-)

diff --git a/llama_stack/distribution/build_container.sh b/llama_stack/distribution/build_container.sh
index 2730ae174..a9aee8f14 100755
--- a/llama_stack/distribution/build_container.sh
+++ b/llama_stack/distribution/build_container.sh
@@ -122,7 +122,7 @@ add_to_docker <<EOF
 # This would be good in production but for debugging flexibility lets not add it right now
 # We need a more solid production ready entrypoint.sh anyway
 #
-ENTRYPOINT ["python", "-m", "llama_stack.distribution.server.server"]
+ENTRYPOINT ["python", "-m", "llama_stack.distribution.server.server", "--template", "$build_name"]
 
 EOF
 
diff --git a/llama_stack/distribution/server/server.py b/llama_stack/distribution/server/server.py
index fecc41b5d..6e038835b 100644
--- a/llama_stack/distribution/server/server.py
+++ b/llama_stack/distribution/server/server.py
@@ -16,6 +16,7 @@ import traceback
 import warnings
 
 from contextlib import asynccontextmanager
+from pathlib import Path
 from ssl import SSLError
 from typing import Any, Dict, Optional
 
@@ -49,6 +50,9 @@ from llama_stack.distribution.stack import (
 from .endpoints import get_all_api_endpoints
 
 
+REPO_ROOT = Path(__file__).parent.parent.parent.parent
+
+
 def warn_with_traceback(message, category, filename, lineno, file=None, line=None):
     log = file if hasattr(file, "write") else sys.stderr
     traceback.print_stack(file=log)
@@ -279,9 +283,12 @@ def main():
     parser = argparse.ArgumentParser(description="Start the LlamaStack server.")
     parser.add_argument(
         "--yaml-config",
-        default="llamastack-run.yaml",
         help="Path to YAML configuration file",
     )
+    parser.add_argument(
+        "--template",
+        help="One of the template names in llama_stack/templates (e.g., tgi, fireworks, remote-vllm, etc.)",
+    )
     parser.add_argument("--port", type=int, default=5000, help="Port to listen on")
     parser.add_argument(
         "--disable-ipv6", action="store_true", help="Whether to disable IPv6 support"
@@ -303,10 +310,28 @@ def main():
                 print(f"Error: {str(e)}")
                 sys.exit(1)
 
-    with open(args.yaml_config, "r") as fp:
+    if args.yaml_config:
+        # if the user provided a config file, use it, even if template was specified
+        config_file = Path(args.yaml_config)
+        if not config_file.exists():
+            raise ValueError(f"Config file {config_file} does not exist")
+
+    elif args.template:
+        config_file = (
+            Path(REPO_ROOT) / "llama_stack" / "templates" / args.template / "run.yaml"
+        )
+        if not config_file.exists():
+            raise ValueError(f"Template {args.template} does not exist")
+    else:
+        raise ValueError("Either --yaml-config or --template must be provided")
+
+    with open(config_file, "r") as fp:
         config = replace_env_vars(yaml.safe_load(fp))
         config = StackRunConfig(**config)
 
+    print(f"Using config file: {config_file}")
+    print(f"Config: {yaml.dump(config.model_dump(), indent=2)}")
+
     app = FastAPI()
 
     try: