feat: Add HTTPS serving option

llama_stack/cli/stack/run.py

@@ -55,6 +55,16 @@ def _add_arguments(self):
             default=[],
             metavar="KEY=VALUE",
         )
+        self.parser.add_argument(
+            "--tls-keyfile",
+            type=str,
+            help="Path to TLS key file for HTTPS",
+        )
+        self.parser.add_argument(
+            "--tls-certfile",
+            type=str,
+            help="Path to TLS certificate file for HTTPS",
+        )
 
     def _run_stack_run_cmd(self, args: argparse.Namespace) -> None:
         import importlib.resources
@@ -178,4 +188,7 @@ def get_conda_prefix(env_name):
                 return
             run_args.extend(["--env", f"{key}={value}"])
 
+        if args.tls_keyfile and args.tls_certfile:
+            run_args.extend(["--tls-keyfile", args.tls_keyfile, "--tls-certfile", args.tls_certfile])
+
         run_with_pty(run_args)

llama_stack/distribution/datatypes.py

@@ -117,6 +117,23 @@ class Provider(BaseModel):
     config: Dict[str, Any]
 
 
+class ServerConfig(BaseModel):
+    port: int = Field(
+        default=8321,
+        description="Port to listen on",
+        ge=1024,
+        le=65535,
+    )
+    tls_certfile: Optional[str] = Field(
+        default=None,
+        description="Path to TLS certificate file for HTTPS",
+    )
+    tls_keyfile: Optional[str] = Field(
+        default=None,
+        description="Path to TLS key file for HTTPS",
+    )
+
+
 class StackRunConfig(BaseModel):
     version: str = LLAMA_STACK_RUN_CONFIG_VERSION
 
@@ -159,6 +176,11 @@ class StackRunConfig(BaseModel):
     eval_tasks: List[EvalTaskInput] = Field(default_factory=list)
     tool_groups: List[ToolGroupInput] = Field(default_factory=list)
 
+    server: ServerConfig = Field(
+        default_factory=ServerConfig,
+        description="Configuration for the HTTP(S) server",
+    )
+
 
 class BuildConfig(BaseModel):
     version: str = LLAMA_STACK_BUILD_CONFIG_VERSION

llama_stack/distribution/server/server.py

@@ -282,8 +282,19 @@ def main():
         action="append",
         help="Environment variables in KEY=value format. Can be specified multiple times.",
     )
+    parser.add_argument(
+        "--tls-keyfile",
+        help="Path to TLS key file for HTTPS",
+        required="--tls-certfile" in sys.argv,
+    )
+    parser.add_argument(
+        "--tls-certfile",
+        help="Path to TLS certificate file for HTTPS",
+        required="--tls-keyfile" in sys.argv,
+    )
 
     args = parser.parse_args()
+
     if args.env:
         for env_pair in args.env:
             try:
@@ -381,11 +392,36 @@ def main():
 
     import uvicorn
 
-    # FYI this does not do hot-reloads
+    # Configure SSL if certificates are provided
+    port = args.port or config.server.port
+
+    ssl_config = None
+    if args.tls_keyfile:
+        keyfile = args.tls_keyfile
+        certfile = args.tls_certfile
+    else:
+        keyfile = config.server.tls_keyfile
+        certfile = config.server.tls_certfile
+
+    if keyfile and certfile:
+        ssl_config = {
+            "ssl_keyfile": keyfile,
+            "ssl_certfile": certfile,
+        }
+        print(f"HTTPS enabled with certificates:\n  Key: {keyfile}\n  Cert: {certfile}")
 
     listen_host = ["::", "0.0.0.0"] if not args.disable_ipv6 else "0.0.0.0"
-    print(f"Listening on {listen_host}:{args.port}")
-    uvicorn.run(app, host=listen_host, port=args.port)
+    print(f"Listening on {listen_host}:{port}")
+
+    uvicorn_config = {
+        "app": app,
+        "host": listen_host,
+        "port": port,
+    }
+    if ssl_config:
+        uvicorn_config.update(ssl_config)
+
+    uvicorn.run(**uvicorn_config)
 
 
 def extract_path_params(route: str) -> List[str]:

llama_stack/distribution/start_conda_env.sh

@@ -34,6 +34,7 @@ shift
 
 # Process environment variables from --env arguments
 env_vars=""
+other_args=""
 while [[ $# -gt 0 ]]; do
   case "$1" in
   --env)
@@ -48,6 +49,7 @@ while [[ $# -gt 0 ]]; do
     fi
     ;;
   *)
+    other_args="$other_args $1"
     shift
     ;;
   esac
@@ -61,4 +63,5 @@ $CONDA_PREFIX/bin/python \
   -m llama_stack.distribution.server.server \
   --yaml-config "$yaml_config" \
   --port "$port" \
-  $env_vars
+  $env_vars \
+  $other_args

llama_stack/distribution/start_container.sh

@@ -40,8 +40,12 @@ shift
 port="$1"
 shift
 
+# Initialize other_args
+other_args=""
+
 # Process environment variables from --env arguments
 env_vars=""
+
 while [[ $# -gt 0 ]]; do
     case "$1" in
         --env)
@@ -55,6 +59,7 @@ while [[ $# -gt 0 ]]; do
             fi
             ;;
         *)
+            other_args="$other_args $1"
             shift
             ;;
     esac
@@ -93,5 +98,8 @@ $CONTAINER_BINARY run $CONTAINER_OPTS -it \
   -v "$yaml_config:/app/config.yaml" \
   $mounts \
   --env LLAMA_STACK_PORT=$port \
-  --entrypoint='["python", "-m", "llama_stack.distribution.server.server", "--yaml-config", "/app/config.yaml"]' \
-  $container_image:$version_tag
+  --entrypoint python \
+  $container_image:$version_tag \
+  -m llama_stack.distribution.server.server \
+  --yaml-config /app/config.yaml \
+  $other_args