feat: add support for running in a venv (#1018)

# What does this PR do?

add --image-type to `llama stack run`. Which takes conda, container or
venv also add start_venv.sh which start the stack using a venv

resolves #1007

## Test Plan

running locally:

`llama stack build --template ollama --image-type venv`
`llama stack run --image-type venv
~/.llama/distributions/ollama/ollama-run.yaml`
...
```
llama stack run --image-type venv ~/.llama/distributions/ollama/ollama-run.yaml
Using run configuration: /Users/charliedoern/.llama/distributions/ollama/ollama-run.yaml
+ python -m llama_stack.distribution.server.server --yaml-config /Users/charliedoern/.llama/distributions/ollama/ollama-run.yaml --port 8321
Using config file: /Users/charliedoern/.llama/distributions/ollama/ollama-run.yaml
Run configuration:
apis:
- agents
- datasetio
...
```

Signed-off-by: Charlie Doern <cdoern@redhat.com>

docs/source/distributions/building_distro.md

@@ -180,12 +180,45 @@ After this step is successful, you should be able to find the built container im
 ### Running your Stack server
 Now, let's start the Llama Stack Distribution Server. You will need the YAML configuration file which was written out at the end by the `llama stack build` step.
 
+```
+llama stack run -h
+usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME] [--disable-ipv6] [--env KEY=VALUE] [--tls-keyfile TLS_KEYFILE]
+                       [--tls-certfile TLS_CERTFILE] [--image-type {conda,container,venv}]
+                       config
+
+start the server for a Llama Stack Distribution. You should have already built (or downloaded) and configured the distribution.
+
+positional arguments:
+  config                Path to config file to use for the run
+
+options:
+  -h, --help            show this help message and exit
+  --port PORT           Port to run the server on. Defaults to 8321
+  --image-name IMAGE_NAME
+                        Name of the image to run. Defaults to the current conda environment
+  --disable-ipv6        Disable IPv6 support
+  --env KEY=VALUE       Environment variables to pass to the server in KEY=VALUE format. Can be specified multiple times.
+  --tls-keyfile TLS_KEYFILE
+                        Path to TLS key file for HTTPS
+  --tls-certfile TLS_CERTFILE
+                        Path to TLS certificate file for HTTPS
+  --image-type {conda,container,venv}
+                        Image Type used during the build. This can be either conda or container or venv.
+
+```
+
 ```
 # Start using template name
 llama stack run tgi
 
 # Start using config file
 llama stack run ~/.llama/distributions/llamastack-my-local-stack/my-local-stack-run.yaml
+
+# Start using a venv
+llama stack run --image-type venv ~/.llama/distributions/llamastack-my-local-stack/my-local-stack-run.yaml
+
+# Start using a conda environment
+llama stack run --image-type conda ~/.llama/distributions/llamastack-my-local-stack/my-local-stack-run.yaml
 ```
 
 ```

llama_stack/cli/stack/run.py

@@ -65,6 +65,13 @@ class StackRun(Subcommand):
             type=str,
             help="Path to TLS certificate file for HTTPS",
         )
+        self.parser.add_argument(
+            "--image-type",
+            type=str,
+            help="Image Type used during the build. This can be either conda or container or venv.",
+            choices=["conda", "container", "venv"],
+            default="conda",
+        )
 
     def _run_stack_run_cmd(self, args: argparse.Namespace) -> None:
         import importlib.resources
@@ -118,11 +125,11 @@ class StackRun(Subcommand):
         config_dict = yaml.safe_load(config_file.read_text())
         config = parse_and_maybe_upgrade_config(config_dict)
 
-        if config.container_image:
+        if args.image_type == ImageType.container.value or config.container_image:
             script = importlib.resources.files("llama_stack") / "distribution/start_container.sh"
             image_name = f"distribution-{template_name}" if template_name else config.container_image
             run_args = [script, image_name]
-        else:
+        elif args.image_type == ImageType.conda.value:
             current_conda_env = os.environ.get("CONDA_DEFAULT_ENV")
             image_name = args.image_name or current_conda_env
             if not image_name:
@@ -167,6 +174,15 @@ class StackRun(Subcommand):
                 script,
                 image_name,
             ]
+        else:
+            # else must be venv since that is the only valid option left.
+            current_venv = os.environ.get("VIRTUAL_ENV")
+            venv = args.image_name or current_venv
+            script = importlib.resources.files("llama_stack") / "distribution/start_venv.sh"
+            run_args = [
+                script,
+                venv,
+            ]
 
         run_args.extend([str(config_file), str(args.port)])
         if args.disable_ipv6:

llama_stack/distribution/start_venv.sh

@@ -0,0 +1,71 @@
+#!/bin/bash
+
+# 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.
+
+set -euo pipefail
+
+RED='\033[0;31m'
+NC='\033[0m' # No Color
+
+error_handler() {
+  echo "Error occurred in script at line: ${1}" >&2
+  exit 1
+}
+
+trap 'error_handler ${LINENO}' ERR
+
+if [ $# -lt 3 ]; then
+  echo "Usage: $0 <venv_path> <yaml_config> <port> <script_args...>"
+  exit 1
+fi
+
+venv_path="$1"
+shift
+
+yaml_config="$1"
+shift
+
+port="$1"
+shift
+
+# Initialize env_vars as an empty array
+env_vars=""
+other_args=""
+# Process environment variables from --env arguments
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+  --env)
+
+    if [[ -n "$2" ]]; then
+      env_vars="$env_vars --env $2"
+      shift 2
+    else
+      echo -e "${RED}Error: --env requires a KEY=VALUE argument${NC}" >&2
+      exit 1
+    fi
+    ;;
+  *)
+    other_args="$other_args $1"
+    shift
+    ;;
+  esac
+done
+
+# Activate virtual environment
+if [ ! -d "$venv_path" ]; then
+  echo -e "${RED}Error: Virtual environment not found at $venv_path${NC}" >&2
+  exit 1
+fi
+
+source "$venv_path/bin/activate"
+
+set -x
+python -m llama_stack.distribution.server.server \
+  --yaml-config "$yaml_config" \
+  --port "$port" \
+  $env_vars \
+  $other_args