phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-07 04:45:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: remove --env from llama stack run

Browse source 
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-10-06 14:58:57 -07:00
parent 597d405e13
commit 0751002bf3
18 changed files with 105 additions and 167 deletions
Download patch file Download diff file Expand all files Collapse all files

9
docs/docs/building_applications/tools.mdx
View file

@ -219,13 +219,10 @@ group_tools = client.tools.list_tools(toolgroup_id="search_tools")
<TabItem value="setup" label="Setup & Configuration">
1. Start by registering a Tavily API key at [Tavily](https://tavily.com/).
2. [Optional] Provide the API key directly to the Llama Stack server
2. [Optional] Set the API key in your environment before starting the Llama Stack server
```bash
export TAVILY_SEARCH_API_KEY="your key"
```
```bash
--env TAVILY_SEARCH_API_KEY=${TAVILY_SEARCH_API_KEY}
```
</TabItem>
<TabItem value="implementation" label="Implementation">
@ -273,9 +270,9 @@ for log in EventLogger().log(response):
<TabItem value="setup" label="Setup & Configuration">
1. Start by registering for a WolframAlpha API key at [WolframAlpha Developer Portal](https://developer.wolframalpha.com/access).
2. Provide the API key either when starting the Llama Stack server:
2. Provide the API key either by setting it in your environment before starting the Llama Stack server:
```bash
--env WOLFRAM_ALPHA_API_KEY=${WOLFRAM_ALPHA_API_KEY}
export WOLFRAM_ALPHA_API_KEY="your key"
```
or from the client side:
```python

2
docs/docs/contributing/new_api_provider.mdx
View file

@ -76,7 +76,7 @@ Integration tests are located in [tests/integration](https://github.com/meta-lla
Consult [tests/integration/README.md](https://github.com/meta-llama/llama-stack/blob/main/tests/integration/README.md) for more details on how to run the tests.
Note that each provider's `sample_run_config()` method (in the configuration class for that provider)
typically references some environment variables for specifying API keys and the like. You can set these in the environment or pass these via the `--env` flag to the test command.
typically references some environment variables for specifying API keys and the like. You can set these in the environment before running the test command.
### 2. Unit Testing

17
docs/docs/distributions/building_distro.mdx
View file

@ -289,10 +289,10 @@ After this step is successful, you should be able to find the built container im
docker run -d \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
-e INFERENCE_MODEL=$INFERENCE_MODEL \
-e OLLAMA_URL=http://host.docker.internal:11434 \
localhost/distribution-ollama:dev \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env OLLAMA_URL=http://host.docker.internal:11434
--port $LLAMA_STACK_PORT
```
Here are the docker flags and their uses:
@ -305,12 +305,12 @@ Here are the docker flags and their uses:
* `localhost/distribution-ollama:dev`: The name and tag of the container image to run
* `-e INFERENCE_MODEL=$INFERENCE_MODEL`: Sets the INFERENCE_MODEL environment variable in the container
* `-e OLLAMA_URL=http://host.docker.internal:11434`: Sets the OLLAMA_URL environment variable in the container
* `--port $LLAMA_STACK_PORT`: Port number for the server to listen on
* `--env INFERENCE_MODEL=$INFERENCE_MODEL`: Sets the model to use for inference
* `--env OLLAMA_URL=http://host.docker.internal:11434`: Configures the URL for the Ollama service
</TabItem>
</Tabs>
@ -320,7 +320,7 @@ Now, let's start the Llama Stack Distribution Server. You will need the YAML con
```
llama stack run -h
usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME] [--env KEY=VALUE]
usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME]
[--image-type {venv}] [--enable-ui]
[config | template]
@ -334,7 +334,6 @@ options:
--port PORT Port to run the server on. It can also be passed via the env var LLAMA_STACK_PORT. (default: 8321)
--image-name IMAGE_NAME
Name of the image to run. Defaults to the current environment (default: None)
--env KEY=VALUE Environment variables to pass to the server in KEY=VALUE format. Can be specified multiple times. (default: None)
--image-type {venv}
Image Type used during the build. This should be venv. (default: None)
--enable-ui Start the UI server (default: False)

9
docs/docs/distributions/configuration.mdx
View file

@ -101,7 +101,7 @@ A few things to note:
- The id is a string you can choose freely.
- You can instantiate any number of provider instances of the same type.
- The configuration dictionary is provider-specific.
- Notice that configuration can reference environment variables (with default values), which are expanded at runtime. When you run a stack server (via docker or via `llama stack run`), you can specify `--env OLLAMA_URL=http://my-server:11434` to override the default value.
- Notice that configuration can reference environment variables (with default values), which are expanded at runtime. When you run a stack server, you can set environment variables in your shell before running `llama stack run` to override the default values.
### Environment Variable Substitution
@ -173,13 +173,10 @@ optional_token: ${env.OPTIONAL_TOKEN:+}
#### Runtime Override
You can override environment variables at runtime when starting the server:
You can override environment variables at runtime by setting them in your shell before starting the server:
```bash
# Override specific environment variables
llama stack run --config run.yaml --env API_KEY=sk-123 --env BASE_URL=https://custom-api.com
# Or set them in your shell
# Set environment variables in your shell
export API_KEY=sk-123
export BASE_URL=https://custom-api.com
llama stack run --config run.yaml

8
docs/docs/distributions/remote_hosted_distro/watsonx.md
View file

@ -69,10 +69,10 @@ docker run \
-it \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ./run.yaml:/root/my-run.yaml \
-e WATSONX_API_KEY=$WATSONX_API_KEY \
-e WATSONX_PROJECT_ID=$WATSONX_PROJECT_ID \
-e WATSONX_BASE_URL=$WATSONX_BASE_URL \
llamastack/distribution-watsonx \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env WATSONX_API_KEY=$WATSONX_API_KEY \
--env WATSONX_PROJECT_ID=$WATSONX_PROJECT_ID \
--env WATSONX_BASE_URL=$WATSONX_BASE_URL
--port $LLAMA_STACK_PORT
```

44
docs/docs/distributions/self_hosted_distro/dell.md
View file

@ -129,11 +129,11 @@ docker run -it \
# NOTE: mount the llama-stack / llama-model directories if testing local changes else not needed
-v $HOME/git/llama-stack:/app/llama-stack-source -v $HOME/git/llama-models:/app/llama-models-source \
# localhost/distribution-dell:dev if building / testing locally
llamastack/distribution-dell\
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env DEH_URL=$DEH_URL \
--env CHROMA_URL=$CHROMA_URL
-e INFERENCE_MODEL=$INFERENCE_MODEL \
-e DEH_URL=$DEH_URL \
-e CHROMA_URL=$CHROMA_URL \
llamastack/distribution-dell \
--port $LLAMA_STACK_PORT
```
@ -154,14 +154,14 @@ docker run \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v $HOME/.llama:/root/.llama \
-v ./llama_stack/distributions/tgi/run-with-safety.yaml:/root/my-run.yaml \
-e INFERENCE_MODEL=$INFERENCE_MODEL \
-e DEH_URL=$DEH_URL \
-e SAFETY_MODEL=$SAFETY_MODEL \
-e DEH_SAFETY_URL=$DEH_SAFETY_URL \
-e CHROMA_URL=$CHROMA_URL \
llamastack/distribution-dell \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env DEH_URL=$DEH_URL \
--env SAFETY_MODEL=$SAFETY_MODEL \
--env DEH_SAFETY_URL=$DEH_SAFETY_URL \
--env CHROMA_URL=$CHROMA_URL
--port $LLAMA_STACK_PORT
```
### Via venv
@ -170,21 +170,21 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
```bash
llama stack build --distro dell --image-type venv
llama stack run dell
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env DEH_URL=$DEH_URL \
--env CHROMA_URL=$CHROMA_URL
INFERENCE_MODEL=$INFERENCE_MODEL \
DEH_URL=$DEH_URL \
CHROMA_URL=$CHROMA_URL \
llama stack run dell \
--port $LLAMA_STACK_PORT
```
If you are using Llama Stack Safety / Shield APIs, use:
```bash
INFERENCE_MODEL=$INFERENCE_MODEL \
DEH_URL=$DEH_URL \
SAFETY_MODEL=$SAFETY_MODEL \
DEH_SAFETY_URL=$DEH_SAFETY_URL \
CHROMA_URL=$CHROMA_URL \
llama stack run ./run-with-safety.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env DEH_URL=$DEH_URL \
--env SAFETY_MODEL=$SAFETY_MODEL \
--env DEH_SAFETY_URL=$DEH_SAFETY_URL \
--env CHROMA_URL=$CHROMA_URL
--port $LLAMA_STACK_PORT
```

20
docs/docs/distributions/self_hosted_distro/meta-reference-gpu.md
View file

@ -84,9 +84,9 @@ docker run \
--gpu all \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
-e INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
llamastack/distribution-meta-reference-gpu \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
--port $LLAMA_STACK_PORT
```
If you are using Llama Stack Safety / Shield APIs, use:
@ -98,10 +98,10 @@ docker run \
--gpu all \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
-e INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
-e SAFETY_MODEL=meta-llama/Llama-Guard-3-1B \
llamastack/distribution-meta-reference-gpu \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
--port $LLAMA_STACK_PORT
```
### Via venv
@ -110,16 +110,16 @@ Make sure you have done `uv pip install llama-stack` and have the Llama Stack CL
```bash
llama stack build --distro meta-reference-gpu --image-type venv
INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
llama stack run distributions/meta-reference-gpu/run.yaml \
--port 8321 \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
--port 8321
```
If you are using Llama Stack Safety / Shield APIs, use:
```bash
INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
SAFETY_MODEL=meta-llama/Llama-Guard-3-1B \
llama stack run distributions/meta-reference-gpu/run-with-safety.yaml \
--port 8321 \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
--port 8321
```

10
docs/docs/distributions/self_hosted_distro/nvidia.md
View file

@ -129,10 +129,10 @@ docker run \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ./run.yaml:/root/my-run.yaml \
-e NVIDIA_API_KEY=$NVIDIA_API_KEY \
llamastack/distribution-nvidia \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env NVIDIA_API_KEY=$NVIDIA_API_KEY
--port $LLAMA_STACK_PORT
```
### Via venv
@ -142,10 +142,10 @@ If you've set up your local development environment, you can also build the imag
```bash
INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
llama stack build --distro nvidia --image-type venv
NVIDIA_API_KEY=$NVIDIA_API_KEY \
INFERENCE_MODEL=$INFERENCE_MODEL \
llama stack run ./run.yaml \
--port 8321 \
--env NVIDIA_API_KEY=$NVIDIA_API_KEY \
--env INFERENCE_MODEL=$INFERENCE_MODEL
--port 8321
```
## Example Notebooks

8
docs/docs/getting_started/detailed_tutorial.mdx
View file

@ -86,9 +86,9 @@ docker run -it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
-e OLLAMA_URL=http://host.docker.internal:11434 \
llamastack/distribution-starter \
--port $LLAMA_STACK_PORT \
--env OLLAMA_URL=http://host.docker.internal:11434
--port $LLAMA_STACK_PORT
```
Note to start the container with Podman, you can do the same but replace `docker` at the start of the command with
`podman`. If you are using `podman` older than `4.7.0`, please also replace `host.docker.internal` in the `OLLAMA_URL`
@ -106,9 +106,9 @@ docker run -it \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
--network=host \
-e OLLAMA_URL=http://localhost:11434 \
llamastack/distribution-starter \
--port $LLAMA_STACK_PORT \
--env OLLAMA_URL=http://localhost:11434
--port $LLAMA_STACK_PORT
```
:::
You will see output like below:

2
docs/getting_started_llama4.ipynb
View file

@ -238,7 +238,7 @@
"def run_llama_stack_server_background():\n",
" log_file = open(\"llama_stack_server.log\", \"w\")\n",
" process = subprocess.Popen(\n",
" f\"uv run --with llama-stack llama stack run meta-reference-gpu --image-type venv --env INFERENCE_MODEL={model_id}\",\n",
" f\"INFERENCE_MODEL={model_id} uv run --with llama-stack llama stack run meta-reference-gpu --image-type venv\",\n",
" shell=True,\n",
" stdout=log_file,\n",
" stderr=log_file,\n",

8
docs/zero_to_hero_guide/README.md
View file

@ -102,12 +102,12 @@ If you're looking for more specific topics, we have a [Zero to Hero Guide](#next
3. **Run the Llama Stack**:
Run the stack using uv:
```bash
INFERENCE_MODEL=$INFERENCE_MODEL \
SAFETY_MODEL=$SAFETY_MODEL \
OLLAMA_URL=$OLLAMA_URL \
uv run --with llama-stack llama stack run starter \
--image-type venv \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env SAFETY_MODEL=$SAFETY_MODEL \
--env OLLAMA_URL=$OLLAMA_URL
--port $LLAMA_STACK_PORT
```
Note: Every time you run a new model with `ollama run`, you will need to restart the llama stack. Otherwise it won't see the new model.

30
llama_stack/cli/stack/run.py
View file

@ -16,7 +16,7 @@ import yaml
from llama_stack.cli.stack.utils import ImageType
from llama_stack.cli.subcommand import Subcommand
from llama_stack.core.datatypes import LoggingConfig, StackRunConfig
from llama_stack.core.stack import cast_image_name_to_string, replace_env_vars, validate_env_pair
from llama_stack.core.stack import cast_image_name_to_string, replace_env_vars
from llama_stack.core.utils.config_resolution import Mode, resolve_config_or_distro
from llama_stack.log import get_logger
@ -57,12 +57,6 @@ class StackRun(Subcommand):
default=None,
help="Name of the image to run. Defaults to the current environment",
)
self.parser.add_argument(
"--env",
action="append",
help="Environment variables to pass to the server in KEY=VALUE format. Can be specified multiple times.",
metavar="KEY=VALUE",
)
self.parser.add_argument(
"--image-type",
type=str,
@ -162,34 +156,12 @@ class StackRun(Subcommand):
if config_file:
run_args.extend(["--config", str(config_file)])
if args.env:
for env_var in args.env:
if "=" not in env_var:
self.parser.error(f"Environment variable '{env_var}' must be in KEY=VALUE format")
return
key, value = env_var.split("=", 1) # split on first = only
if not key:
self.parser.error(f"Environment variable '{env_var}' has empty key")
return
run_args.extend(["--env", f"{key}={value}"])
run_command(run_args)
def _uvicorn_run(self, config_file: Path | None, args: argparse.Namespace) -> None:
if not config_file:
self.parser.error("Config file is required")
# Set environment variables if provided
if args.env:
for env_pair in args.env:
try:
key, value = validate_env_pair(env_pair)
logger.info(f"Setting environment variable {key} => {value}")
os.environ[key] = value
except ValueError as e:
logger.error(f"Error: {str(e)}")
self.parser.error(f"Invalid environment variable format: {env_pair}")
config_file = resolve_config_or_distro(str(config_file), Mode.RUN)
with open(config_file) as fp:
config_contents = yaml.safe_load(fp)

16
llama_stack/core/stack.py
View file

@ -274,22 +274,6 @@ def cast_image_name_to_string(config_dict: dict[str, Any]) -> dict[str, Any]:
return config_dict
def validate_env_pair(env_pair: str) -> tuple[str, str]:
"""Validate and split an environment variable key-value pair."""
try:
key, value = env_pair.split("=", 1)
key = key.strip()
if not key:
raise ValueError(f"Empty key in environment variable pair: {env_pair}")
if not all(c.isalnum() or c == "_" for c in key):
raise ValueError(f"Key must contain only alphanumeric characters and underscores: {key}")
return key, value
except ValueError as e:
raise ValueError(
f"Invalid environment variable format '{env_pair}': {str(e)}. Expected format: KEY=value"
) from e
def add_internal_implementations(impls: dict[Api, Any], run_config: StackRunConfig) -> None:
"""Add internal implementations (inspect and providers) to the implementations dictionary.

13
llama_stack/core/start_stack.sh
View file

@ -25,7 +25,7 @@ error_handler() {
trap 'error_handler ${LINENO}' ERR
if [ $# -lt 3 ]; then
echo "Usage: $0 <env_type> <env_path_or_name> <port> [--config <yaml_config>] [--env KEY=VALUE]..."
echo "Usage: $0 <env_type> <env_path_or_name> <port> [--config <yaml_config>]"
exit 1
fi
@ -43,7 +43,6 @@ SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
# Initialize variables
yaml_config=""
env_vars=""
other_args=""
# Process remaining arguments
@ -58,15 +57,6 @@ while [[ $# -gt 0 ]]; do
exit 1
fi
;;
--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 $1"
shift
@ -119,7 +109,6 @@ if [[ "$env_type" == "venv" ]]; then
llama stack run \
$yaml_config_arg \
--port "$port" \
$env_vars \
$other_args
elif [[ "$env_type" == "container" ]]; then
echo -e "${RED}Warning: Llama Stack no longer supports running Containers via the 'llama stack run' command.${NC}"

42
llama_stack/distributions/dell/doc_template.md
View file

@ -117,11 +117,11 @@ docker run -it \
# NOTE: mount the llama-stack directory if testing local changes else not needed
-v $HOME/git/llama-stack:/app/llama-stack-source \
# localhost/distribution-dell:dev if building / testing locally
-e INFERENCE_MODEL=$INFERENCE_MODEL \
-e DEH_URL=$DEH_URL \
-e CHROMA_URL=$CHROMA_URL \
llamastack/distribution-{{ name }}\
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env DEH_URL=$DEH_URL \
--env CHROMA_URL=$CHROMA_URL
--port $LLAMA_STACK_PORT
```
@ -142,14 +142,14 @@ docker run \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v $HOME/.llama:/root/.llama \
-v ./llama_stack/distributions/tgi/run-with-safety.yaml:/root/my-run.yaml \
-e INFERENCE_MODEL=$INFERENCE_MODEL \
-e DEH_URL=$DEH_URL \
-e SAFETY_MODEL=$SAFETY_MODEL \
-e DEH_SAFETY_URL=$DEH_SAFETY_URL \
-e CHROMA_URL=$CHROMA_URL \
llamastack/distribution-{{ name }} \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env DEH_URL=$DEH_URL \
--env SAFETY_MODEL=$SAFETY_MODEL \
--env DEH_SAFETY_URL=$DEH_SAFETY_URL \
--env CHROMA_URL=$CHROMA_URL
--port $LLAMA_STACK_PORT
```
### Via Conda
@ -158,21 +158,21 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
```bash
llama stack build --distro {{ name }} --image-type conda
llama stack run {{ name }}
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env DEH_URL=$DEH_URL \
--env CHROMA_URL=$CHROMA_URL
INFERENCE_MODEL=$INFERENCE_MODEL \
DEH_URL=$DEH_URL \
CHROMA_URL=$CHROMA_URL \
llama stack run {{ name }} \
--port $LLAMA_STACK_PORT
```
If you are using Llama Stack Safety / Shield APIs, use:
```bash
INFERENCE_MODEL=$INFERENCE_MODEL \
DEH_URL=$DEH_URL \
SAFETY_MODEL=$SAFETY_MODEL \
DEH_SAFETY_URL=$DEH_SAFETY_URL \
CHROMA_URL=$CHROMA_URL \
llama stack run ./run-with-safety.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env DEH_URL=$DEH_URL \
--env SAFETY_MODEL=$SAFETY_MODEL \
--env DEH_SAFETY_URL=$DEH_SAFETY_URL \
--env CHROMA_URL=$CHROMA_URL
--port $LLAMA_STACK_PORT
```

20
llama_stack/distributions/meta-reference-gpu/doc_template.md
View file

@ -72,9 +72,9 @@ docker run \
--gpu all \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
-e INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
--port $LLAMA_STACK_PORT
```
If you are using Llama Stack Safety / Shield APIs, use:
@ -86,10 +86,10 @@ docker run \
--gpu all \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
-e INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
-e SAFETY_MODEL=meta-llama/Llama-Guard-3-1B \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
--port $LLAMA_STACK_PORT
```
### Via venv
@ -98,16 +98,16 @@ Make sure you have done `uv pip install llama-stack` and have the Llama Stack CL
```bash
llama stack build --distro {{ name }} --image-type venv
INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
llama stack run distributions/{{ name }}/run.yaml \
--port 8321 \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
--port 8321
```
If you are using Llama Stack Safety / Shield APIs, use:
```bash
INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
SAFETY_MODEL=meta-llama/Llama-Guard-3-1B \
llama stack run distributions/{{ name }}/run-with-safety.yaml \
--port 8321 \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
--port 8321
```

10
llama_stack/distributions/nvidia/doc_template.md
View file

@ -118,10 +118,10 @@ docker run \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ./run.yaml:/root/my-run.yaml \
-e NVIDIA_API_KEY=$NVIDIA_API_KEY \
llamastack/distribution-{{ name }} \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env NVIDIA_API_KEY=$NVIDIA_API_KEY
--port $LLAMA_STACK_PORT
```
### Via venv
@ -131,10 +131,10 @@ If you've set up your local development environment, you can also build the imag
```bash
INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
llama stack build --distro nvidia --image-type venv
NVIDIA_API_KEY=$NVIDIA_API_KEY \
INFERENCE_MODEL=$INFERENCE_MODEL \
llama stack run ./run.yaml \
--port 8321 \
--env NVIDIA_API_KEY=$NVIDIA_API_KEY \
--env INFERENCE_MODEL=$INFERENCE_MODEL
--port 8321
```
## Example Notebooks

4
scripts/install.sh
View file

@ -221,8 +221,8 @@ fi
cmd=( run -d "${PLATFORM_OPTS[@]}" --name llama-stack \
--network llama-net \
-p "${PORT}:${PORT}" \
"${SERVER_IMAGE}" --port "${PORT}" \
--env OLLAMA_URL="http://ollama-server:${OLLAMA_PORT}")
-e OLLAMA_URL="http://ollama-server:${OLLAMA_PORT}" \
"${SERVER_IMAGE}" --port "${PORT}")
log "🦙 Starting Llama Stack..."
if ! execute_with_log $ENGINE "${cmd[@]}"; then