phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

feat: include run.yaml in the container image (#2005)

Browse source 
As part of the build process, we now include the generated run.yaml
(based of the provided build configuration file) into the container. We
updated the entrypoint to use this run configuration as well.

Given this simple distribution configuration:

```
# build.yaml
version: '2'
distribution_spec:
  description: Use (an external) Ollama server for running LLM inference
  providers:
    inference:
    - remote::ollama
    vector_io:
    - inline::faiss
    safety:
    - inline::llama-guard
    agents:
    - inline::meta-reference
    telemetry:
    - inline::meta-reference
    eval:
    - inline::meta-reference
    datasetio:
    - remote::huggingface
    - inline::localfs
    scoring:
    - inline::basic
    - inline::llm-as-judge
    - inline::braintrust
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
    - remote::wolfram-alpha
  container_image: "registry.access.redhat.com/ubi9"
image_type: container
image_name: test
```

Build it:
```
llama stack build --config build.yaml
```

Run it:

```
podman run --rm \
         -p 8321:8321 \
         -e OLLAMA_URL=http://host.containers.internal:11434 \
         --name llama-stack-server \
         localhost/leseb-test:0.2.2
```

Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han 2025-04-24 11:29:53 +02:00 • committed by GitHub
parent a673697858
commit 14e60e3c02
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 139 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

22
llama_stack/cli/stack/_build.py
View file

@ -317,11 +317,15 @@ def _generate_run_config(
to_write = json.loads(run_config.model_dump_json())
f.write(yaml.dump(to_write, sort_keys=False))
# this path is only invoked when no template is provided
cprint(
f"You can now run your stack with `llama stack run {run_config_file}`",
color="green",
)
# Only print this message for non-container builds since it will be displayed before the
# container is built
# For non-container builds, the run.yaml is generated at the very end of the build process so it
# makes sense to display this message
if build_config.image_type != LlamaStackImageType.CONTAINER.value:
cprint(
f"You can now run your stack with `llama stack run {run_config_file}`",
color="green",
)
return run_config_file
@ -355,6 +359,13 @@ def _run_stack_build_command_from_build_config(
build_file_path = build_dir / f"{image_name}-build.yaml"
os.makedirs(build_dir, exist_ok=True)
run_config_file = None
# Generate the run.yaml so it can be included in the container image with the proper entrypoint
# Only do this if we're building a container image and we're not using a template
if build_config.image_type == LlamaStackImageType.CONTAINER.value and not template_name and config_path:
cprint("Generating run.yaml file", color="green")
run_config_file = _generate_run_config(build_config, build_dir, image_name)
with open(build_file_path, "w") as f:
to_write = json.loads(build_config.model_dump_json())
f.write(yaml.dump(to_write, sort_keys=False))
@ -364,6 +375,7 @@ def _run_stack_build_command_from_build_config(
build_file_path,
image_name,
template_or_config=template_name or config_path or str(build_file_path),
run_config=run_config_file,
)
if return_code != 0:
raise RuntimeError(f"Failed to build image {image_name}")