phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: ability to use postgres as store for starter distro

Browse source 
The starter distribution now comes with all the required packages to
support persistent stores—like the agent store, metadata, and
inference—using PostgreSQL.  We’ve added a new run YAML file,
run-with-postgres-store.yaml, to make this setup easy. The file is
included in the container image, so users can simply override the
entrypoint to use the Postgres-specific config.  The documentation has
been updated with instructions on how to do that.

Closes: #2619
Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han 2025-07-22 11:31:30 +02:00
parent b6cb817897
commit 046d85fa79
No known key found for this signature in database
15 changed files with 426 additions and 336 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/distributions/starter-gpu/starter_gpu.py
View file

@ -14,6 +14,9 @@ def get_distribution_template() -> DistributionTemplate:
template = get_starter_distribution_template(name="starter-gpu")
template.description = "Quick start template for running Llama Stack with several popular providers. This distribution is intended for GPU-enabled environments."
# remove "run-with-postgres-store.yaml" from run_configs
template.run_configs.pop("run-with-postgres-store.yaml", None)
template.providers["post_training"] = [
BuildProvider(provider_type="inline::huggingface-gpu"),
]