mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
d96f6ec763
# What does this PR do? - no more CORS middleware needed ## Test Plan ### Local test llama stack run starter --image-type conda npm run dev verify UI works in browser ### Deploy to k8s temporarily change ui-k8s.yaml.template to load from PR commit <img width="604" alt="image" src="https://github.com/user-attachments/assets/87fa2e52-1e93-4e32-9e0f-5b283b7a37b3" /> sh ./apply.sh $ kubectl get services go to external_ip:8322 and play around with UI <img width="1690" alt="image" src="https://github.com/user-attachments/assets/5b7ec827-4302-4435-a9eb-df423676d873" />
32 lines
1.1 KiB
Bash
Executable file
32 lines
1.1 KiB
Bash
Executable file
#!/usr/bin/env 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.
|
|
|
|
export POSTGRES_USER=${POSTGRES_USER:-llamastack}
|
|
export POSTGRES_DB=${POSTGRES_DB:-llamastack}
|
|
export POSTGRES_PASSWORD=${POSTGRES_PASSWORD:-llamastack}
|
|
|
|
export INFERENCE_MODEL=${INFERENCE_MODEL:-meta-llama/Llama-3.2-3B-Instruct}
|
|
export SAFETY_MODEL=${SAFETY_MODEL:-meta-llama/Llama-Guard-3-1B}
|
|
|
|
set -euo pipefail
|
|
set -x
|
|
|
|
envsubst < ./vllm-k8s.yaml.template | kubectl apply -f -
|
|
envsubst < ./vllm-safety-k8s.yaml.template | kubectl apply -f -
|
|
envsubst < ./postgres-k8s.yaml.template | kubectl apply -f -
|
|
envsubst < ./chroma-k8s.yaml.template | kubectl apply -f -
|
|
|
|
kubectl create configmap llama-stack-config --from-file=stack_run_config.yaml \
|
|
--dry-run=client -o yaml > stack-configmap.yaml
|
|
|
|
kubectl apply -f stack-configmap.yaml
|
|
|
|
envsubst < ./stack-k8s.yaml.template | kubectl apply -f -
|
|
envsubst < ./ingress-k8s.yaml.template | kubectl apply -f -
|
|
|
|
envsubst < ./ui-k8s.yaml.template | kubectl apply -f -
|