mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-18 10:52:28 +00:00
chore: update k8s template (#2786)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Integration Tests / discover-tests (push) Successful in 3s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 4s
Python Package Build Test / build (3.12) (push) Failing after 3s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 8s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 7s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 7s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 10s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 8s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 8s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 14s
Unit Tests / unit-tests (3.12) (push) Failing after 5s
Update ReadTheDocs / update-readthedocs (push) Failing after 3s
Python Package Build Test / build (3.13) (push) Failing after 7s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 14s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 11s
Test External Providers / test-external-providers (venv) (push) Failing after 50s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 58s
Unit Tests / unit-tests (3.13) (push) Failing after 54s
Integration Tests / test-matrix (push) Failing after 53s
Pre-commit / pre-commit (push) Successful in 1m40s
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Integration Tests / discover-tests (push) Successful in 3s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 4s
Python Package Build Test / build (3.12) (push) Failing after 3s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 8s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 7s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 7s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 10s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 8s
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 8s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 14s
Unit Tests / unit-tests (3.12) (push) Failing after 5s
Update ReadTheDocs / update-readthedocs (push) Failing after 3s
Python Package Build Test / build (3.13) (push) Failing after 7s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 14s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 11s
Test External Providers / test-external-providers (venv) (push) Failing after 50s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 58s
Unit Tests / unit-tests (3.13) (push) Failing after 54s
Integration Tests / test-matrix (push) Failing after 53s
Pre-commit / pre-commit (push) Successful in 1m40s
# What does this PR do? - enables auth - updates to use distribution-starter docker ## Test Plan bash apply.sh
This commit is contained in:
parent
b57db11bed
commit
51b179e1c5
6 changed files with 43 additions and 2 deletions
|
@ -222,10 +222,21 @@ llama-stack-client --endpoint http://localhost:5000 inference chat-completion --
|
||||||
|
|
||||||
## Deploying Llama Stack Server in AWS EKS
|
## Deploying Llama Stack Server in AWS EKS
|
||||||
|
|
||||||
We've also provided a script to deploy the Llama Stack server in an AWS EKS cluster. Once you have an [EKS cluster](https://docs.aws.amazon.com/eks/latest/userguide/getting-started.html), you can run the following script to deploy the Llama Stack server.
|
We've also provided a script to deploy the Llama Stack server in an AWS EKS cluster.
|
||||||
|
|
||||||
|
Prerequisites:
|
||||||
|
- Set up an [EKS cluster](https://docs.aws.amazon.com/eks/latest/userguide/getting-started.html).
|
||||||
|
- Create a [Github OAuth app](https://docs.github.com/en/apps/oauth-apps/building-oauth-apps/creating-an-oauth-app) and get the client ID and client secret.
|
||||||
|
- Set the `Authorization callback URL` to `http://<your-llama-stack-ui-url>/api/auth/callback/`
|
||||||
|
|
||||||
|
|
||||||
|
Run the following script to deploy the Llama Stack server:
|
||||||
```
|
```
|
||||||
|
export HF_TOKEN=<your-huggingface-token>
|
||||||
|
export GITHUB_CLIENT_ID=<your-github-client-id>
|
||||||
|
export GITHUB_CLIENT_SECRET=<your-github-client-secret>
|
||||||
|
export LLAMA_STACK_UI_URL=<your-llama-stack-ui-url>
|
||||||
|
|
||||||
cd docs/source/distributions/eks
|
cd docs/source/distributions/eks
|
||||||
./apply.sh
|
./apply.sh
|
||||||
```
|
```
|
||||||
|
|
|
@ -21,6 +21,24 @@ else
|
||||||
exit 1
|
exit 1
|
||||||
fi
|
fi
|
||||||
|
|
||||||
|
if [ -z "${GITHUB_CLIENT_ID:-}" ]; then
|
||||||
|
echo "ERROR: GITHUB_CLIENT_ID not set. You need it for Github login to work. Refer to https://llama-stack.readthedocs.io/en/latest/deploying/index.html#kubernetes-deployment-guide"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
if [ -z "${GITHUB_CLIENT_SECRET:-}" ]; then
|
||||||
|
echo "ERROR: GITHUB_CLIENT_SECRET not set. You need it for Github login to work. Refer to https://llama-stack.readthedocs.io/en/latest/deploying/index.html#kubernetes-deployment-guide"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
if [ -z "${LLAMA_STACK_UI_URL:-}" ]; then
|
||||||
|
echo "ERROR: LLAMA_STACK_UI_URL not set. Should be set to the external URL of the UI (excluding port). You need it for Github login to work. Refer to https://llama-stack.readthedocs.io/en/latest/deploying/index.html#kubernetes-deployment-guide"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
set -euo pipefail
|
set -euo pipefail
|
||||||
set -x
|
set -x
|
||||||
|
|
||||||
|
|
|
@ -122,6 +122,9 @@ data:
|
||||||
provider_id: rag-runtime
|
provider_id: rag-runtime
|
||||||
server:
|
server:
|
||||||
port: 8321
|
port: 8321
|
||||||
|
auth:
|
||||||
|
provider_config:
|
||||||
|
type: github_token
|
||||||
kind: ConfigMap
|
kind: ConfigMap
|
||||||
metadata:
|
metadata:
|
||||||
creationTimestamp: null
|
creationTimestamp: null
|
||||||
|
|
|
@ -27,7 +27,7 @@ spec:
|
||||||
spec:
|
spec:
|
||||||
containers:
|
containers:
|
||||||
- name: llama-stack
|
- name: llama-stack
|
||||||
image: llamastack/distribution-remote-vllm:latest
|
image: llamastack/distribution-starter:latest
|
||||||
imagePullPolicy: Always # since we have specified latest instead of a version
|
imagePullPolicy: Always # since we have specified latest instead of a version
|
||||||
env:
|
env:
|
||||||
- name: ENABLE_CHROMADB
|
- name: ENABLE_CHROMADB
|
||||||
|
|
|
@ -119,3 +119,6 @@ tool_groups:
|
||||||
provider_id: rag-runtime
|
provider_id: rag-runtime
|
||||||
server:
|
server:
|
||||||
port: 8321
|
port: 8321
|
||||||
|
auth:
|
||||||
|
provider_config:
|
||||||
|
type: github_token
|
||||||
|
|
|
@ -26,6 +26,12 @@ spec:
|
||||||
value: "http://llama-stack-service:8321"
|
value: "http://llama-stack-service:8321"
|
||||||
- name: LLAMA_STACK_UI_PORT
|
- name: LLAMA_STACK_UI_PORT
|
||||||
value: "8322"
|
value: "8322"
|
||||||
|
- name: GITHUB_CLIENT_ID
|
||||||
|
value: "${GITHUB_CLIENT_ID}"
|
||||||
|
- name: GITHUB_CLIENT_SECRET
|
||||||
|
value: "${GITHUB_CLIENT_SECRET}"
|
||||||
|
- name: NEXTAUTH_URL
|
||||||
|
value: "${LLAMA_STACK_UI_URL}:8322"
|
||||||
args:
|
args:
|
||||||
- -c
|
- -c
|
||||||
- |
|
- |
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue