Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Bug] can NOT launch ChatQnA on xeon using K8S manifest files #752

Closed
1 of 6 tasks
lianhao opened this issue Sep 6, 2024 · 0 comments
Closed
1 of 6 tasks

[Bug] can NOT launch ChatQnA on xeon using K8S manifest files #752

lianhao opened this issue Sep 6, 2024 · 0 comments
Assignees

Comments

@lianhao
Copy link
Collaborator

lianhao commented Sep 6, 2024

Priority

P1-Stopper

OS type

Ubuntu

Hardware type

Xeon-SPR

Installation method

  • Pull docker images from hub.docker.com
  • Build docker images from source

Deploy method

  • Docker compose
  • Docker
  • Kubernetes
  • Helm

Running nodes

Single Node

What's the version?

The version with PR #669 merged.

Description

Launch ChatQnA on xeon by the following command:

kubectl install -n lianhao-test -f ChatQnA/kubernetes/manifests/xeon/chatqna.yaml

Then check the pod status by the followings:

$ kubectl -n lianhao-test get pod
NAME                                        READY   STATUS             RESTARTS        AGE
chatqna-69b57f4976-p4glm                    1/1     Running            0               7m39s
chatqna-data-prep-5cc8f86b77-plm9s          1/1     Running            0               7m40s
chatqna-embedding-usvc-5898b9766d-7fqzx     1/1     Running            0               7m40s
chatqna-llm-uservice-58ffcbf4d4-gkddl       1/1     Running            0               7m40s
chatqna-nginx-deployment-6555fc5ff7-mjlk7   0/1     CrashLoopBackOff   6 (113s ago)    7m39s
chatqna-redis-vector-db-676fb75667-kqlc2    1/1     Running            0               7m40s
chatqna-reranking-usvc-844dcf794b-sj2c7     1/1     Running            0               7m40s
chatqna-retriever-usvc-6f569d56d5-dr25s     1/1     Running            1 (7m34s ago)   7m40s
chatqna-tei-67b6b789db-n8vqw                1/1     Running            0               7m40s
chatqna-teirerank-657b8b9464-pnkw4          1/1     Running            0               7m40s
chatqna-tgi-ddc6696cb-2pmrw                 1/1     Running            0               7m40s
chatqna-ui-9b85b64d9-svwzd                  1/1     Running            0               7m40s

nginx pod keeps crashing. The root cause of this that in nginx configuration, the upstream URL is hardcoded, which doesn't support install ChatQnA in non-default k8s namespace.

Reproduce steps

kubectl create ns lianhao-test
kubectl install -n lianhao-test -f ChatQnA/kubernetes/manifests/xeon/chatqna.yaml
kubectl -n lianhao-test get pod

Raw log

No response

@lianhao lianhao self-assigned this Sep 6, 2024
lianhao added a commit to lianhao/GenAIExamples that referenced this issue Sep 6, 2024
- Update ChatQnA/CodeGen/CodeTrans/DocSum k8s manifest
  to avoid requiring creating directory for cache model.

- Add chatqna-guardrails manifest files.

- Fix bug opea-project#752 introduced by PR opea-project#669

Signed-off-by: Lianhao Lu <[email protected]>
yongfengdu pushed a commit that referenced this issue Sep 6, 2024
- Update ChatQnA/CodeGen/CodeTrans/DocSum k8s manifest
  to avoid requiring creating directory for cache model.

- Add chatqna-guardrails manifest files.

- Fix bug #752 introduced by PR #669

Signed-off-by: Lianhao Lu <[email protected]>
@lianhao lianhao closed this as completed Sep 6, 2024
xuechendi pushed a commit to xuechendi/GenAIExamples that referenced this issue Sep 9, 2024
- Update ChatQnA/CodeGen/CodeTrans/DocSum k8s manifest
  to avoid requiring creating directory for cache model.

- Add chatqna-guardrails manifest files.

- Fix bug opea-project#752 introduced by PR opea-project#669

Signed-off-by: Lianhao Lu <[email protected]>
dmsuehir pushed a commit to dmsuehir/GenAIExamples that referenced this issue Sep 11, 2024
- Update ChatQnA/CodeGen/CodeTrans/DocSum k8s manifest
  to avoid requiring creating directory for cache model.

- Add chatqna-guardrails manifest files.

- Fix bug opea-project#752 introduced by PR opea-project#669

Signed-off-by: Lianhao Lu <[email protected]>
wangkl2 pushed a commit to wangkl2/GenAIExamples that referenced this issue Dec 11, 2024
* Update Agent vllm client codes and test

Signed-off-by: Chendi.Xue <[email protected]>

* Update README with vllm related update

Signed-off-by: Chendi.Xue <[email protected]>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* remove unnecessary env

Signed-off-by: Chendi.Xue <[email protected]>

* support plan_execute with vllm

Signed-off-by: Chendi.Xue <[email protected]>

* Update README and test llama vllm support

Signed-off-by: Chendi.Xue <[email protected]>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* update vllm_port to 8086 avoid conflict

Signed-off-by: Chendi.Xue <[email protected]>

---------

Signed-off-by: Chendi.Xue <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant