aljaz/scale-gke-qdrant-llama
1
1
Fork 0
mirror of https://github.com/benitomartin/scale-gke-qdrant-llama.git synced 2025-12-17 19:14:29 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Benito Martin
2024-06-30 14:48:08 +02:00
committed by GitHub
parent ebe271e076
commit 6d23e7ae82
1 changed files with 27 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
README.md
View File

@@ -148,22 +148,38 @@ The Python version used for this project is Python 3.10. You can follow along th
11. Verify Kubernetes is running after deployment 11. Verify Kubernetes is running after deployment
```bash ```bash
# Get the Pods
kubectl get po kubectl get po
# Get the Nodes
kubectl get nodes
# Get the Services
kubectl get svc kubectl get svc
# Get the logs of a pod
kubectl logs llama-gke-deploy-668b58b455-fjwvq
# Describe a pod
kubectl describe pod llama-gke-deploy-668b58b455-fjwvq
# Check CPU usage
kubectl top pod llama-gke-deploy-668b58b455-fjwvq
``` ```
<p align="center"> <p align="center">
<img width="940" alt="Pods Running" src="https://github.com/benitomartin/mlops-car-prices/assets/116911431/d4dee27d-383f-4375-9a21-29996a5b5089"> <img width="790" alt="Nodes, Pods, svc and, usage2" src="https://github.com/benitomartin/rag-aws-qdrant/assets/116911431/6443b831-6642-4bea-b40d-b41977e38d4b">
</p> </p>
12. Under svc the external ip is the endpoint (34.65.157.134), that can be added in the streamlit app 12. Under svc the external ip is the endpoint (34.65.157.134), that can be added in the streamlit app
<p align="center"> ```bash
<img width="767" alt="lambda-gke" src="https://github.com/benitomartin/mlops-car-prices/assets/116911431/b4a7e10c-52f9-4ca2-ade3-f2136ff6bbdf"> # Set the FastAPI endpoint
</p> FASTAPI_ENDPOINT = "http://34.65.157.134:8000/query/"
```
13. Check some pods and logs 14. Check some pods and logs
```bash ```bash
kubectl logs llama-gke-deploy-668b58b455-fjwvq kubectl logs llama-gke-deploy-668b58b455-fjwvq
@@ -171,7 +187,7 @@ The Python version used for this project is Python 3.10. You can follow along th
kubectl top pod llama-gke-deploy-668b58b455-8xfhf kubectl top pod llama-gke-deploy-668b58b455-8xfhf
``` ```
14. Clean up to avoid costs deleting the cluster and the docker image 15. Clean up to avoid costs deleting the cluster and the docker image
```bash ```bash
gcloud container clusters delete llama-gke-cluster --zone=europe-west6-a gcloud container clusters delete llama-gke-cluster --zone=europe-west6-a