https://github.com/googlecloudplatform/cloudsql-jump-start-solution-for-genai
A jump start solution using GKE or Cloud Run with Cloud SQL and VertexAI
https://github.com/googlecloudplatform/cloudsql-jump-start-solution-for-genai
cloud-run gke google-cloud
Last synced: 3 months ago
JSON representation
A jump start solution using GKE or Cloud Run with Cloud SQL and VertexAI
- Host: GitHub
- URL: https://github.com/googlecloudplatform/cloudsql-jump-start-solution-for-genai
- Owner: GoogleCloudPlatform
- License: apache-2.0
- Created: 2024-01-26T20:35:18.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-11-18T21:30:44.000Z (about 1 year ago)
- Last Synced: 2024-12-18T08:40:03.384Z (about 1 year ago)
- Topics: cloud-run, gke, google-cloud
- Language: HCL
- Homepage:
- Size: 1.51 MB
- Stars: 35
- Watchers: 16
- Forks: 16
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Codeowners: .github/CODEOWNERS
Awesome Lists containing this project
README
# Deploy a production ready GenAI app in less than 30 minutes
Here is a jump start solution of how to build a basic chatbot API that:
- Leverages GKE or Cloud Run with Cloud SQL, VertexAI, and pgvector
- Demonstrates connectivity to Cloud SQL using Private Service Connect in a VPC
- Codifies all infrastructure including using Terraform
- Uses Python with asyncpg and FastAPI
- (optional) Supports cross-project setups with Cloud SQL and GKE or Cloud Run
in separate projects
This solution is an operationalized version of a previously published colab,
[Building AI-powered data-driven applications using pgvector, LangChain and
LLMs][colab].
[colab]: https://colab.sandbox.google.com/github/GoogleCloudPlatform/python-docs-samples/blob/main/cloud-sql/postgres/pgvector/notebooks/pgvector_gen_ai_demo.ipynb
## Choose your Architecture
This app can be deployed with two different flavors:
- Cloud Run
- Google Kubernetes Engine (GKE)
### Cloud Run ([README](run/README.md))

To deploy the app using Cloud Run head to the [run](run/README.md) folder.
### GKE ([README](gke/README.md))

To deploy the app using GKE head to the [gke](gke/README.md) folder.