Deploying GenAI¶
GenAIInfra is the containerization and cloud native suite for OPEA, including artifacts to deploy GenAI Examples in a cloud native way so enterprise users can deploy to their own cloud.
We’re building this documentation from content in the GenAIInfra GitHub repository.
Installation Guides¶
CI/CD ENV Setup¶
Cloud Service Provider¶
Helm Charts¶
- Helm charts for deploying GenAI Components and Examples
- CI guidelines for helm charts
- HorizontalPodAutoscaler (HPA) support
- Deployment of the Helm Charts on Intel® Xeon® Processors with Intel® Trust Domain Extensions (Intel® TDX)
- Observability for OPEA Workloads in Kubernetes
- agent
- asr
- chathistory-usvc
- Dashboards
- data-prep
- embedding-usvc
- gpt-sovits
- guardrails-usvc
- llm-uservice
- OPEA lvm-serve microservice
- lvm-uservice
- OPEA mm-embedding microservice
- mongodb
- OPEA nginx microservice
- ollama
- prompt-usvc
- redis-vector-db
- reranking-usvc
- retriever-usvc
- speecht5
- tei
- teirerank
- OPEA text2image microservice
- tgi
- tts
- vllm
- web-retriever
- whisper
- AgentQnA
- AudioQnA
- ChatQnA
- ChatQnA Troubleshooting
- CodeGen
- CodeTrans
- DocSum
- FinanceAgent
- SearchQnA
- txt2img
- VisualQnA