https://github.com/interactivetech/riva-audio-agent
End to end demo showcasing how to deploy and run an end to end conversational agent in HPE's Private Cloud AI Environment
https://github.com/interactivetech/riva-audio-agent
Last synced: 12 months ago
JSON representation
End to end demo showcasing how to deploy and run an end to end conversational agent in HPE's Private Cloud AI Environment
- Host: GitHub
- URL: https://github.com/interactivetech/riva-audio-agent
- Owner: interactivetech
- Created: 2025-06-27T20:34:49.000Z (12 months ago)
- Default Branch: main
- Last Pushed: 2025-06-27T20:52:23.000Z (12 months ago)
- Last Synced: 2025-06-27T21:34:13.740Z (12 months ago)
- Language: Python
- Size: 0 Bytes
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# End-to-End Audio Conversational Agent in HPE's Private Cloud AI (PCAI) Platform
This repo guides you through:
1. **Docker** → build & push two images (WebSocket server & Gradio UI)
2. **Kubernetes Dev** → a quick `kubectl apply` to test locally
3. **Helm** → package & import into HPE Private Cloud AI (PCAI)
---
## Pre-requisites
Deploy the following models in your HPE Machine Learning Inference Software Tool:
- **magpie-tts-multilingual**
https://build.nvidia.com/nvidia/magpie-tts-multilingual/api
- **parakeet-ctc-1.1b-asr**
https://build.nvidia.com/nvidia/parakeet-ctc-1_1b-asr/modelcard
- **meta-llama/Llama-3.2-1B**
https://huggingface.co/meta-llama/Llama-3.2-1B
---
## Quickstart
1. **Docker**
```bash
cd docker
bash build.sh
```
See docker/README.md.
2. Kubernetes Dev
```bash
cd dev-k8s-deployment
kubectl apply -f pod-svc-vs.yaml
```
3. Helm & PCAI
```bash
cd helm
helm package .
```
Import audio-pipeline-chart-0.1.0.tgz via PCAI’s Tools & Frameworks → Import Framework.
See helm/README.md.
Now you’re all set to run your end-to-end audio AI pipeline on HPE Private Cloud AI!