AvatarChatbot Application

The AvatarChatbot example demonstrates the implementation of AI avatar chatbot using OPEA component-level microservices.

Table of contents

1. Architecture

2. Deployment Options

Architecture

The AI Avatar example is implemented using both megaservices and the component-level microservices defined in GenAIComps. The flow chart below shows the information flow between different megaservices and microservices for this example.

flowchart LR classDef blue fill:#ADD8E6,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5 classDef thistle fill:#D8BFD8,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5 classDef orange fill:#FBAA60,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5 classDef orchid fill:#C26DBC,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5 classDef invisible fill:transparent,stroke:transparent; style AvatarChatbot-Megaservice stroke:#000000 subgraph AvatarChatbot-Megaservice["AvatarChatbot Megaservice"] direction LR ASR([ASR Microservice]):::blue LLM([LLM Microservice]):::blue TTS([TTS Microservice]):::blue animation([Animation Microservice]):::blue end subgraph UserInterface["User Interface"] direction LR invis1[ ]:::invisible USER1([User Audio Query]):::orchid USER2([User Image/Video Query]):::orchid UI([UI server<br>]):::orchid end GW([AvatarChatbot GateWay<br>]):::orange subgraph . direction LR X([OPEA Microservice]):::blue Y{{Open Source Service}}:::thistle Z([OPEA Gateway]):::orange Z1([UI]):::orchid end WHISPER{{Whisper service}}:::thistle TGI{{LLM service}}:::thistle T5{{Speecht5 service}}:::thistle WAV2LIP{{Wav2Lip service}}:::thistle %% Connections %% direction LR USER1 -->|1| UI UI -->|2| GW GW <==>|3| AvatarChatbot-Megaservice ASR ==>|4| LLM ==>|5| TTS ==>|6| animation direction TB ASR <-.->|3'| WHISPER LLM <-.->|4'| TGI TTS <-.->|5'| T5 animation <-.->|6'| WAV2LIP USER2 -->|1| UI UI <-.->|6'| WAV2LIP

This AvatarChatbot use case performs AI avatar chatbot across multiple platforms. Currently, we provide the example for Intel Gaudi2 and Intel Xeon Scalable Processors, and we invite contributions from other hardware vendors to expand OPEA ecosystem.

Deployment Options

The table below lists the available deployment options and their implementation details for different hardware platforms.

Platform	Deployment Method	Link
Intel Xeon	Docker compose	Deployment on Xeon
Intel Gaudi2	Docker compose	Deployment on Gaudi
AMD ROCm	Docker compose	Deployment on AMD Rocm

Validated Configurations

Deploy Method	LLM Engine	LLM Model	Hardware
Docker Compose	TGI	Intel/neural-chat-7b-v3-3	Intel Gaudi
Docker Compose	TGI	Intel/neural-chat-7b-v3-3	Intel Xeon
Docker Compose	TGI	Intel/neural-chat-7b-v3-3	AMD ROCm