GenAIExamples

Overview of GenAIExamples

What it is

Generative AI Examples (GenAIExamples) is a collection of GenAI examples such as ChatQnA, Copilot, which illustrate the pipeline capabilities of the Open Platform for Enterprise AI (OPEA) project. It is designed to give developers an easy entry into generative AI, featuring microservice-based samples that simplify deploying, testing, and scaling GenAI applications. All examples are compatible with Docker and Kubernetes, supporting hardware platforms including Gaudi, Xeon, AMD EPYC CPUs, AMD Instinct GPUs, and NVIDIA GPUs.

Key features

• Microservice-based architecture using components like llm, embedding, reranking from GenAIComps.
• Supports multiple deployment methods: Python startup, Docker Compose, and Kubernetes.
• Compatible with a wide range of hardware: Gaudi, Xeon, AMD EPYC, AMD Instinct, NVIDIA GPUs.
• Includes GenAIInfra for cloud-native deployment and GenAIEval for performance measurement (throughput, latency, accuracy).
• Covers use cases: ChatQnA, VisualQnA, Text2Image, DocSum, CodeGen, DocIndexRetriever, InstructionTuning.

Use cases

• Question Answering: ChatQnA (chatbot with RAG), VisualQnA (visual question-answering).
• Image Generation: Text2Image (text-to-image generation).
• Content Summarization: DocSum (document summarization).
• Code Generation: CodeGen (AI-powered code generator).
• Information Retrieval: DocIndexRetriever (document retrieval with RAG).
• Fine-tuning: InstructionTuning (instruction tuning application).

Getting started

See the repository README for installation and quick-start commands.

License and pricing

Licensed under Apache-2.0. Open source.

Based on the project's public README and repository metadata.