OPEA™ Logo
latest
OPEA Project v: latest
Document Versions
latest
1.0
1.1
1.2
1.3
OPEA Project links
Project Home
Wiki
  • Documentation Home
  • OPEA Overview
    • OPEA Project Architecture
      • Microservices: Flexible and Scalable Architecture
      • Megaservices: A Comprehensive Solution
      • Gateways: Customized Access to Mega- and Microservices
    • Next Step
      • Open Platform for Enterprise AI (OPEA) Framework Draft Proposal
        • 1. Summary
        • 2. Introduction
        • 3. Framework Components, Architecture and Flow
        • 4. Assessing GenAI components and flows
        • 5. Grading Structure
        • 6. Reference flows
        • Appendix A – Draft OPEA Specifications
  • Getting Started with OPEA
    • Understanding OPEA’s Core Components
    • Prerequisites
    • Create and Configure a Virtual Server
    • Deploy the ChatQnA Solution
      • Interact with ChatQnA
    • What’s Next
      • Get Involved
  • OPEA Tutorials
    • AgentQnA
      • Overview
      • Purpose
      • How It Works
      • Deployment
        • Single Node
    • AudioQnA
      • Overview
      • Purpose
      • Key Implementation Details
      • How It Works
      • Deployment
        • Single Node
    • ChatQnA
      • Overview
      • Purpose
      • Key Implementation Details
      • How It Works
        • Customize with new VectorDB
        • Expected Output
        • Validation Matrix and Prerequisites
      • Architecture
        • Microservice Outline and Diagram
      • Deployment
      • Single Node
        • Xeon Scalable Processor
        • Gaudi AI Accelerator
        • Nvidia GPU
        • AI PC
      • Kubernetes
        • Getting Started
        • Kubernetes Deployment with Helm on Xeon
      • Cloud Native
      • Troubleshooting
      • Monitoring
        • Set Up the Prometheus Server
        • Set Up the Grafana Dashboard
        • Summary and Next Steps
    • CodeGen
      • Overview
      • Purpose
      • How It Works
      • Deployment
        • Intel® Xeon® Scalable processor
        • Gaudi AI Accelerator
    • Code Translation
      • Overview
      • Purpose
      • How It Works
      • Deployment
        • Single Node
    • DocSum
      • Overview
      • Purpose
      • How It Works
      • Deployment
        • Intel® Xeon® Scalable processor
        • Gaudi AI Accelerator
    • DocIndexRetriever
      • Overview
      • Purpose
      • Key Implementation Details
      • How It Works
      • Deployment
        • Single Node
    • VideoQnA
      • Overview
      • Purpose
      • How It Works
      • Deployment
    • Enterprise Inference Guide
      • Overview
      • How It Works
      • Setting Up a Remote Server or Cluster
      • Using Remote Endpoints on OPEA GenAIExamples
        • 1. Endpoints with Megaservices
        • 2. Endpoints with Microservices
      • Next Steps
    • OpenTelemetry on OPEA Guide
      • Overview
      • How It Works
      • How to Monitor
        • 1. Prometheus
        • 2. Grafana
        • 3. Jaeger
      • Code Instrumentations for OPEA Tracing
      • OpenTelemetry on GenAIExamples
        • ChatQnA
        • AgentQnA
  • GenAI Examples
    • Generative AI Examples
      • Introduction
      • Architecture
      • Use Cases
      • Documentation
      • Getting Started
        • Deployment Guide
      • Supported Examples
      • Validated Configurations
      • Contributing to OPEA
      • Additional Content
    • Examples
      • AgentQnA Application
        • Agents for Question and Answering Application
        • Agents for Question and Answering Application
        • Build Service Docker Image
        • Deploy AgentQnA on AMD GPU (ROCm)
        • Deploying AgentQnA on Intel® Xeon® Processors
        • Deploying AgentQnA on Intel® Gaudi® Processors
        • Deploy AgentQnA on Kubernetes cluster
        • Retrieval tool for agent
      • ArbPostHearingAssistant Application
        • Arbitration Post-Hearing Assistant
        • Table of Contents
        • Deploy Arbitration Post-Hearing Assistant Application on AMD EPYC™ Processors with Docker Compose
        • Example Arbitration Post-Hearing Assistant deployments on AMD GPU (ROCm)
        • Example Arbitration Post-Hearing Assistant deployments on Intel Xeon Processor
        • Example Arbitration Post-Hearing Assistant deployments on Intel® Gaudi® Platform
        • DocSum E2E test scripts
        • Arbitration Post-Hearing Assistant
      • AudioQnA Application
        • AudioQnA Application
        • AudioQnA Docker Image Build
        • AudioQnA Accuracy
        • AudioQnA Benchmarking
        • Deploying AudioQnA on AMD EPYC™ Processors
        • Deploying AudioQnA on AMD ROCm GPU
        • Deploying AudioQnA on Intel® Xeon® Processors
        • Deploy AudioQnA application
        • Deploying AudioQnA on Intel® Gaudi® Processors
        • Deploy AudioQnA in Kubernetes Cluster on Xeon and Gaudi
        • Deploy AudioQnA on Kubernetes cluster
        • AudioQnA E2E test scripts
        • AudioQnA
      • AvatarChatbot Application
        • AvatarChatbot Application
        • Build Mega Service of AvatarChatbot on AMD GPU
        • Example AvatarChatbot Deployment on Intel® Xeon® Platform
        • Example AvatarChatbot Deployment on Intel® Gaudi® Platform
        • AvatarChatbot E2E test scripts
      • BrowserUseAgent Application
        • Browser-use Agent Application
        • Example BrowserUseAgent deployments on an Intel® Gaudi® Platform
        • Setup Scripts for Webarena
      • ChatQnA Application
        • ChatQnA Application
        • ChatQnA Docker Image Build
        • ChatQnA Benchmark Results
        • ChatQnA Accuracy
        • FaqGen Accuracy
        • FaqGen Benchmarking
        • Deploying ChatQnA on AMD EPYC™ Processors
        • Deploying FAQ Generation on AMD EPYC™ Processors
        • Deploying ChatQnA with Pinecone on AMD EPYC™ Processors
        • Deploying ChatQnA with Qdrant on AMD EPYC™ Processors
        • Deploying ChatQnA on AMD ROCm GPU
        • Build Mega Service of ChatQnA on AIPC
        • Deploying ChatQnA on Intel® Xeon® Processors
        • Build Mega Service of ChatQnA on Xeon with an LLM Endpoint
        • Deploying FAQ Generation on Intel® Xeon® Processors
        • Deploying ChatQnA with MariaDB Vector on Intel® Xeon® Processors
        • Deploying ChatQnA with openGauss on Intel® Xeon® Processors
        • Deploying ChatQnA with Pinecone on Intel® Xeon® Processors
        • Deploying ChatQnA with Qdrant on Intel® Xeon® Processors
        • Example ChatQnA deployments on an Intel® Gaudi® Platform
        • How to Check and Validate Micro Service in the GenAI Example
        • Build MegaService of ChatQnA on NVIDIA GPU
        • Deploy ChatQnA in Kubernetes Cluster on Xeon and Gaudi
        • Deploy ChatQnA on Kubernetes cluster
        • ChatQnA E2E test scripts
        • ChatQnA Conversational UI
        • ChatQnA Customized UI
      • CodeGen Application
        • Code Generation Example (CodeGen)
        • CodeGen Accuracy Benchmark
        • CodeGen Performance Benchmark
        • Deploy CodeGen Application on AMD EPYC™ Processors with Docker Compose
        • Deploy CodeGen Application on AMD GPU (ROCm) with Docker Compose
        • To deploy the CodeGen services, execute the docker compose up command with the appropriate arguments. For a TGI deployment, execute:
        • Deploy CodeGen Application on Intel Xeon CPU with Docker Compose
        • Deploy CodeGen Application on Intel Gaudi HPU with Docker Compose
        • Deploy CodeGen using Kubernetes Microservices Connector (GMC)
        • Deploy CodeGen on Kubernetes using Helm
        • CodeGen E2E test scripts
        • Document Summary
        • Code Gen
        • Code Gen
      • CodeTrans Application
        • Code Translation Application
        • CodeTrans Docker Image Build
        • CodeTrans Benchmarking
        • Deploy CodeTrans Application on AMD EPYC™ Processors with Docker Compose
        • Deploying CodeTrans on AMD ROCm GPU
        • Deploying CodeTrans on Intel® Xeon® Processors
        • Deploying CodeTrans on Intel® Gaudi® Processors
        • Deploy CodeTrans in a Kubernetes Cluster
        • Deploy CodeTrans on Kubernetes cluster
        • CodeTrans E2E test scripts
        • Code Translation
      • CogniwareIms Application
        • CogniwareIMS - AI-Powered Inventory Management System
        • Kubernetes Deployment for Cogniware IMS
        • Publish Cogniware IMS Helm Chart
        • Cogniware IMS End-to-End Tests
      • DBQnA Application
        • DBQnA Application
        • Example DBQnA Deployment on AMD GPU (ROCm)
        • Example DBQnA Deployment on Intel® Xeon® Platform
        • DBQnA E2E test scripts
        • DBQnA React Application
      • DeepResearchAgent Application
        • Deep Research Agent Application
        • Deep Research Agent Benchmarks
      • DocIndexRetriever Application
        • DocRetriever Application
        • DocRetriever Application with Docker
        • DocRetriever Application with Docker
        • DocIndexRetriever E2E test scripts
      • DocSum Application
        • Document Summarization Application
        • Table of Contents
        • Deploy DocSum Application on AMD EPYC™ Processors with Docker Compose
        • Example DocSum deployments on AMD GPU (ROCm)
        • Example DocSum deployments on Intel Xeon Processor
        • Example DocSum deployments on Intel® Gaudi® Platform
        • Deploy DocSum in Kubernetes Cluster
        • Deploy DocSum on Kubernetes cluster
        • DocSum E2E test scripts
        • Document Summary
        • Doc Summary React
        • Doc Summary
      • EdgeCraftRAG Application
        • Edge Craft Retrieval-Augmented Generation Application
        • EdgeCraft RAG CLI
        • Example Edge Craft Retrieval-Augmented Generation Deployment on Intel® Arc® Platform
        • 在 Intel® Arc® 平台上部署 Edge Craft 检索增强生成（EC-RAG）示例
        • Edge Craft Retrieval-Augmented Generation API Guide
        • Edge Craft Retrieval-Augmented Generation Advanced Setup
        • Edge Craft 检索增强生成（EC-RAG）高级部署说明
        • EC-RAG Agent Guide
        • EC-RAG智能体指南
        • EC-RAG Experience Guide
        • EC-RAG 经验注入指南
        • Explore Edge Craft RAG
        • 探索 Edge Craft RAG
        • EdgeCraftRAG E2E test scripts
        • 1.Script Overview
        • 2.Quick Deployment Script (New Users)
        • 3.Startup Scripts
        • 4.Container Image Build Script
        • 1.脚本介绍
        • 2.快速部署脚本（新用户）
        • 3.启动脚本
        • 4.容器镜像编译脚本
      • FinanceAgent Application
        • Finance Agent Example
        • Deploy Finance Agent on Intel® Xeon® Scalable processors with Docker Compose
        • Deploy Finance Agent on Intel® Gaudi® AI Accelerator with Docker Compose
      • GraphRAG Application
        • GraphRAG Application
        • About GraphRAG LLMs
        • GraphRAG Application
        • Example GraphRAG Deployment on Intel® Gaudi® Platform
        • GraphRAG Example Datasets
        • GraphRAG E2E test scripts
        • ChatQnA Conversational UI
        • ChatQnA Customized UI
      • HybridRAG Application
        • HybridRAG Application
        • Notice for FFmpeg:
        • Example HybridRAG deployments on an Intel® Gaudi® Platform
        • ChatQnA Customized UI
      • InstructionTuning Application
        • Instruction Tuning
        • Table of contents
        • Deploy Instruction Tuning Service on Intel® Xeon® Processors
        • Table of contents
        • Deploy Instruction Tuning Service on Intel® Gaudi® Platform
        • Table of contents
        • Translation E2E test scripts
      • MultimodalQnA Application
        • MultimodalQnA Application
        • MultimodalQnA Docker Image Build
        • Build Mega Service of MultimodalQnA on AMD EPYC™ Processors
        • Deploying MultimodalQnA on AMD GPU (ROCm)
        • Table of Contents
        • Deploying MultimodalQnA on Intel® Xeon® Processors
        • Deploying MultimodalQnA on Intel® Gaudi® Processors
        • MultimodalQnA E2E test scripts
      • PolyLingua Application
        • PolyLingua
        • PolyLingua UI
      • ProductivitySuite Application
        • Productivity Suite Application
        • Build Mega Service of Productivity Suite on AMD EPYC™ Processors
        • 🔐 Keycloak Configuration Setup
        • Example Productivity Suite Deployment on Intel® Xeon® Platform
        • 🔐 Keycloak Configuration Setup
        • ProductivitySuite E2E test scripts
        • Productivity Suite React UI
      • RerankFinetuning Application
        • Rerank Model Finetuning
        • Deploy Rerank Model Finetuning Service on Xeon
        • Deploy Rerank Model Finetuning Service on Gaudi
      • SearchQnA Application
        • SearchQnA Application
        • SearchQnA Docker Image Build
        • Deploying SearchQnA on AMD EPYC™ Processors
        • Deploying SearchQnA on AMD ROCm Platform
        • Deploying SearchQnA on Intel® Xeon® Processors
        • Deploying searchqna on Intel® Gaudi® Processors
        • Deploy SearchQnA in a Kubernetes Cluster
        • Deploy SearchQnA on Kubernetes cluster
        • SearchQnA E2E test scripts
        • Neural Chat
      • Text2Image Application
        • Text-to-Image Microservice
        • Deploy Text-to-Image Service on AMD EPYC™ Processors
        • Deploy Text-to-Image Service on Xeon
        • Deploy Text-to-Image Service on Gaudi
        • Deploy txt2img on Kubernetes cluster
        • Text2Image E2E test scripts
        • Text2Image Customized UI
      • Translation Application
        • Translation Application
        • Example Translation Deployment on AMD EPYC™ Platform
        • Example Translation Deployment on AMD GPU (ROCm)
        • Example Translation Deployment on Intel® Xeon® Platform
        • Example Translation Deployment on Intel® Gaudi® Platform
        • Deploy Translation in a Kubernetes Cluster
        • Translation E2E test scripts
        • Language Translation
      • VideoQnA Application
        • VideoQnA Application
        • Build Mega Service of VideoQnA on Xeon
      • VisualQnA Application
        • Visual Question and Answering
        • VisualQnA Docker Image Build
        • VisualQnA Benchmarking
        • Build Mega Service of VisualQnA on AMD EPYC™ Processors
        • Deploy VisualQnA on AMD GPU (ROCm)
        • Deploying VisualQnA on Intel® Xeon® Processors
        • Deploying VisualQnA on Intel® Gaudi® Processors
        • Deploy VisualQnA in a Kubernetes Cluster
        • Deploy VisualQnA on Kubernetes cluster
        • VisualQnA E2E test scripts
      • WorkflowExecAgent Application
        • Workflow Executor Agent
        • Deploying WorkflowExecAgent on Intel® Xeon® Processors
        • Validate Workflow Agent Microservice
      • one_click_deploy Application
        • One-Click Deployment for GenAI Examples
    • Legal Information
      • License
      • Citation
    • Deploy and Benchmark
      • Purpose
        • Support Example List
      • Table of Contents
      • Prerequisites
      • Data Preparation
      • Running Deploy and Benchmark Tests
        • Running the Tests
        • Test Modes
        • Troubleshooting
      • ChatQnA Release Data
    • Docker Images
      • Example images
      • Microservice images
    • Supported Examples
      • ChatQnA
        • CodeGen
        • CodeTrans
        • DocSum
        • Language Translation
        • SearchQnA
        • VisualQnA
        • VideoQnA
        • RerankFinetuning
        • InstructionTuning
        • DocIndexRetriever
        • AgentQnA
        • AudioQnA
        • MultimodalQnA
        • ProductivitySuite
        • DBQnA
        • Text2Image
        • AvatarChatbot
    • Validated Configurations
      • v1.3 Release Test Config Overview
      • v1.4 Release Test Config Overview
  • GenAI Microservices
    • Generative AI Components (GenAIComps)
      • GenAIComps
        • Installation
      • MicroService
      • MegaService
      • Contributing to OPEA
        • uv pip compile usage
      • Additional Content
    • Legal Information
      • License
      • Citation
    • Agent Microservice
      • Deploy Agent microservice on Kubernetes cluster
        • Deploy on Kubernetes
      • Agent Microservice
        • Table of Contents
        • Quick Start Deployment
        • Supported agent types
        • Docker Compose Files
        • Other Supported Features
        • Customizations
      • Plan Execute Agent Microservice
      • RAG Agent Microservice
      • SQL Agent Microservice
        • Table of Contents
        • Overview of sql_agent_llama
        • Overview of sql_agent
        • Limitations
    • Animation Microservice
      • Deploying Avatar Animation Service
        • 🚀 1. Quick Start with Docker Compose
        • 🚀 2. Manual Step-by-Step Deployment (Advanced)
      • Avatar Animation Microservice
        • Table of contents
        • Architecture
        • Deployment Options
        • Validated Configurations
    • Arb_post_hearing_assistant Microservice
      • Arbitrator Post-Hearing Assistant
        • Features
        • Benefits
        • Table of Contents
        • Start Microservice
    • Asr Microservice
      • Deploy ASR microservice on Kubernetes cluster
        • Deploy on Kubernetes
      • ASR Microservice
        • Table of contents
        • Architecture
        • Deployment Options
        • Validated Configurations
      • Deploying ASR Service
        • Table of contents
        • 🚀 1. Quick Start with Docker Compose
        • 🚀 2. Manual Step-by-Step Deployment (Advanced)
        • 🚀 3. Start Microservice with Python
      • Deploying ASR Service
        • Table of contents
        • 🚀 1. Quick Start with Docker Compose
        • 🚀 2. Manual Step-by-Step Deployment (Advanced)
        • 🚀 3. Start Microservice with Python
    • Chathistory Microservice
      • 📝 Chat History Microservice
        • 🛠️ Features
        • ⚙️ Deployment Options
      • 📝 Chat History Microservice with MongoDB
        • Setup Environment Variables
        • 🚀 Start Microservice with Docker (Option 1)
        • 🚀 Start Microservice with Docker Compose (Option 2)
        • ✅ Invoke Microservice
      • 📝 Chat History Microservice with ArangoDB
        • Setup Environment Variables
        • 🚀 Start Microservice with Docker (Option 1)
        • 🚀 Start Microservice with Docker Compose (Option 2)
        • ✅ Invoke Microservice
      • 📝 Chat History Microservice with Redis
        • Setup Environment Variables
        • 🚀 Start Microservice with Docker (Option 1)
        • 🚀 Start Microservice with Docker Compose (Option 2)
        • ✅ Invoke Microservice
      • Deploy chathistory microservice on Kubernetes cluster
        • Deploy on Kubernetes
    • Cores Microservice
      • OPEA MCP Tool
        • OPEA MCP Tool Overview
        • API Usage
        • Examples
      • Contributing to Storage
        • Storage
        • Adding a New Storage Backend
        • Example
      • Telemetry for OPEA
        • Metrics
        • Statistics
        • Tracing
        • Visualization
    • Dataprep Microservice
      • Dataprep Microservice
        • Table of contents
        • Install Requirements
        • Summarizing Image Data with LVM
        • Dataprep Microservice on Various Databases
        • Running in the air gapped environment
      • Deploy dataprep microservice on Kubernetes cluster
        • Table of contents
        • Deploy on Kubernetes with redis VectorDB
        • Deploy on Kubernetes with milvus VectorDB
      • Dataprep Microservice with ArangoDB
        • Table of contents
        • 🚀Start Microservice with Docker
        • 🚀Consume Dataprep Service
      • Dataprep Microservice with Elasticsearch
        • Table of contents
        • 🚀1. Start Microservice with Docker
        • 🚀2. Consume Microservice
      • Dataprep microservice for financial domain data
        • Table of contents
        • 1. Overview
        • 2. Deploy with docker
        • 3. Consume Microservice
      • Dataprep Microservice with MariaDB Vector
        • Table of contents
        • 🚀1. Start Microservice with Docker
        • 🚀2. Consume Microservice
      • Dataprep Microservice with Milvus
        • Table of contents
        • 🚀1. Start Microservice with Docker
        • 🚀2. Consume Microservice
        • 🚀3. Troubleshooting
        • Running in the air gapped environment
      • Dataprep Microservice for Multimodal Data with Redis
        • Table of contents
        • 🚀1. Start Microservice with Docker
        • 🚀2. Status Microservice
        • 🚀3. Consume Microservice
      • Dataprep Microservice with Neo4J
        • Table of contents
        • Start Microservice with Docker
        • Invoke Microservice
      • Dataprep Microservice with Neo4J
        • Table of contents
        • Start Microservice with Docker
        • Invoke Microservice
      • Dataprep Microservice with openGauss
        • Table of contents
        • 🚀1. Start Microservice with Docker
        • 🚀2. Consume Microservice
      • Dataprep Microservice with OpenSearch
        • Table of contents
        • 🚀1. Start Microservice with Docker
        • 🚀2. Status Microservice
        • 🚀3. Consume Microservice
      • Dataprep Microservice with PGVector
        • Table of contents
        • 🚀1. Start Microservice with Docker
        • 🚀2. Consume Microservice
      • Dataprep Microservice with Pinecone
        • Table of contents
        • 🚀Start Microservice with Docker
        • Invoke Microservice
      • Dataprep Microservice with Qdrant
        • Table of contents
        • 🚀Start Microservice with Docker
        • Invoke Microservice
        • Running in the air gapped environment
      • Dataprep Microservice with Redis
        • Table of contents
        • 🚀1. Start Microservice with Docker
        • 🚀2. Status Microservice
        • 🚀3. Consume Microservice
        • Running in the air gapped environment
      • Dataprep Microservice with VDMS
        • Table of contents
        • 🚀1. Start Microservice with Docker (Option 2)
        • 🚀2. Status Microservice
        • 🚀3. Consume Microservice
    • Embeddings Microservice
      • Embeddings Microservice
        • Table of Contents
        • Overview
        • Key Features
        • Supported Implementations
      • Deploy Embedding microservice on Kubernetes cluster
        • Deploy on Kubernetes
      • Multimodal Embeddings Microservice
        • Table of Contents
        • Start Microservice
        • Consume Embedding Service
        • Running in the air gapped environment
      • Multimodal CLIP Embedding Microservice
        • Table of Contents
        • Start Microservice
        • Consume Embedding Service
      • Embedding Microservice with OpenVINO Model Server (OVMS)
        • Table of Contents
        • Start Microservice with docker run
        • Start Microservice with Docker Compose
        • Consume Embedding Service
        • Tips for Better Understanding
      • Embedding Microservice with Prediction Guard
        • Table of Contents
        • Start Microservice with docker run
        • Start Microservice with Docker Compose
        • Consume Embedding Service
        • Tips for Better Understanding
      • Embedding Microservice with TEI
        • Table of Contents
        • Start Microservice with docker run
        • Start Microservice with Docker Compose
        • Consume Embedding Service
        • Tips for Better Understanding
    • Feedback_management Microservice
      • 🗨 Feedback Management Microservice
        • 🛠️ Features
        • ⚙️ Deployment Options
      • 🗨 Feedback Management Microservice with MongoDB
        • Setup Environment Variables
        • 🚀 Start Microservice with Docker (Option 1)
        • 🚀 Start Microservice with Docker Compose (Option 2)
      • 🗨 Feedback Management Microservice with ArangoDB
        • Setup Environment Variables
        • 🚀 Start Microservice with Docker (Option 1)
        • 🚀 Start Microservice with Docker Compose (Option 2)
      • 🗨 Feedback Management Microservice with Redis
        • Setup Environment Variables
        • 🚀 Start Microservice with Docker (Option 1)
        • 🚀 Start Microservice with Docker Compose (Option 2)
    • Finetuning Microservice
      • Fine-tuning Microservice
        • Table of contents
        • 🚀1. Start Microservice with Python (Option 1)
        • 🚀2. Start Microservice with Docker (Option 2)
        • 🚀3. Consume Finetuning Service
        • 🚀4. Descriptions for Finetuning parameters
      • XTune - Model finetune tool for Intel GPU
        • Table of contents
        • Installation
        • Data Preparation
        • Fine-Tuning with LLaMA Board GUI (powered by Gradio)
        • Fine-Tuning with Shell instead of GUI
        • Xtune Examples
        • Citation
        • Acknowledgement
      • Dataset
        • Dataset for CLIP
        • Dataset for AdaCLIP
        • Preprocessing
        • Dataset for Qwen2-VL & Qwen2.5-VL Finetune
        • Update dataset_info.json
      • Qwen2-VL & Qwen2.5-VL Finetune and Hyperparameter Optimization
        • Table of Contents
        • Features
        • Configuration Differences Between Qwen2-VL and Qwen2.5-VL
        • Usage
        • Configuration Parameters
        • Optuna features
      • <<<<<<< HEAD
        • Output and Results
        • Calculation and Plotting of Evaluation Metrics During Fine-Tuning
      • AdaCLIP-Finetune
      • Prerequisites
      • How to Install
        • Install on NVIDIA
        • Install on Arc A770
      • Prepare Datasets
        • Datasets
        • Frame Extraction
        • Dataset JSON prepare
      • Implemented finetune methods
        • BitFit & SSF
        • Importance Based Selection (IBS)
        • Performance of different finetune methods
      • How to Finetune
        • Finetune on NVIDIA
        • Finetune on Arc A770
      • Use optuna to automatic get the best param
        • Visualization
      • Install linux kernel
      • Install Driver
        • Optional:
      • The core features for clip finetune tool:
      • How to config features for clip finetune tool:
        • Basic yaml for vit_b16.yaml
        • Angle-Based Selection for full-finetune
        • customize trained layer for partial-finetune
        • fixed cache size for tip-adapter
    • Guardrails Microservice
      • Trust and Safety with LLM
      • Deploy guardrails microservice on Kubernetes cluster
        • Deploy on Kubernetes
      • Bias Detection Microservice
        • Table of Contents
        • Introduction
        • Future Development
        • Start Microservice
      • Factuality Check Prediction Guard Microservice
        • Table of Contents
        • Introduction
        • Start Microservice with Docker
        • Consume Factuality Check Service
      • Guardrails Microservice
        • Table of Contents
        • Introduction
        • Setups
        • Start Microservice
        • Consume Microservice
      • Hallucination Detection Microservice
        • Table of Contents
        • Introduction
        • Start Microservice
        • Set up Microservice
        • Consume Guardrail Micorservice
      • PII Detection Microservice
        • Table of Contents
        • Introduction
        • Environment Setup
        • Start Microservice
        • Get Status of Microservice
        • Consume Microservice
      • Prompt Injection and Jailbreak Detection Microservice
        • Table of Contents
        • Introduction
        • Environment Setup
        • Start Microservice with Docker
        • Get Status of Microservice
        • Consume Prompt Injection Detection Service
      • Toxicity Detection Microservice
        • Table of Contents
        • Introduction
        • Environment Setup
        • Start Microservice with Python（Option 1）
        • Start Microservice with Docker (Option 2)
        • Get Status of Microservice
        • Consume Microservice Pre-LLM/Post-LLM
    • Image2image Microservice
      • Deploying Image-to-Image Service
        • 🚀 1. Quick Start with Docker Compose
        • 🚀 2. Manual Step-by-Step Deployment (Advanced)
      • Image-to-Image Microservice
        • Table of contents
        • Architecture
        • Deployment Options
        • Validated Configurations
    • Image2video Microservice
      • Deploying Image-to-Video Service
        • 🚀 1. Quick Start with Docker Compose
        • 🚀 2. Manual Step-by-Step Deployment (Advanced)
      • Image-to-Video Microservice
        • Table of contents
        • Architecture
        • Deployment Options
        • Validated Configurations
    • Language_detection Microservice
      • Deploying language-detection Service
        • 🚀 1. Quick Start with Docker Compose
        • 🚀 2. Manual Step-by-Step Deployment (Advanced)
        • 🚀 3. Start Language Detection Microservice with Python
      • Language Detection microservice
        • Table of contents
        • Architecture
        • Deployment Options
        • Validated Configurations
    • Llms Microservice
      • Deploy LLM microservice on Kubernetes cluster
        • Deploy on Kubernetes
      • Document Summary LLM Microservice
        • Table of Contents
        • Start Microservice
        • Consume Microservice
        • Air-Gapped Environment Usage
      • FAQGen LLM Microservice
        • Table of Contents
        • Start Microservice
        • Consume Microservice
      • LLM Text Generation Microservice
        • Table of Contents
        • Validated LLM Models
        • Start Microservice
        • Consume Microservice
      • OPEA Text Generation Microservice (Amazon Bedrock)
        • Table of Contents
        • Setup Environment Variables
        • Build Docker Image
        • Start Microservice
        • Consume Microservice
      • OPEA Text Generation Microservice (OpenAI-Compatible Endpoint)
        • Table of Contents
        • Prepare Docker Image
        • Setup Environment Variables
        • Start Microservice
        • Consume Microservice
      • LLM Native Microservice
        • Table of Contents
        • Start Microservice
        • Consume Microservice
      • LLM OVMS Microservice
        • Table of Contents
        • Start OVMS Microservice
        • Start OPEA LLM Microservice
        • Consume Microservice
        • Tips
      • Prediction Guard Microservice
        • Table of Contents
        • Start Microservice
        • Consume Microservice
      • LLM Microservice with vLLM on Intel XPU
        • Table of Contents
        • Prerequisites
        • Start Microservice
        • Consume LLM Service
      • LM-Eval Microservice
        • CPU service
    • Lvms Microservice
      • LVM Microservice
        • Table of Contents
        • Overview
        • Key Features
        • Supported Implementations
      • Deploy LVM microservice on Kubernetes cluster
        • Deploy on Kubernetes
      • LVM Microservice with LLaMA-Vision
        • Table of Contents
        • Start Microservice
        • Consume LVM Service
      • LVM Microservice with LLaVA
        • Table of Contents
        • Start Microservice
        • Consume LVM Service
      • LVM Microservice with TGI-accelerated LLaVA
        • Table of Contents
        • Start Microservice
        • Consume LVM Service
      • LVM Microservice with PredictionGuard
        • Table of Contents
        • Start Microservice
        • Consume LVM Service
      • LVM Microservice with Video-LLaMA
        • Table of Contents
        • Start Microservice
        • Consume LVM Service
      • LVM Microservice with vLLM on Gaudi
        • Table of Contents
        • Prerequisites
        • Start Microservice
        • Consume LVM Service
      • LVM Microservice with vLLM on Intel XPU
        • Table of Contents
        • Prerequisites
        • Start Microservice
        • Consume LVM Service
    • Prompt_registry Microservice
      • 🧾 Prompt Registry Microservice
        • 🛠️ Features
        • ⚙️ Deployment Options
      • 🧾 Prompt Registry Microservice with MongoDB
        • Setup Environment Variables
        • 🚀 Start Microservice with Docker (Option 1)
        • 🚀 Start Microservice with Docker Compose (Option 2)
        • 🤖 MCP (Model Context Protocol) Usage
      • 🧾 Prompt Registry Microservice with ArangoDB
        • Setup Environment Variables
        • 🚀 Start Microservice with Docker (Option 1)
        • 🚀 Start Microservice with Docker Compose (Option 2)
        • 🤖 MCP (Model Context Protocol) Usage
      • 🧾 Prompt Registry Microservice with Redis
        • Setup Environment Variables
        • 🚀 Start Microservice with Docker (Option 1)
        • 🚀 Start Microservice with Docker Compose (Option 2)
        • 🤖 MCP (Model Context Protocol) Usage
      • Deploy prompt microservice on Kubernetes cluster
        • Deploy on Kubernetes
    • Prompt_template Microservice
      • Prompt Template microservice
        • Getting started
    • Rerankings Microservice
      • Deploy reranking microservice on Kubernetes cluster
        • Deploy on Kubernetes
      • Reranking Microservice
        • 🛠️ Features
        • ⚙️ Implementation
      • 🌟 Reranking Microservice with OVMS
        • 📦 1. Prepare the model in the model repository
        • 📦 2. Start Microservice with Docker
        • 📦 3. Start Microservice with docker compose
        • 📦 4. Consume Reranking Service
        • ✨ Tips for Better Understanding:
      • 🌟 Reranking Microservice with TEI
        • 📦 1. Start Microservice with Docker
        • 📦 2. Start Microservice with docker compose
        • 📦 3. Consume Reranking Service
        • ✨ Tips for Better Understanding:
      • 🌟 Reranking Microservice with VideoQnA
        • 📦 1. Start Microservice with Docker
        • 📦 2. Start Microservice with docker compose
        • 📦 3. Consume Reranking Service
        • ✨ Tips for Better Understanding:
    • Retrievers Microservice
      • Retriever Microservice
        • Retriever Microservice with Redis
        • Retriever Microservice with Milvus
        • Retriever Microservice with Qdrant
        • Retriever Microservice with PGVector
        • Retriever Microservice with VDMS
        • Retriever Microservice with ElasticSearch
        • Retriever Microservice with OpenSearch
        • Retriever Microservice with neo4j
        • Retriever Microservice with Pathway
        • Retriever Microservice with MariaDB Vector
        • Retriever Microservice with ArangoDB
        • Retriever Microservice with openGauss
      • Deploy retriever microservice on Kubernetes cluster
        • Deploy on Kubernetes with redis vector DB
        • Deploy on Kubernetes with milvus vector DB
      • Retriever Microservice with ArangoDB
        • 🚀Start Microservice with Docker
        • 🚀3. Consume Retriever Service
      • Retriever Microservice
        • 🚀1. Start Microservice with Python (Option 1)
        • 🚀2. Start Microservice with Docker (Option 2)
        • 🚀3. Consume Retriever Service
      • Retriever Microservice
        • 🚀1. Start Microservice with Docker
        • 🚀2. Consume Retriever Service
      • Retriever Microservice with Milvus
        • 🚀Start Microservice with Python
        • 🚀Start Microservice with Docker
        • 🚀3. Consume Retriever Service
      • Retriever Microservice with Neo4J
        • 🚀Start Microservice with Docker
        • Invoke Microservice
      • Retriever Microservice
        • 🚀1. Start Microservice with Python (Option 1)
        • 🚀2. Start Microservice with Docker (Option 2)
        • 🚀3. Consume Retriever Service
      • Retriever Microservice
        • 🚀1. Start Microservice with Python (Option 1)
        • 🚀2. Start Microservice with Docker (Option 2)
        • 🚀3. Consume Retriever Service
      • Retriever Microservice with Pathway
        • 🚀Start Microservices
      • Retriever Microservice
        • 🚀1. Start Microservice with Python (Option 1)
        • 🚀2. Start Microservice with Docker (Option 2)
        • 🚀3. Consume Retriever Service
      • Retriever Microservice with Qdrant
        • 1. 🚀Start Microservice with Python (Option 1)
        • 2. 🚀Start Microservice with Docker (Option 2)
        • 🚀3. Consume Retriever Service
      • Retriever Microservice
        • 🚀1. Start Microservice with Python (Option 1)
        • 🚀2. Start Microservice with Docker (Option 2)
        • 🚀3. Consume Retriever Service
      • Retriever Microservice
        • Visual Data Management System (VDMS)
        • 🚀1. Start Microservice with Python (Option 1)
        • 🚀2. Start Microservice with Docker (Option 2)
        • 🚀3. Consume Retriever Service
    • Router Microservice
      • Router Microservice
        • Build
        • RouteLLM compatibility patch
        • API Usage
        • Configuration Reference
        • Troubleshooting
        • Testing
    • Struct2graph Microservice
      • Struct2Graph Microservice
        • Features
        • Implementation
        • 🚀1. Start Microservice with docker run
        • 🚀2. Start Microservice with docker compose
        • 3. Validate the service using API endpoint
    • Text2cypher Microservice
      • Deploy text2cypher microservice using docker-compose
        • Deploy on Intel Gaudi
      • ⚠️ Deprecation Notice: text2cypher
      • 🛢 Text-to-Cypher Microservice
        • 🛠️ Features
        • ⚙️ Implementation
    • Text2graph Microservice
      • Text to graph triplet extractor
        • Decoder Models
        • Encoder-decoder models
      • Features
        • Implementation
      • 🚀1. Start Microservice with Docker
        • Install Requirements
        • Environment variables : Configure LLM Parameters based on the model selected.
      • Validation and testing
        • Text to triplets
        • Check if services are up
    • Text2image Microservice
      • Deploy text2image on kubernetes cluster
        • Deploy on Xeon
        • Deploy on Gaudi
      • Text-to-Image Microservice
      • 🚀1. Start Microservice with Python (Option 1)
        • 1.1 Install Requirements
        • 1.2 Start Text-to-Image Microservice
      • 🚀2. Start Microservice with Docker (Option 2)
        • 2.1 Build Images
        • 2.2 Start Text-to-Image Service
      • 3 Test Text-to-Image Service
    • Text2kg Microservice
      • Text to knowledge graph (text2kg) microservice
        • Decoder-Only Models
        • Features
        • 🚀 1. Start individual microservices using docker cli (Option 1)
        • 🚀 2. Start text2kg and dependent microservices with docker-compose (Option 2)
        • 3. Check the service using API endpoint
    • Text2query Microservice
      • 🛢 Text-to-Query Microservice
        • 🛠️ Features
        • ⚙️ Supported Implementations
      • 🛢 Text-to-Cypher Microservice
        • Setup Environment Variables.
        • 🚀 Start Text2Cypher Microservice with Python（Option 1）
        • 🚀 Start Microservice with Docker (Option 2)
        • ✅ Invoke the microservice.
      • Text-to-SQL Microservice
        • 🚀 Start Microservice with Python（Option 1）
        • 🚀 Start Microservice with Docker (Option 2)
        • ✅ Invoke the microservice.
    • Text2sql Microservice
      • ⚠️ Deprecation Notice: text2sql
      • 🛢 Text-to-SQL Microservice
        • 🛠️ Features
        • ⚙️ Implementation
    • Third_parties Microservice
      • Start ArangoDB Server
        • 1. Download ArangoDB image
        • 2. Configure the password
        • 3. Run ArangoDB service
      • Deploy mm-embedding on kubernetes cluster
        • Deploy on Xeon
        • Deploy on Gaudi
      • Multimodal Embeddings Microservice with BridgeTower
        • 🚀1. Start MMEI on Gaudi2 HPU
        • 🚀2. Start MMEI on Xeon CPU
        • Running in the air gapped environment
        • 🚀3. Access the service
      • Multimodal Embeddings Microservice with CLIP
        • 🚀1. Start Microservice with Docker
        • 🚀2. Consume Embedding Service
      • Start Elasticsearch server
        • 1. Download Elasticsearch image
        • 2. Run Elasticsearch service
      • Deploy gpt-sovits on kubernetes cluster
        • Deploy on Xeon
      • GPT-SoVITS Microservice
        • Build the Image
        • Start the Service
        • Test
      • IPEX Serving microservice
        • 🚀1. Build the Docker Image
        • 🚀2. Start the microservice
        • 🚀3. Access the service
      • LVM Microservice
        • 🚀 Start Microservice with Docker
      • LVM Microservice
        • 🚀1. Start Microservice with Python (Option 1)
        • 🚀2. Start Microservice with Docker (Option 2)
      • Start MariaDB Server
        • 1. Configure the server
        • 2. Run MariaDB Server
      • Start Milvus server
        • 1. Configuration
        • 2. Run Milvus service
      • Deploy MongoDB on kubernetes cluster
        • Deploy on Xeon
      • Start Neo4J Server
        • 1. Download Neo4J image
        • 2. Configure the username, password and dbname
        • 3. Run Neo4J service
      • Deploy nginx on kubernetes cluster
        • Deploy on Xeon
      • Introduction
        • Get Started
      • Start openGauss server
        • 1. Download openGauss image
        • 2. Configure the username, password and dbname
        • 3. Run openGauss service
      • Start Opensearch server
        • Prerequisites
        • Instructions
        • Troubleshooting
      • Deploy OVMS on kubernetes cluster
        • Deploy on Xeon
      • Start the Pathway Vector DB Server
        • Configuration
        • Building and running
        • Health check the vector store
      • Start PGVector server
        • 1. Download Pgvector image
        • 2. Configure the username, password and dbname
        • 3. Run Pgvector service
      • LVM Prediction Guard Microservice
        • 🚀1. Start Microservice with Python
        • 🚀2. Start Microservice with Docker (Option 2)
        • 🚀3. Consume LVM Service
      • Start PGVector server
        • 1. Download Pgvector image
        • 2. Configure the username, password and dbname
        • 3. Run Pgvector service
      • Deploy RedisDB on kubernetes cluster
        • Deploy on Xeon
      • Start Redis server
        • 1. Download Redis image
        • 2. Run Redis service
      • SGLang Serving microservice
        • 🚀1. Build the Docker Image
        • 🚀2. Start the microservice
        • 🚀3. Access the service
      • Deploy speecht5 on kubernetes cluster
        • Deploy on Xeon
        • Deploy on Gaudi
      • Deploy TEI on kubernetes cluster
        • Deploy on Xeon
        • Deploy on Gaudi
      • TGI LLM Microservice
        • Start TGI with docker compose
      • Deploy TGI on kubernetes cluster
        • Deploy on Xeon
        • Deploy on Gaudi
      • Start VDMS server
        • 1. Download VDMS image
        • 2. Run VDMS service
      • LVM Microservice
        • 🚀1. Start Microservice with Docker
        • ✅ 2. Test
        • ♻️ 3. Clean
      • vLLM Endpoint Service
        • 🚀1. Set up Environment Variables
        • 🚀2. Set up vLLM Service
        • 🚀3. Set up LLM microservice
      • Deploy vllm on kubernetes cluster
        • Deploy on Xeon
        • Deploy on Gaudi
      • Deploy whisper on kubernetes cluster
        • Deploy on Xeon
        • Deploy on Gaudi
    • Tts Microservice
      • Deploy tts microservice on Kubernetes cluster
        • Deploy on Kubernetes
      • TTS Microservice
        • 1.2 Start SpeechT5 Service/Test
        • 1.3 Start TTS Service/Test
        • 🚀2. Start Microservice with Docker (Option 2)
        • 🚀3. Start Microservice with Docker Compose (Option 3)
    • Web_retrievers Microservice
      • Deploy web-retriever microservice on Kubernetes cluster
        • Deploy on Kubernetes
      • Web Retriever Microservice
        • 🚀1. Start Microservice with Docker (Option 1)
        • 🚀2. Start Microservice with Docker Compose (Option 2)
        • 🚀3. Consume Web Retriever Service
  • Deploying GenAI
    • GenAIInfra
      • Overview
      • Prerequisite
        • Setup Kubernetes cluster
        • (Optional) To run GenAIInfra on Intel Gaudi product
      • Usages
        • Use GenAI Microservices Connector (GMC) to deploy and adjust GenAIExamples
        • Use helm charts to deploy
        • Use terraform to deploy on cloud service providers
      • Additional Content
    • Development
      • Prerequisites
      • Creating new helm chart for OPEA services
      • Testing
      • pre-commit testing
    • Legal Information
      • License
      • Citation
    • Release Branches
      • 1. Create release candidate branch
      • 2. Create images with release tag
      • 3. Test helm charts
      • 4. Test GMC
      • 5. Publish images
    • Installation Guides
      • GenAI-microservices-connector(GMC) Installation
        • GenAI-microservices-connector(GMC)
        • Install GMC
        • Use GMC to compose a chatQnA Pipeline
      • Kubernetes Installation Options
      • Kubernetes Installation using AWS EKS Cluster
        • Prerequisites
        • Create AWS EKS Cluster in AWS Console
        • Uploading images to an AWS Private Registry
      • Kubernetes installation demo using kubeadm
        • Node configuration
        • Step 0. Clean up the environment
        • Step 1. Install relevant components
        • Step 2. Create the k8s cluster
        • Step 3 (optional) Reset Kubernetes cluster
        • NOTES
      • Kubernetes installation using Kubespray
        • Node preparation
        • Prerequisites
        • Step 1. Set up Kubespray and Ansible
        • Step 2. Build your own inventory
        • Step 3. Define Kubernetes configuration
        • Step 4. Deploy Kubernetes
        • Step 5. Create kubectl configuration
        • Quick reference
    • CI/CD ENV Setup
      • Setup Test Environment for CI/CD
        • Install Habana Driver (Gaudi Only)
        • Install Docker
        • Install Conda
        • Install K8S
        • Setup Image Registry for K8S Test
        • Setup GHA ENV for CI/CD
        • Setup Action Runner Controller (ARC)
    • Cloud Service Provider
      • OPEA applications AWS EKS deployment guide
        • Prerequisites
        • Setup
        • EKS cluster
        • Persistent Volume Claim
        • OPEA Applications
      • OPEA applications Azure AKS deployment guide
        • Prerequisites
        • Setup
        • AKS cluster
        • Cosmos DB
        • Persistent Volume Claim
        • OPEA Applications
      • OPEA applications GCP GKE deployment guide
        • Prerequisites
        • Setup
        • Update your opea-chatqna.tfvars file
        • GKE cluster
        • Persistent Volume Claim
        • OPEA Applications
    • Authentication and Authorization
      • Authentication and authorization
        • Istio based implementation for cloud native environments
        • APISIX based implementation for cloud native environments
      • Authentication and Authorization with APISIX and OIDC based Identity provider (Keycloak)
        • Start ChatQnA service
        • Starting and Configuring Keycloak
        • Update values
        • Install APISIX
        • Usage
        • Uninstall
      • Leveraging Istio to compose an OPEA Pipeline with authentication and authorization enabled
        • Prerequisite
        • Perform authentication and authorization via Bearer JWT tokens and curl
        • Perform authentication and authorization via oauth2-proxy and OIDC provider and UI
        • Uninstall Istio
    • Helm Charts
      • Helm charts for deploying GenAI Components and Examples
        • Table of Contents
        • Helm Charts
        • Deploy with Helm charts
        • Helm Charts Options
        • Deploy the Helm Charts on Intel® Xeon® Processors with Intel® Trust Domain Extensions (Intel® TDX)
        • Using HPA (autoscaling)
        • Using Persistent Volume
        • Using Private Docker Hub
        • Generate manifests from Helm Charts
      • CI guidelines for helm charts
        • Table of Contents
        • Infra Setup
        • Add new test case
      • HorizontalPodAutoscaler (HPA) support
        • Table of Contents
        • Introduction
        • Pre-conditions
        • Gotchas
        • Enable HPA
        • Verify
        • Scaling metric considerations
      • Deployment of the Helm Charts on Intel® Xeon® Processors with Intel® Trust Domain Extensions (Intel® TDX)
        • Technical background
        • Prerequisites
        • Getting Started
      • Observability for OPEA Workloads in Kubernetes
        • Table of Contents
        • Introduction
        • Pre-conditions
        • Install
        • Verify
      • agent
        • Deploy
        • Verify
        • Options
      • asr
        • (Option1): Installing the chart separately
        • (Option2): Installing the chart with dependencies automatically
        • Verify
        • Values
      • chathistory-usvc
        • (Option1): Installing the chart separately
        • (Option2): Installing the chart with dependencies automatically
        • Verify
        • Values
      • Dashboards
        • Installing the Chart
        • Values
      • data-prep
        • Installing the chart
        • Verify
        • Values
        • Milvus support
      • embedding-usvc
        • Installing the chart
        • Verify
        • Values
      • gpt-sovits
        • Install the chart
        • Verify
        • Values
      • guardrails-usvc
        • Installing the chart
        • Verify
        • Values