|
| 1 | +# OPEA Release Notes v1.4 |
| 2 | +We are excited to announce the release of OPEA version 1.4, which includes significant contributions from the open-source community. This release addresses over 330 pull requests. |
| 3 | + |
| 4 | +More information about how to get started with OPEA v1.4 can be found on the [Getting Started](https://opea-project.github.io/latest/index.html) page. All project source code is maintained in the [opea-project organization](https://github.com/opea-project). To pull Docker images, please access the [Docker Hub](https://hub.docker.com/u/opea). For instructions on deploying Helm Charts, please refer to the [guide](https://github.com/opea-project/GenAIInfra/tree/v1.4/helm-charts#readme). |
| 5 | + |
| 6 | +## Table of Contents |
| 7 | +- [OPEA Release Notes v1.4](#opea-release-notes-v14) |
| 8 | + - [Table of Contents](#table-of-contents) |
| 9 | + - [What's New in OPEA v1.4](#whats-new-in-opea-v14) |
| 10 | + - [Advanced Agent Capabilities](#advanced-agent-capabilities) |
| 11 | + - [Components as MCP Servers](#components-as-mcp-servers) |
| 12 | + - [KubeAI Operator for OPEA](#kubeai-operator-for-opea) |
| 13 | + - [New GenAI Capabilities](#new-genai-capabilities) |
| 14 | + - [Better User Experience](#better-user-experience) |
| 15 | + - [Newly Supported Models](#newly-supported-models) |
| 16 | + - [Newly Supported Hardware](#newly-supported-hardware) |
| 17 | + - [Newly Supported OS](#newly-supported-os) |
| 18 | + - [Updated Dependencies](#updated-dependencies) |
| 19 | + - [Changes to Default Behavior](#changes-to-default-behavior) |
| 20 | + - [Validated Hardware](#validated-hardware) |
| 21 | + - [Validated Software](#validated-software) |
| 22 | + - [Known Issues](#known-issues) |
| 23 | + - [Full Changelogs](#full-changelogs) |
| 24 | + - [Contributors](#contributors) |
| 25 | + - [Contributing Organizations](#contributing-organizations) |
| 26 | + - [Individual Contributors](#individual-contributors) |
| 27 | + |
| 28 | +## What's New in OPEA v1.4 |
| 29 | + |
| 30 | +This release includes new features, optimizations, and user-focused updates. |
| 31 | + |
| 32 | +### Advanced Agent Capabilities |
| 33 | + |
| 34 | +- <b>MCP (Model Context Protocol) Support</b>: The OPEA agent now supports the MCP, allowing for standardized and more efficient integration with external data and services. ([GenAIComps#1678](https://github.com/opea-project/GenAIComps/pull/1678), [GenAIComps#1810](https://github.com/opea-project/GenAIComps/pull/1810)) |
| 35 | + |
| 36 | +- <b>Deep Research Agent</b>: The [example](https://github.com/opea-project/GenAIExamples/tree/v1.4/DeepResearchAgent) is designed to handle complex, multi-step research. It leverages [langchain-ai/open_deep_research](https://github.com/langchain-ai/open_deep_research) and supports Intel Gaudi accelerators. ([GenAIExamples#2117](https://github.com/opea-project/GenAIExamples/pull/2117)) |
| 37 | + |
| 38 | +### Components as MCP Servers |
| 39 | +OPEA components can now serve as Model Context Protocol (MCP) servers, allowing external MCP-compatible frameworks and applications to integrate with OPEA seamlessly. ([GenAIComps#1652](https://github.com/opea-project/GenAIComps/issues/1652)) |
| 40 | + |
| 41 | +### KubeAI Operator for OPEA |
| 42 | +The KubeAI Operator now features an improved autoscaler, monitoring support, optimized resource placement via [NRI plugins](https://github.com/containers/nri-plugins), and expanded support for new models on Gaudi. ([GenAIInfra#967](https://github.com/opea-project/GenAIInfra/pull/967), [GenAIInfra#1052](https://github.com/opea-project/GenAIInfra/pull/1052), [GenAIInfra#1054](https://github.com/opea-project/GenAIInfra/pull/1054), [GenAIInfra#1089](https://github.com/opea-project/GenAIInfra/pull/1089), [GenAIInfra#1113](https://github.com/opea-project/GenAIInfra/pull/1113), [GenAIInfra#1144](https://github.com/opea-project/GenAIInfra/pull/1144), [GenAIInfra#1150](https://github.com/opea-project/GenAIInfra/pull/1150)) |
| 43 | + |
| 44 | +### New GenAI Capabilities |
| 45 | +- <b>Fine-Tuning of Reasoning Models</b>: This feature is compatible with the dataset format used in [FreedomIntelligence/medical-o1-reasoning-SFT](https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT), enabling you to customize models with your own data. ([GenAIComps#1839](https://github.com/opea-project/GenAIComps/pull/1839)) |
| 46 | +- <b>HybridRAG</b>: Combined GraphRAG (knowledge graph-based retrieval) and VectorRAG (vector database retrieval) for enhanced accuracy and contextual relevance. ([GenAIExamples#1968](https://github.com/opea-project/GenAIExamples/pull/1968)) |
| 47 | +- <b>LLM Router</b>: LLM Router decides which downstream LLM serving endpoint is best suited for an incoming prompt. ([GenAIComps#1716](https://github.com/opea-project/GenAIComps/pull/1716)) |
| 48 | +- <b>OPEA Store</b>: Redis and MongoDB have been integrated into OPEA Store. ([GenAIComps#1816](https://github.com/opea-project/GenAIComps/pull/1816), [GenAIComps#1818](https://github.com/opea-project/GenAIComps/pull/1818)) |
| 49 | +- <b>Guardrails</b>: Added Input/Output Guardrails to enforce content safety and prevent the creation of inappropriate outputs. ([GenAIComps#1798](https://github.com/opea-project/GenAIComps/pull/1798)) |
| 50 | +- <b>Language Detection</b>: The microservice is used to ensure the pipeline's response matches the query's language. ([GenAIComps#1774](https://github.com/opea-project/GenAIComps/pull/1774)) |
| 51 | +- <b>Prompt Template</b>: The microservice can dynamically generate system and user prompts based on structured inputs and document context. ([GenAIComps#1826](https://github.com/opea-project/GenAIComps/pull/1826)) |
| 52 | +- <b>Air-gapped Environment Support</b>: Some OPEA microservices can now be deployed in an air-gapped Docker environment. ([GenAIComps#1480](https://github.com/opea-project/GenAIComps/issues/1480)) |
| 53 | +- <b>Remote Inference Endpoints Support</b>: Added support for remote inference endpoints for OPEA examples. ([GenAIExamples#1973](https://github.com/opea-project/GenAIExamples/issues/1973)) |
| 54 | + |
| 55 | +### Better User Experience |
| 56 | +- <b>One-click Deployment</b>: You can now deploy 8 OPEA examples with one click. ChatQnA can deploy in an air-gapped Docker environment. ([GenAIExamples#1727](https://github.com/opea-project/GenAIExamples/issues/1727)) |
| 57 | +- <b>GenAIStudio</b>: Added support for drag-and-drop creation of documentation summarization and code generation applications. ([GenAIStudio#61](https://github.com/opea-project/GenAIStudio/pull/61)) |
| 58 | +- <b>Documentation Refinement</b>: Refined READMEs for key examples and components to help readers easily locate documentation tailored to deployment, customization, and hardware. ([GenAIExamples#1673](https://github.com/opea-project/GenAIExamples/issues/1673), [GenAIComps#1398](https://github.com/opea-project/GenAIComps/issues/1398)) |
| 59 | + |
| 60 | +### Newly Supported Models |
| 61 | +OPEA introduces support for the following models in this release. |
| 62 | + |
| 63 | +| Model | TGI-Gaudi | vLLM-CPU | vLLM-Gaudi | vLLM-ROCm | OVMS | Optimum-Habana | PredictionGuard | SGLANG-CPU | |
| 64 | +| --------------------------------------------- | --------- | -------- | ---------- | --------- | -------- | -------------- | --------------- | ------------- | |
| 65 | +| meta-llama/Llama-4-Scout-17B-16E-Instruct | - | - | - | - | - | - | - | ✓ | |
| 66 | +| meta-llama/Llama-4-Maverick-17B-128E-Instruct | - | - | - | - | - | - | - | ✓ | |
| 67 | + |
| 68 | +(✓: supported; -: not validated; x: unsupported) |
| 69 | + |
| 70 | + |
| 71 | +### Newly Supported Hardware |
| 72 | +- Support for AMD® EPYC™ has been added for 11 OPEA examples. ([GenAIExamples#2083](https://github.com/opea-project/GenAIExamples/pull/2083)) |
| 73 | + |
| 74 | +### Newly Supported OS |
| 75 | +- Support for openEuler has been added. ([GenAIExamples#2088](https://github.com/opea-project/GenAIExamples/pull/2088), [GenAIComps#1813](https://github.com/opea-project/GenAIComps/pull/1813)) |
| 76 | + |
| 77 | +## Updated Dependencies |
| 78 | + |
| 79 | +| Dependency | Hardware | Scope | Version | Version in OPEA v1.3 | Comments | |
| 80 | +|--|--|--|--|--|--| |
| 81 | +|huggingface/text-embeddings-inference|all|all supported examples|cpu-1.7|cpu-1.6|| |
| 82 | +|vllm|Xeon|all supported examples except EdgeCraftRAG|v0.10.0|v0.8.3|| |
| 83 | + |
| 84 | +## Changes to Default Behavior |
| 85 | +- `CodeTrans`: The default model changed from `mistralai/Mistral-7B-Instruct-v0.3` to `Qwen/Qwen2.5-Coder-7B-Instruct` on Xeon and Gaudi. |
| 86 | + |
| 87 | + |
| 88 | +## Validated Hardware |
| 89 | +- Intel® Gaudi® AI Accelerators (2nd) |
| 90 | +- Intel® Xeon® Scalable processor (3rd) |
| 91 | +- Intel® Arc™ Graphics GPU (A770) |
| 92 | +- AMD® EPYC™ processors (4th, 5th) |
| 93 | + |
| 94 | +## Validated Software |
| 95 | +- Docker version 28.3.3 |
| 96 | +- Docker Compose version v2.39.1 |
| 97 | +- Intel® Gaudi® software and drivers [v1.21](https://docs.habana.ai/en/v1.21.3/Installation_Guide/) |
| 98 | +- Kubernetes v1.32.7 |
| 99 | +- TEI v1.7 |
| 100 | +- TGI v2.4.0 (Xeon, EPYC), v2.3.1 (Gaudi), v2.4.1 (ROCm) |
| 101 | +- Torch v2.5.1 |
| 102 | +- Ubuntu 22.04 |
| 103 | +- vLLM v0.10.0 (Xeon, EPYC), v0.6.6.post1+Gaudi-1.20.0 (Gaudi) |
| 104 | + |
| 105 | +## Known Issues |
| 106 | +- [AvatarChatbot](https://github.com/opea-project/GenAIExamples/tree/v1.4/AvatarChatbot) cannot run in a K8s environment due to a functional gap in the wav2clip service. ([GenAIExamples#1506](https://github.com/opea-project/GenAIExamples/pull/1506)) |
| 107 | + |
| 108 | +## Full Changelogs |
| 109 | +- GenAIExamples: [v1.3...v1.4](https://github.com/opea-project/GenAIExamples/compare/v1.3...v1.4) |
| 110 | +- GenAIComps: [v1.3...v1.4](https://github.com/opea-project/GenAIComps/compare/v1.3...v1.4) |
| 111 | +- GenAIInfra: [v1.3...v1.4](https://github.com/opea-project/GenAIInfra/compare/v1.3...v1.4) |
| 112 | +- GenAIEval: [v1.3...v1.4](https://github.com/opea-project/GenAIEval/compare/v1.3...v1.4) |
| 113 | +- GenAIStudio: [v1.3...v1.4](https://github.com/opea-project/GenAIStudio/compare/v1.3...v1.4) |
| 114 | +- docs: [v1.3...v1.4](https://github.com/opea-project/docs/compare/v1.3...v1.4) |
| 115 | + |
| 116 | +## Contributors |
| 117 | +This release would not have been possible without the contributions of the following organizations and individuals. |
| 118 | + |
| 119 | +### Contributing Organizations |
| 120 | +- `AMD`: AMD EPYC support. |
| 121 | +- `Bud`: Components as MCP Servers. |
| 122 | +- `Intel`: Development and improvements to GenAI examples, components, infrastructure, evaluation, and studio. |
| 123 | +- `MariaDB`: Added ChatQnA docker-compose example on Intel Xeon using MariaDB Vector. |
| 124 | +- `openEuler`: openEuler OS support. |
| 125 | + |
| 126 | +### Individual Contributors |
| 127 | +For a comprehensive list of individual contributors, please refer to the [Full Changelogs](#full-changelogs) section. |
0 commit comments