Skip to content

Commit

Permalink
Add Helm Charts Support in highlights of v1.1 release notes
Browse files Browse the repository at this point in the history
  • Loading branch information
joshuayao committed Nov 20, 2024
1 parent c39a066 commit 963b5f6
Showing 1 changed file with 8 additions and 5 deletions.
13 changes: 8 additions & 5 deletions release_notes/v1.1.md
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
# OPEA Release Notes v1.1
We are pleased to announce the release of OPEA version 1.1, which includes significant contributions from the open-source community. This release addresses over 450 pull requests.
We are pleased to announce the release of OPEA version 1.1, which includes significant contributions from the open-source community. This release addresses over 460 pull requests.

More information about how to get started with OPEA v1.1 can be found at [Getting Started](https://opea-project.github.io/latest/index.html) page. All project source code is maintained in the [repository](https://github.com/opea-project). To pull Docker images, please access the [hub](https://hub.docker.com/u/opea).

## What's New in OPEA v1.1
This release introduces more scenarios with general availability, including the [Image-to-Video](https://github.com/opea-project/GenAIComps/pull/465), [Test-to-Image](https://github.com/opea-project/GenAIComps/pull/729), [Text-to-SQL](https://github.com/opea-project/GenAIExamples/tree/main/DBQnA) and [Avatar Animation](https://github.com/opea-project/GenAIComps/pull/775) capabilities; introduces [Prediction Guard](https://github.com/opea-project/GenAIComps/pull/677) to enhance AI security by Factuality Check, PII Detection, Prompt Injection Detection and Toxicity Detection; introduces [Generative AI Studio](https://github.com/opea-project/GenAIStudio) that streamlines the creation of enterprise Generative AI applications, offering an alternative to manual processes; expands the hardware support portfolio, like [Intel® Arc™ GPUs](https://github.com/opea-project/GenAIComps/pull/641) and [AMD® GPUs](https://github.com/opea-project/GenAIExamples/issues/1153); introduces enhanced monitoring system, providing real-time insights into performance and system resource utilization for [CPU and Intel® Gaudi® AI Accelerator](https://github.com/opea-project/GenAIEval/issues/195), as well as [Horizontal Pod Autoscaler(HPA)](https://github.com/opea-project/GenAIInfra/pull/531); integrates benchmark tools for long-context language models (LCLMs), like [LongBench](https://github.com/opea-project/GenAIEval/pull/179) and [HELMET](https://github.com/opea-project/GenAIEval/pull/182).
This release introduces more scenarios with general availability, including the [Image-to-Video](https://github.com/opea-project/GenAIComps/pull/465), [Text-to-Image](https://github.com/opea-project/GenAIComps/pull/729), [Text-to-SQL](https://github.com/opea-project/GenAIExamples/tree/main/DBQnA) and [Avatar Animation](https://github.com/opea-project/GenAIComps/pull/775) capabilities; introduces [Prediction Guard](https://github.com/opea-project/GenAIComps/pull/677) to enhance AI security by Factuality Check, PII Detection, Prompt Injection Detection and Toxicity Detection; introduces [Generative AI Studio](https://github.com/opea-project/GenAIStudio) that streamlines the creation of enterprise Generative AI applications, offering an alternative to manual processes; expands the hardware support portfolio, like [Intel® Arc™ GPUs](https://github.com/opea-project/GenAIComps/pull/641) and [AMD® GPUs](https://github.com/opea-project/GenAIExamples/issues/1153); introduces enhanced monitoring system, providing real-time insights into runtime status and system resource utilization for [CPU and Intel® Gaudi® AI Accelerator](https://github.com/opea-project/GenAIEval/issues/195), as well as [Horizontal Pod Autoscaler(HPA)](https://github.com/opea-project/GenAIInfra/pull/531); introduces Helm Charts suppport for 7 examples and microservices; integrates benchmark tools for long-context language models (LCLMs), like [LongBench](https://github.com/opea-project/GenAIEval/pull/179) and [HELMET](https://github.com/opea-project/GenAIEval/pull/182).

### Highlights
#### New GenAI Examples
Expand Down Expand Up @@ -41,8 +41,11 @@ This release introduces more scenarios with general availability, including the
#### Enhanced Observability
Observability offers real-time insights into component performance and system resource utilization. We enhanced this capability by monitoring [key system metrics](https://github.com/opea-project/GenAIInfra/pull/541), including [CPU](https://github.com/opea-project/GenAIInfra/pull/541), host memory, storage, network, and accelerators (such as [Intel Gaudi](https://github.com/opea-project/GenAIInfra/pull/541)), as well as tracking [OPEA application scaling](https://github.com/opea-project/GenAIInfra/pull/541).

#### Helm Charts Support
OPEA examples and microservices support Helm Charts as the packaging format on K8S. The newly supported examples include [AgentQnA](https://github.com/opea-project/GenAIInfra/commit/66de41c), [AudioQnA](https://github.com/opea-project/GenAIInfra/commit/9efacee), [FaqGen](https://github.com/opea-project/GenAIInfra/commit/f847e05), [VisualQnA](https://github.com/opea-project/GenAIInfra/commit/b077d44) etc. The newly supported microservices include [chathistory, mongodb, prompt](https://github.com/opea-project/GenAIInfra/commit/881e2b5), and [Milvus for data-prep and retriever](https://github.com/opea-project/GenAIInfra/commit/d289b4e).

#### Long-context Benchmark Support
We added the following two benchmark kit to response to the community's requirements of long-context language models.
We added the following two benchmark kits to response to the community's requirements of long-context language models.

- HELMET: a comprehensive benchmark for long-context language models covering seven diverse categories of tasks. The datasets are application-centric and are designed to evaluate models at different lengths and levels of complexity.
- [LongBench](https://github.com/THUDM/LongBench): a benchmark tool for bilingual, multitask, and comprehensive assessment of long context understanding capabilities of large language models.
Expand Down Expand Up @@ -304,9 +307,9 @@ We added the following two benchmark kit to response to the community's requirem
- Add hyperlinks and paths validation. [d8cd3a1](https://github.com/opea-project/GenAIInfra/commit/d8cd3a1)
</details>

### Full Changelog
### Full Changelogs
- GenAIExamples: [v1.0...v1.1](https://github.com/opea-project/GenAIExamples/compare/v1.0...v1.1)
- GenAIComps: [v1.0...v1.1](https://github.com/opea-project/GenAIComps/compare/v1.0...v1.1)
- GenAIInfra: [v1.0...v1.1](https://github.com/opea-project/GenAIInfra/compare/v1.0...v1.1)
- GenAIEval: [v1.0...v1.1](https://github.com/opea-project/GenAIEval/compare/v1.0...v1.1)
- GenAIStudio: [...v1.1](https://github.com/opea-project/GenAIStudio/compare/v1.1...v1.1)
- GenAIStudio: [...v1.1](https://github.com/opea-project/GenAIStudio/compare/3df407115e079622428c17978719ce782a25927a...v1.1)

0 comments on commit 963b5f6

Please sign in to comment.