Skip to content

OpenSearch plugin that enables builders to innovate AI apps on OpenSearch

License

Notifications You must be signed in to change notification settings

opensearch-project/flow-framework

This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.

Folders and files

NameName
Last commit message
Last commit date
Nov 30, 2023
Aug 16, 2023
Sep 19, 2023
Dec 4, 2023
Dec 20, 2023
Oct 31, 2023
Aug 16, 2023
Aug 15, 2023
Aug 16, 2023
Nov 21, 2023
Nov 30, 2023
Aug 15, 2023
Aug 15, 2023
Aug 16, 2023
Aug 16, 2023
Sep 7, 2023
Dec 19, 2023
Oct 13, 2023
Oct 10, 2023
Aug 16, 2023
Nov 21, 2023

Repository files navigation

OpenSearch AI Flow Framework

This project is an OpenSearch plugin that enables builders to innovate AI apps on OpenSearch.

The current process of using ML offerings in OpenSearch, such as Semantic Search, requires users to handle complex setup and pre-processing tasks, and send verbose user queries, both of which can be time-consuming and error-prone.

The directional idea is to provide OpenSearch users with use case templates, which provide a compact description (e.g., JSON document). These templates would describe configurations for automated workflows such as Retrieval Augment Generation (RAG), AI connectors and other components that prime OpenSearch as a backend to leverage generative models—once primed, builders can query OpenSearch directly without building middleware logic to stitch together data flows and ML models.

See the RFC on the OpenSearch project for initial design discussions.

Security

See CONTRIBUTING for more information.

License

This project is licensed under the Apache-2.0 License.