Elastic launches low-code RAG development interface

Search AI company Elastic has launched a new low-code interface designed to help developers quickly build retrieval augmented generation (RAG) applications.

Elastic said the interface, Playground, can help developers integrate and build RAG applications within minutes. Developers can A/B test different large language models and refine retrieval mechanisms to ground answers with proprietary data indexed into Elasticsearch.

The platform is augmented by the Elasticsearch Open Inference API, which integrates models from a range of inference providers including Cohere and Azure AI Studio. Playground currently supports chat completion models from OpenAI and the Azure OpenAI Service.

Elastic Global VP and GM for Search Matt Riley said the ability to rapidly iterate on key components of a RAG workflow is essential to ensure accurate and hallucination-free responses from large language models.

“Developers use the Elastic Search AI platform, which includes the Elasticsearch vector database, for comprehensive hybrid search capabilities and to tap into innovation from a growing list of LLM providers,” he said. “Now, the Playground experience brings these capabilities together via an intuitive user interface, removing the complexity from building and iterating on generative AI experiences, ultimately accelerating time to market for our customers.”

Image credit: iStock.com/The best photo for all