OpenSearch Assistant Toolkit

Introduced 2.12

This is an experimental feature and is not recommended for use in a production environment. For updates on the progress of the feature or if you want to leave feedback, see the associated OpenSearch forum thread.

The OpenSearch Assistant Toolkit helps you create AI-powered assistants for OpenSearch Dashboards. The toolkit includes the following elements:

  • Agents and tools: Agents interface with a large language model (LLM) and execute high-level tasks, such as summarization or generating Piped Processing Language (PPL) queries from natural language. The agent’s high-level tasks consist of low-level tasks called tools, which can be reused by multiple agents.
  • Configuration automation: Uses templates to set up infrastructure for artificial intelligence and machine learning (AI/ML) applications. For example, you can automate configuring agents to be used for chat or generating PPL queries from natural language.
  • OpenSearch Assistant for OpenSearch Dashboards: This is the OpenSearch Dashboards UI for the AI-powered assistant. The assistant’s workflow is configured with various agents and tools.

Enabling OpenSearch Assistant

To enable OpenSearch Assistant, perform the following steps:

  • Enable the agent framework and retrieval-augmented generation (RAG) by configuring the following settings:

    1.   plugins.ml_commons.agent_framework_enabled: true
    2.   plugins.ml_commons.rag_pipeline_feature_enabled: true

    copy

  • Enable the assistant by configuring the following settings:

    1.   assistant.chat.enabled: true
    2.   observability.query_assist.enabled: true

    copy

For more information about ways to enable experimental features, see Experimental feature flags.

Next steps