View and modify queries

Warning

Playground was deprecated in Elastic Stack 9.4 and removed in 9.6. It is unavailable in Elastic Serverless. Use Agent Builder (generally available since 9.3) instead.

With Agent Builder you can:

Interact with your Elasticsearch data using a chat interface in full-screen and sidebar modes
Use built-in agents, tools, and skills out of the box
Create custom agents, custom tools, and custom skills
Integrate via REST API and MCP
Combine LLM reasoning with Elastic Workflows to automate complex processes

Once you've set up your chat interface, you can start chatting with the model. Playground automatically generates Elasticsearch queries based on your questions, and retrieves the most relevant documents from your Elasticsearch indices. The Playground UI enables you to view and modify these queries.

Select the Query tab to open the visual query editor.
Modify the query by selecting fields to query per index.

Tip

The {{query}} variable represents the user’s question, rewritten as an Elasticsearch query.

The following screenshot shows the query editor in the Playground UI. In this basic example, the books index has two fields: author and name. Selecting a field adds it to the fields array in the query.

Certain fields in your documents might be hidden. Learn more about hidden fields.

Improving relevance

The fields you select in the query editor determine the relevance of the retrieved documents.

Remember that the next step in the workflow is to send the retrieved documents to the LLM to answer the question. Context length is an important factor in ensuring the model has enough information to generate a relevant answer. Refer to Optimize context for more information.

Troubleshooting provides tips on how to diagnose and fix relevance issues.

Note

Playground uses the retriever syntax for Elasticsearch queries. Retrievers make it easier to compose and test different retrieval strategies in your search pipelines. Refer to Retrievers for a high level overview of retrievers.

Hidden fields

The query editor shows fields which make sense for the user to search on, but not all fields in your documents are visible from the editor.

Available field types:

Semantic fields like sparse_vector or dense_vector fields where the embeddings have been created from a inference processor
text fields

Hidden Field Types:

non text fields like keyword fields
fields that are not indexed
semantic fields where the embeddings have not been created from a inference processor
nested fields