Troubleshooting RAG Playground

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

Dense vectors are not searchable

Embeddings must be generated using the inference processor with an ML node.

Context length error

You’ll need to adjust the size of the context you’re sending to the model. Refer to Optimize model context.

LLM credentials not working

Under LLM settings, use the button to edit your GenAI connector settings.

Poor answer quality

Check the retrieved documents to verify if they are valid. Adjust your Elasticsearch queries to improve the relevance of the documents retrieved. Refer to View and modify queries.

You can update the initial instructions to be more detailed. This is called prompt engineering. Refer to this OpenAI guide for more information.

You might need to click ⟳ Clear chat to clear chat history and start a new conversation. If you mix topics, the model will find it harder to generate relevant responses.