Generative AI connectors
The OpenAI, Amazon Bedrock, Google Gemini, and AI Connector types are being replaced by Elasticsearch inference endpoints and will be removed entirely in Elastic Stack 10.0 or in January 2028, whichever comes first. To configure access to an LLM provider, create an inference endpoint with the chat_completion task type. For steps that use your own provider account and API key, refer to External inference. To use models that Elastic hosts instead, refer to Elastic Managed LLMs.
Availability of these connector types depends on your deployment and version:
-
You can no longer create new connectors of these types by selecting Create connector in Kibana. Existing connectors and their rule actions continue to work, but the Connectors page hides them by default. To show them, open Display options and set Deprecated to Show. -
These connector types are still available, but deprecated.
These connectors connect Kibana to third-party large language model (LLM) services and to Elastic Managed LLMs.
-
AI Connector: Connect to third-party LLM services including Amazon Bedrock, Azure, Google Gemini, OpenAI, and Elastic Inference Service. -
Amazon Bedrock: Send a request to Amazon Bedrock. - Elastic Managed LLMs: Send a request to Elastic Managed LLMs.
-
Google Gemini: Send a request to Google Gemini. -
OpenAI: Send a request to OpenAI.
External MCP Server
- MCP: Connect to MCP servers and call their tools.
Connecting to LLM providers through a proxy is in technical preview. If you use a proxy, it should support streaming and be SSE-compatible. Elastic only parses streamed responses.
To check if problems are caused by using a proxy, you can test your LLM service without using a proxy.