elasticsearch/docs/reference/query-languages/esql/_snippets/commands/layout/completion.md

serverless: preview
stack: preview 9.1.0

The COMPLETION command allows you to send prompts and context to a Large Language Model (LLM) directly within your ES|QL queries, to perform text generation tasks.

Syntax

::::{tab-set}

:::{tab-item} 9.2.0+

COMPLETION [column =] prompt WITH { "inference_id" : "my_inference_endpoint" }

:::

:::{tab-item} 9.1.x only

COMPLETION [column =] prompt WITH my_inference_endpoint

:::

::::

Parameters

column : (Optional) The name of the output column containing the LLM's response.

If not specified, the results will be stored in a column named `completion`.
If the specified column already exists, it will be overwritten with the new results.

prompt : The input text or expression used to prompt the LLM.

This can be a string literal or a reference to a column containing text.

my_inference_endpoint : The ID of the inference endpoint to use for the task.

The inference endpoint must be configured with the `completion` task type.

Description

The COMPLETION command provides a general-purpose interface for text generation tasks using a Large Language Model (LLM) in ES|QL.

COMPLETION supports a wide range of text generation tasks. Depending on your prompt and the model you use, you can perform arbitrary text generation tasks including:

• Question answering
• Summarization
• Translation
• Content rewriting
• Creative generation

Requirements

To use this command, you must deploy your LLM model in Elasticsearch as an inference endpoint with the task type completion.

Handling timeouts

COMPLETION commands may time out when processing large datasets or complex prompts. The default timeout is 10 minutes, but you can increase this limit if necessary.

How you increase the timeout depends on your deployment type:

::::{tab-set} :::{tab-item} {{ech}}

• You can adjust {{es}} settings in the Elastic Cloud Console
• You can also adjust the search.default_search_timeout cluster setting using Kibana's Advanced settings :::

:::{tab-item} Self-managed

• You can configure at the cluster level by setting search.default_search_timeout in elasticsearch.yml or updating via Cluster Settings API
• You can also adjust the search:timeout setting using Kibana's Advanced settings
• Alternatively, you can add timeout parameters to individual queries :::

:::{tab-item} {{serverless-full}}

• Requires a manual override from Elastic Support because you cannot modify timeout settings directly ::: ::::

If you don't want to increase the timeout limit, try the following:

• Reduce data volume with LIMIT or more selective filters before the COMPLETION command
• Split complex operations into multiple simpler queries
• Configure your HTTP client's response timeout (Refer to HTTP client configuration)

Examples

Use the default column name (results stored in completion column):

ROW question = "What is Elasticsearch?"
| COMPLETION question WITH { "inference_id" : "my_inference_endpoint" }
| KEEP question, completion

question:keyword	completion:keyword
What is Elasticsearch?	A distributed search and analytics engine

Specify the output column (results stored in answer column):

ROW question = "What is Elasticsearch?"
| COMPLETION answer = question WITH { "inference_id" : "my_inference_endpoint" }
| KEEP question, answer

question:keyword	answer:keyword
What is Elasticsearch?	A distributed search and analytics engine

Summarize the top 10 highest-rated movies using a prompt:

FROM movies
| SORT rating DESC
| LIMIT 10
| EVAL prompt = CONCAT(
   "Summarize this movie using the following information: \n",
   "Title: ", title, "\n",
   "Synopsis: ", synopsis, "\n",
   "Actors: ", MV_CONCAT(actors, ", "), "\n",
  )
| COMPLETION summary = prompt WITH { "inference_id" : "my_inference_endpoint" }
| KEEP title, summary, rating

title:keyword	summary:keyword	rating:double
The Shawshank Redemption	A tale of hope and redemption in prison.	9.3
The Godfather	A mafia family's rise and fall.	9.2
The Dark Knight	Batman battles the Joker in Gotham.	9.0
Pulp Fiction	Interconnected crime stories with dark humor.	8.9
Fight Club	A man starts an underground fight club.	8.8
Inception	A thief steals secrets through dreams.	8.8
The Matrix	A hacker discovers reality is a simulation.	8.7
Parasite	Class conflict between two families.	8.6
Interstellar	A team explores space to save humanity.	8.6
The Prestige	Rival magicians engage in dangerous competition.	8.5