Skip to main content

Deploy a Pipeline

After you create and save a pipeline, you must deploy it to use it for search. Deploying a pipeline triggers indexing of your files making them ready for search. Deploy always uses the latest version of the pipeline, so you can deploy without choosing between drafts and versions.

Deploy a Pipeline from the UI​

  1. In Haystack Enterprise Platform, click Pipelines.
  2. In the In Development section, find the desired pipeline, and click Deploy next to it.
    The pipeline is moved to Deployed and the deployment starts.

Deploy a Pipeline with the REST API​

Here's the code you can use. For more information about this endpoint, see Deploy Pipeline API.

You need to Generate an API Key first.

Copy this code replacing workspace name, pipeline name, and API key:

curl --request POST \
     --url https://api.cloud.deepset.ai/api/v1/workspaces/<workspace_name>/pipelines/<pipeline_name>/deploy \
     --header 'Accept: application/json' \
     --header 'Authorization: Bearer <your_API_key>'

What To Do Next​

It may happen that the deployment fails, and the pipeline status is failed to deploy. This status means the pipeline wasn't deployed. If you encounter this error, you must take some troubleshooting action.

To view pipeline information, such as statistics or feedback, click the pipeline name. It opens the Pipeline Details page, which contains all the information you may need.

Deployed pipelines that haven't been used for a while become idle to save resources. The default idle timeout depends on the pipeline service level. By default, production pipelines go on standby after 24 hours of not being used and development pipelines after 20 minutes. You can customize the idle timeout on the Pipeline Details page, under Settings. An idle pipeline gets automatically activated if you run a search with it or you can trigger the activation manually on the Pipelines page. For more information, see Pipelines.