Update Pipeline Settings
Change a pipeline's settings to control its hosting, speed it up with a GPU, or pin its Haystack version.
Open Pipeline Settings
- In Haystack Enterprise Platform, go to Pipelines.
- Find the pipeline you want to configure and click Settings next to its name.

Configure Pipeline Hosting
Use the Pipeline Hosting section to control how your pipeline scales and how long it stays active when idle. These settings apply only to pipelines deployed without a service. When a pipeline is published to a service, the service's hosting settings take over.
For the difference between pipeline and service hosting settings, see Gateway.
For production and business-critical pipelines, we recommend at least 2 replicas always available and a longer idle timeout, like 1 day or more. For test pipelines or pipelines with low traffic, you can keep 1 replica at a minimum and a shorter idle timeout to save resources. For details, see Pipeline Hosting Settings.
Set the Production Service Level
Turn on Production to apply the recommended production hosting values automatically:
- Minimum replicas: 2
- Idle timeout: 30 days
Turn it off to switch to development defaults:
- Minimum replicas: 0
- Idle timeout: 20 minutes
You can also set the values manually at any time, regardless of whether Production is on or off. Adding more replicas increases your costs.
Enable GPU Acceleration
By default, pipelines run on CPU. You can enable GPU acceleration for a pipeline to speed it up. This is especially useful for pipelines that include components that run faster on a GPU, like custom components that use AI models.
When you enable GPU acceleration, the pipeline checks whether a component needs a GPU and assigns one automatically. GPUs are only used when required and are not reserved for the entire pipeline run.
If GPU acceleration is disabled and your pipeline includes components that rely on a GPU, those components run on the CPU instead. This can slow down processing and may cause timeouts, especially for larger or more complex pipelines.
Turn on GPU Enabled to allocate a GPU to your pipeline.
Pin the Haystack Version
Haystack Enterprise Platform uses Haystack Open Source as its underlying framework. You can choose which version of Haystack your pipeline runs on to keep behavior consistent and avoid breaking changes.
Choose a version from the Haystack Version list to pin the version your pipeline runs on. The selected version is saved to the pipeline configuration as a haystack-ai dependency, so your pipeline always uses that version. If you leave it unset, the pipeline runs on the default supported version.
You must pin a Haystack version before you can publish a pipeline version to a service. Pin a version in these settings first. The pin can be the Haystack Version setting or a haystack-ai==<version> entry under dependencies in the pipeline YAML. REST API requests and SDK or CLI pushes need the pin too. For details, see Publish a Pipeline to a Service.
Pin the Custom Components Version
A pipeline that doesn't pin a custom components version runs on whichever version is the latest when its environment starts. Pin a version to keep the pipeline on a version you tested, so uploading a new version never changes it silently. The pin is saved to the pipeline configuration as a dc-custom-component==<version> entry under dependencies, next to the Haystack pin.
Before you start, make sure your organization has at least one custom components version that finished uploading. Without one, and with no pin on the pipeline, the Custom components section is hidden.
To pin a version:
- Pin a Haystack version first. The Custom components section stays disabled until the pipeline pins
haystack-ai, because the pipeline installs a custom components pin only when Haystack is pinned too. - In the Custom components section, choose a version from the list. Only versions that were uploaded and built successfully are listed. Use the upload date and the package description or requirements to tell versions apart.
- Save the pipeline. The platform then warms up the pipeline's environment with all of its pinned dependencies, so the Builder shows the components of the version you chose. To confirm the pin, check that
dc-custom-component==<version>appears underdependenciesin the pipeline YAML.
To remove the pin, clear the selection. The pipeline then runs on the latest version again.
If the pinned version is no longer available, for example because it was removed, it stays visible and is marked as unavailable. Choose another version or clear the selection.
Check for Unpinned Custom Components in Builder
If a pipeline uses a custom component but pins no custom components version, the Issues panel in Builder warns you. The pipeline then runs on whichever version is the latest when its environment starts. Pin a version in Settings to resolve the warning. The warning doesn't block saving or deploying.
Configure History Granularity
History granularity controls how much of the conversation history gets sent to the pipeline on each turn. Use this setting for chat-based pipelines.
Choose one of the following from the Granularity dropdown:
- Query & answer: Sends only the user query and final answer from each previous turn. Use this to keep context lightweight.
- All messages: Sends every message from previous turns, including tool calls and reasoning. Use this when the pipeline needs full context to respond accurately.
Enable Session Storage
Turn on Session storage to give each session an isolated file system. This lets tools like bash store and reuse files across requests within the same session.
When you turn on session storage, the platform automatically treats the pipeline as a chat output type in Playground and the API, even if the pipeline has no generators or prompts configured. To use a different output type instead, set pipeline_output_type explicitly in the pipeline YAML. For details, see Set Pipeline Output Type.
A session keeps one saved snapshot of its files. If two runs on the same session ID overlap and session snapshots are stored in S3, a save fails when another run has replaced the snapshot since this run last restored or saved it. The platform keeps the other run's files instead of overwriting them. The later run fails at its final save, while conflicts during periodic saves are logged and the run continues. After a failed final save, requests for that session ID that reach the same pod can fail with a 503 error until the session recovers. To avoid this, send the next request for a session only after the previous run has finished.
View Linked Services
Check the services where this pipeline is currently published. GPU settings, replicas, and idle timeout for these services are configured per service, not here.
Manage Feedback Tags
Add tags in the Feedback tags section that users can select when leaving feedback on the pipeline's responses. Tags help you group and filter the feedback you receive.
To add a tag, click + New Tag, type the tag name, and press Enter. To remove a tag, click × next to it.
For details on working with feedback, see Collect Feedback.
Related Information
Was this page helpful?