> ## Documentation Index
> Fetch the complete documentation index at: https://docs.neuronsearchlab.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Pipeline Config

> Configure the multi-stage recommendation pipeline — enable or disable stages, set candidate limits, and control page sizes.

The pipeline config page gives you control over the multi-stage recommendation pipeline. Each recommendation request flows through a series of stages, and you can enable, disable, or tune each one independently.

***

## Pipeline stages

Recommendations are produced through these stages, in order:

| Stage                    | Purpose                                                                                                       | Key config                                 |
| ------------------------ | ------------------------------------------------------------------------------------------------------------- | ------------------------------------------ |
| **Candidate generation** | Retrieve initial candidates from the vector index using cosine similarity                                     | `candidate_limit` — max candidates to pull |
| **Feature enrichment**   | Attach metadata and computed features to each candidate                                                       | —                                          |
| **Scoring**              | Run the ML model scoring pass over enriched candidates                                                        | —                                          |
| **Rules**                | Apply business rules such as boost, bury, pin, filter, cap, diversity, dedupe, reorder, and grouping controls | Can be disabled entirely                   |
| **Ranking**              | Final sort by adjusted scores                                                                                 | —                                          |
| **Post-processing**      | Trim to page size and apply any final transforms                                                              | `page_size` — number of items returned     |

***

## Configuring the pipeline

<Steps>
  <Step title="Open Pipeline Config">
    Navigate to **Console > Pipeline Config**.
  </Step>

  <Step title="Review each stage">
    Each stage is shown as a card with its current status (enabled/disabled) and configuration.
  </Step>

  <Step title="Toggle stages">
    Toggle a stage on or off. Disabled stages are skipped entirely at runtime.
  </Step>

  <Step title="Tune stage settings">
    Where available, adjust stage-specific settings like `candidate_limit` or `page_size`.
  </Step>

  <Step title="Save changes">
    Save your changes.
  </Step>
</Steps>

### When to disable stages

* **Disable Rules** to produce pure ML-ranked results. Useful as a control arm in an A/B experiment to measure whether your business rules help or hurt engagement.
* **Disable Feature Enrichment** if you are testing raw embedding similarity without metadata features.

### Tuning candidate limits

The `candidate_limit` in the candidate generation stage controls how many items are pulled from the vector index before scoring. A higher limit gives the scoring model more candidates to choose from but increases latency. Start with 100-200 and increase if you notice the final results lack diversity.

### Tuning page size

The `page_size` in post-processing determines how many items are returned in the API response. This does not affect internal processing — all stages operate on the full candidate set. The trim happens at the end.

***

## Pipeline and experiments

When running an A/B experiment, each variant can reference a different pipeline config. For example:

* **Control**: default pipeline with all stages enabled
* **Treatment**: pipeline with the rules stage disabled

This lets you isolate the impact of specific pipeline stages on recommendation quality. See [A/B Testing](/guides/ab-testing) for setup details.

***

## Fallback behaviour

If no pipeline config exists for your team, the system uses sensible defaults:

* All stages enabled
* `candidate_limit`: 100
* `page_size`: 20

You only need to configure the pipeline if you want to change these defaults.