Orchestrator user guide

DELIVERY:

Last updated Dec 5, 2025

Managing indexes

The Indexes page displays your currently configured indexes and enables you to create new indexes in shared folders that you have permissions to.

For each listed index, you can view its name, data source, description, ingestion status, when it was last synced, and when it was last queried. Use the refresh icon to retrieve the latest information.

For any listed index, select the context menu to:

Edit the index, to update the index description. Once you create an index, you cannot change the ingestion technique, but you can specify which data formats to ingest in that specific job.
Sync the index with the data source, to ingest the latest data.
Delete the index. This action can break existing processes for indexes used in agents, GenAI activities, or Autopilot.

Index health

The Index health helps you monitor the condition of your Context Grounding indexes and identify those that may need maintenance or cleanup. It provides an automated, objective score showing how well each index performs and how frequently it’s used.

Each index receives a health score based on two criteria:

Ingestion reliability – How successfully documents were processed during the latest ingestion run.
Utilization – How recently the index has been queried.

The combined score helps you determine whether an index is healthy and delivering value (overall score above 75%), or degraded (overall score 75% or below). The score updates automatically after each successful ingestion or query.

Index health is recalculated every 15 minutes for all tenants and only applies to indexes with completed ingestion jobs. New indexes have a 24-hour grace period after creation before health scoring begins.

The following table describes how each health criterion is calculated and weighted to determine the overall index health score.

Table 1.
Criterion	Metric	Formula	Notes
Ingestion reliability	Success rate from last ingestion	100 × (1 - failed_docs / total_docs)	Skipped and deleted documents are excluded. If no ingestion is completed within 24h, score = 0.
Utilization	Days since last query (max 90 days)	100 × (1 - days_since_last_query / 90)	After 24h without any query, score = 0.
Overall health	Average of both metrics	(Ingestion Reliability + Utilization)	Calculated only if both component scores exist.

Creating indexes

Creating indexes is supported only in shared folders.

To create an index, take the following steps:

From the Indexes page, select the Add Index button. The Add Indexes window is displayed.
Under General Details, add an Index name and a Description.

Note: Index names cannot include the following characters: (, ), or -. Storage bucket names do not have these restrictions. Keep this in mind if you plan to use matching names for indexes and storage buckets.
Under Data Settings, configure your preferred data source: Storage Bucket or Connector. Ensure your data is stored within shared folders.
1. If you choose Storage bucket:
  - Select the Orchestrator folder containing the bucket.
  - Choose the file type matching the files in your specified bucket. Select All for all file types. Note that certain file types or large scale of documents may take longer to ingest.
  - Upload files directly using one of the following options:
    - Drag and drop files into the File Upload box.
    - Select Add files to open the file picker.
  - Review the uploaded files. You can remove individual files before saving.
2. If you select Connector:
  - Navigate to the desired Orchestrator folder for connection creation.
  - Select the appropriate Integration Service connector.
  - Choose an existing connection or create a new one.
  After establishing the connection, select the Data Source location (the folder in the external storage system), and the File type. Optional: Enable Include subfolders to access nested directories.
Under Additional settings, specify the ingestion pattern:
- Basic – Ingests text-based documents.
- Advanced – Ingests both image-based and text-based documents. This option entails specific costs. For details, refer to Context Grounding licensing.
Use the Enable schedule toggle to turn on scheduling to run ingestions automatically. When scheduling ingestions, you can configure the following options:
- Timezone – Select the timezone in which the ingestion will run.
- Frequency – Choose how often the ingestion runs:
  - Daily – Runs every day at a specified hour.
  - Weekly (default) – Runs on one or more selected weekdays at a specified hour.
  - Monthly – Runs on one or more selected dates of the month. You can also choose from two preconfigured options: Last day of the month, or Last working day of the month.
Select Save.

On this page

Index health
Creating indexes

Was this page helpful?

PREVIOUSAbout indexes

NEXTFAQ - Deprecating the testing module

Support and Services

Get The Help You Need

UiPath Academy

Learning RPA - Automation Courses

UiPath Forum

UiPath Community Forum

Trust and Security

Cookies Policy