Frequently asked questions

What is Context grounding?

Context grounding is a new UiPath® feature, part of the AI Trust Layer. It provides a mechanism to search and retrieve relevant context from data to ground prompts and guide more precise generations from large language models (LLMs) through UiPath GenAI features and products.

Why is Context grounding important?

Context grounding provides evidence via user-provided data to LLMs to influence their generations. This makes predictions more tailored to your use cases and data, rather than based on the general data upon which LLMs are trained. This allows both attended and unattended automations which leverage GenAI to be more accurate and precise.

How does Context grounding work?

Context grounding provides two services:

• Managed Vector DB as a Service: We make it easy for you to convert your data into embedding representations.
• Retrieval Augmented Generation (RAG) as a Service: Context grounding queries data from various automation products, retrieves the most relevant results, and augments prompts with those results to ensure generations are more specific.

How do I use Context grounding?

You can use Context grounding through UiPath GenAI Activities.

1. Index and Ingest (Public Preview): Establish an index in the managed vector database and associated embeddings. The created index can then be queried at runtime for RAG. You need to:
   1. Upload data into Orchestrator bucket entities in shared Orchestrator folders.
2. Delete Index (Public Preview): Delete indices you create in your tenant.
3. Content Generation: This activity includes a parameter for Context grounding, with two options:
   1. Existing index: Allows you to query across documents in the index created in the Index and Ingest (Public Preview) activity.
   2. File resource: Allows you to ingest and query a single file resource variable (one single document) without creating an index.

Context grounding is also available via Automation Cloud^TM Admin, as part of the AI Trust Layer admin experience. See Governing contextual data for GenAI features.

Does Context grounding eliminate hallucinations?

No, but it does significantly reduce the likelihood of hallucinations because generations are based on information queried from user-provided data. By default, Context grounding provides a citation, or proof of knowledge, from which the generation was based. This means you can verify and validate the source. When Context grounding isn't able to find a highly confident corresponding answer in the provided data, it does not try to make up answers. Instead, it generates a response such as: "An answer could not be found".

Do I have access to Context grounding?

Context grounding is now available in preview. It is accessible to all tenants and organizations. Context grounding is only hosted in the United States and European Union regions. Data leveraged by Context grounding is limited to these two regions. Other UiPath regions will be routed to these two regions.

Do I have to pay for Context grounding?

Context grounding is free while the feature is in preview.

Is Context grounding only in the cloud?

Yes, Context grounding is only available in UiPath Automation Cloud^TM.

Where is Context grounding hosted in the cloud?

Context grounding is available in the United States and European Union regions of UiPath Automation Cloud^TM.

What types of data can I use in Context grounding?

Context grounding currently works with PDF, JSON, and CSV objects. Future releases will bring additional support for structured and unstructured data formats.

Can I import additional business data into Context grounding?

To leverage Context grounding, you need to import data into UiPath Orchestrator storage buckets (via direct upload, Studio activity, or API). You can then use Context grounding activities to ingest and index, and manage the queried data to ensure highly relevant results.

Is there a limit on the amount of data I can include in Context grounding?

The limit of data you can use to ground your prompts is based on the model context window token size limits. Refer to the model you are using to execute the RAG (e.g., in GenAI activities) to determine potential token limit thresholds.

• Index limit: There is a limit of ten indices per tenant. We recommend you maintain a 1-1 relationship between Orchestrator buckets from which you are ingesting data to prevent data leak across folders and ensure logical separation of data that may need to be queried by different users for different purposes. Context Grounding takes advantage of folder authorization permissions to help enforce this recommendation.
• Storage: There is no limit on storage across or within these indices. However, we impose some limits on customers who have exceedingly high amount of data ingested.

Is Context grounding the same as RAG?

Context grounding does provide a RAG service at runtime for UiPath GenAI experiences. However, it also provides a managed vector database as a service to help manage the data used at runtime. This guarantees a high-quality search and generated results.

Which UiPath products and services support Context grounding?

Context grounding is currently available as part of the UiPath GenAI Activities activity package. You can use the service as standalone activities or as parameters in the activity.

How is my data stored or shared with Context grounding?

All data shared with UiPath is treated with standard enterprise compliance, encryption, and security standards. This includes features like Context grounding. Context grounding is also part of the AI Trust Layer, which means your data is never stored outside of UiPath, nor is it used to train third-party models.

How do you ensure data security?

Context grounding is tenant-scoped and takes advantage of existing RBAC, AuthZ policies in UiPath, in addition to encrypting data at rest and in transit.

Because it is tenant-scoped, no data is shared across indices within the same tenant or across tenants.

How is Context grounding permissioned?

Context grounding is tenant-scoped. We support folder-level authorization in Orchestrator buckets, and Context grounding leverages existing authentication and Automation Ops policies applied to the GenAI Activities.

Can I dynamically select which LLM to use?

In the UiPath GenAI activities you can select which LLM to use for executing the RAG portion that Context grounding supports. You can select any LLM available in the LLM Gateway (part of the UiPath AI Trust Layer). UiPath then manages the ingestion and semantic search strategies to optimize the generation.