- Getting started
- Data security and compliance
- Organizations
- Authentication and security
- Licensing
- Tenants and services
- Accounts and roles
- AI Trust Layer
- About AI Trust Layer
- Managing AI Trust Layer
- Best practices
- Common Context Grounding patterns
- Notifications
- Frequently asked questions
- External applications
- Notifications
- Logging
- Troubleshooting
- Migrating to Automation Cloud™
Frequently asked questions
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.
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.
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.
You can use Context Grounding through UiPath GenAI Activities and Autopilot for everyone.
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".
Context Grounding is accessible to all tenants and organizations.
Context Grounding is hosted in the European Union, Japan, and United States regions. Data leveraged by Context Grounding is limited to these three regions. Other UiPath regions will be routed to these three regions.
Context Grounding charges for searches or RAG as it is executed through its supported UiPath product surfaces:
- When you use Context Grounding with GenAI Activities, an additional AIU is charged. For example, if you use the Content Generation without Context Grounding, the run execution charges 1 AIU. If you use Content Generation with Context Grounding, the run execution cost is 2 AIU.
- Autopilot activities are measured through Autopilot actions, not AI units. When you use Context grounding, with or without a Context Grounding query, the cost remains the same: 1 Autopilot action. For more information on Autopilot actions, see the Autopilot licensing page.
Yes, Context Grounding is only available in UiPath Automation CloudTM.
Context Grounding is available in the European Union, Japan, and United States regions of UiPath Automation CloudTM.
Context Grounding currently works the following data formats: PDF, JSON, CSV, DOCX, TXT, XLS.
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.
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.
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.
All data shared with UiPath is treated with standard enterprise compliance, encryption, and security standards. 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.
Context Grounding is tenant-scoped and takes advantage of existing RBAC and 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.
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.
- What is Context Grounding?
- Why is Context Grounding important?
- How does Context Grounding work?
- How do I use Context Grounding?
- Does Context Grounding eliminate hallucinations?
- Do I have access to Context Grounding?
- Do I have to pay for Context Grounding?
- Is Context Grounding only in the cloud?
- Where is Context Grounding hosted in the cloud?
- What types of data can I use in Context Grounding?
- Can I import additional business data into Context Grounding?
- Is there a limit on the amount of data I can include in Context Grounding?
- Is Context Grounding the same as RAG?
- How is my data stored or shared with Context Grounding?
- How do you ensure data security?
- How is Context Grounding permissioned?
- Can I dynamically select which LLM to use?