- Getting started
- Data security and compliance
- Organizations
- Authentication and security
- Licensing
- Tenants and services
- Accounts and roles
- AI Trust Layer
- External applications
- Notifications
- Logging
- Troubleshooting
- Migrating to Automation Cloud
Automation Cloud admin guide
About Context Grounding
Context Grounding is a component of the UiPath AI Trust Layer which allows you to bring in your data to generate more accurate, reliable GenAI predictions. Context Grounding is designed to make your business data LLM-ready without the need for any additional subscription to embedding models, vector databases, or large language models (LLMs). You can create representative indexes and embeddings of business data that UiPath GenAI features can reference for contextual evidence at runtime.
Context Grounding is a tenant-scoped platform service designed to support UiPath GenAI experiences (such as GenAI Activities, Autopilot for Everyone, and UiPath Agents) by grounding your prompts with relevant information before they are executed by the LLM via retrieval augmented generation (RAG).
Providing RAG as a service to UiPath GenAI experiences helps to:
- Overcome LLM context window limitations: for both small and large models, RAG helps improve accuracy, reliability, scalability, and efficiency of models as they interact with knowledge bases.
- Reduce risk of hallucination through references to ground truth data stores.
- Give generative apps access to specialized and proprietary knowledge sources.
- Give generative apps access to up-to-date sources of information.
- Enable positive feedback loops between data stores and user-queries.
The terminology and core components of Context Grounding include:
Ingestion and indexing: make your business data LLM-ready
- Ingestion: Convert business data into representative embeddings using UiPath-managed embedding models.
- Embedding: A representation of business data that an LLM can understand and search through.
- Index: A folder in a vector database that organizes the embeddings.
- Vector DBs: UiPath-managed vector database that stores embeddings organized in indexes.
Retrieval
- Search through LLM-ready business data to find the most relevant information. Context Grounding uses a variety of extraction, chunking, retrieval, and re-ranking techniques that are optimized based on different data formats and queries.
- Products that use Context Grounding (GenAI Activities, Autopilot for Everyone, Agents) interpret prompts as a query to search through embeddings, and produce the most relevant results based on cosine similarity search. These search results are an intermediate, precursor step to RAG, to augment prompts with relevant context from business data.
Retrieval Augmented Generation
- Ground and update prompts with the most relevant information from the semantic similarity search results, then execute a generation via an LLM hosted through the LLM Gateway of the AI Trust Layer.
The following list presents some of the key features of Context Grounding:
- Multi-document support: PDF, JSON, CSV, XLS, DOCX, TXT files.
- Managed ingestion and indexing pipelines: UiPath optimizes the ingestion and indexing of data in UiPath-managed vector databases.
- Multiple surfaces: Context Grounding is currently available as part of the UiPath GenAI Activities, AI Trust Layer (with a dedicated UI), and Autopilot for Everyone.
- Data retrieval: Query within documents or across datasets using a variety of techniques (e.g. query transformation, embedding, fine tuning, etc.) to ensure search results are highly relevant.
- Retrieval Augmented Generation: Ground prompts via just-in-time (JIT) in-memory or over a knowledge base.
- Proof of knowledge: Provides a citation of the reference source and text from the semantic similarity search.
- Streaming support: Streaming API support to show generation as it is being produced.
- Multilingual support: Ability to ingest and query from documents in all UTF-8 encoded languages.
- Support for
multiple data sources:
- UiPath Orchestrator bucket entities: You can ingest, index, and query data stored within shared folders in Orchestrator bucket entities.
- Document storage systems: Through Integration Service connectors, such as Dropbox, Google Drive, and Microsoft OneDrive & SharePoint: Context Grounding can access data directly stored in third-party applications.
- Context Grounding currently supports specific file types: PDF, JSON, CSV, XLS, DOCX, TXT.
- There is a limit of ten indexes per tenant. We recommend you keep a 1-1 relationship with these and the folder path in the data source you want to use.
- Context Grounding respects folder permissions and authorization for shared folder entities. Users who do not have the appropriate permissions may not be able to view, update, delete, or use indexes that are affiliated with folders they do not have permissions to.
- To use Context Grounding through UiPath GenAI Activities, you must use Studio Web or Studio Desktop version 2024.4 or newer. For more information, refer to the Getting started section.
The core components of Context Grounding are designed to provide a mechanism that supports finding pertinent information within and across documents, and surfacing only the most relevant pieces needed for a high-quality, low-latency generation from an LLM.
Searching within documents
The Context Grounding service helps you find specific information within a single document more effectively. Instead of just matching keywords, it understands the meaning and context of your search query. For example, if you're looking for information about "apple pie recipes" in a cookbook, it would understand that you're interested in desserts and baking, not technology or fruit farming.
Searching across documents
Context Grounding helps you find information spread across multiple documents. It can understand the relationships between different pieces of information and provide more relevant results. For example, if you're researching "climate change effects on agriculture" across various scientific papers, it pulls together relevant information from multiple sources, understanding that topics like rainfall patterns, crop yields, and temperature changes are all related to your query.
This means you can use Context Grounding for:
-
Data extraction and comparison: Context Grounding can automatically identify and extract specific types of information from documents, then compare them in meaningful ways. Imagine you have a stack of résumés and want to compare candidates' work experiences. The service could extract job titles, durations, and responsibilities, then present them in a way that makes comparison easy, even if the information is formatted differently in each résumé.
-
Summarization: Context Grounding can create summaries of long documents or multiple related documents. It doesn't pick out random sentences, but understands the key points and overall message. For example, if you have a long report on market trends, the service can provide a summary highlighting the main findings, key statistics, and overall conclusions.
You can subscribe to receive notifications from Context Grounding in Automation CloudTM. Visit Notifications panel to learn more.
Events serve as triggers for notifications. The Context Grounding events that generate notifications are:
- Ingestion Job Completed
- Ingestion Job Failed
- Ingestion Job Started
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, Autopilot for Everyone, and Agents.
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.
- 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 Autopilot, with or without a Context Grounding query, the cost remains the same: 1 Autopilot action. For more information on Autopilot actions, refer to 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 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.
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.
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.
- Core components
- Key features
- Limitations and considerations
- Common Context Grounding patterns
- How it works
- Notifications
- Events
- Severity
- Frequently asked questions
- 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?
