activities
latest
false
Integration Service Activities
Last updated Oct 8, 2024

About Context grounding

UiPath® 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 indices and embeddings of business data that UiPath GenAI features can reference for contextual evidence at runtime.

Context groundingis a tenant-scoped platform service designed to support UiPath GenAI experiences (such as GenAI Activities) by grounding user 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 reference 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.

Terminology and core components of Context grounding include:

Figure 1. Context grounding Component Architecture
docs image

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 than 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 indices.

Semantic similarity search

  • Search through LLM-ready business data to find the most relevant information.
  • Interpret prompt 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.

RAG

  • 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.

For more information, refer to the following pages:

Core features

Here are some of the key features of Context grounding:

  • Multi-document support: PDF, JSON, and CSV files are currently supported, with more formats planned.
  • Managed ingestion and indexing pipelines: UiPath optimizes the ingestion and indexing of data in UiPath-managed vector databases.
  • Multiple surfaces: Currently available as part of the UiPath GenAI Activities.
  • Semantic similarity search: 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 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.
  • Data sources: UiPath Orchestrator bucket entities: data stored within shared folders in Orchestrator bucket entities can be ingested, indexed, and queried.

  • Multilingual Support: Ability to ingest and query from documents in all UTF-8 encoded languages.

Limitations

  • Context Grounding currently supports PDF, JSON, and CSV file types.
  • There is a limit of ten indices per tenant. We recommend you keep a 1-1 relationship with these and the Orchestrator buckets in which you are uploading the business data you want Context Grounding to use. This means you are able to upload, ingest, and query from ten Orchestrator buckets per tenant.
  • To use Context Grounding via UiPath GenAI Activities, you must use Studio Web or Studio Desktop version 2024.4 or newer. For more information, see the Getting started section.
  • Core features
  • Limitations

Was this page helpful?

Get The Help You Need
Learning RPA - Automation Courses
UiPath Community Forum
Uipath Logo White
Trust and Security
© 2005-2024 UiPath. All rights reserved.