Sobre embasamento de contexto

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 and Autopilot for everyone) by grounding your prompts with relevant information before they are executed by the LLM via retrieval augmented generation (RAG).

Fornecer RAG como um serviço para experiências da UiPath GenAI ajuda a:

• Supere as limitações da janela de contexto do LLM: para modelos pequenos e grandes, o RAG ajuda a melhorar a precisão, confiabilidade, escalabilidade e eficiência dos modelos à medida que interagem com bancos de conhecimento.
• Reduza o risco de paliatividade por meio de referências a armazenamentos de dados de verdade.
• Dê a aplicativos generativos acesso a fontes de conhecimento especializadas e proprietárias.
• Dê acesso a aplicativos generativos a fontes atualizadas de informação.
• Habilite loops de feedback positivos entre armazenamentos de dados e consultas de usuários.

Core components

The terminology and core components of Context Grounding include:

Figure 1. Context Grounding component architecture

Ingestão e indexação: prepare seus dados de negócios para o LLM

• 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 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.
• Interprete o prompt como uma consulta para pesquisar por meio de incorporações e produza os resultados mais relevantes com base na pesquisa de similaridade de cosseno. Esses resultados da pesquisa são uma etapa intermediária e percursora do RAG para aumentar os prompts com contexto relevante dos dados de negócios.

Retrieval Augmented Generation

• Embase e atualize os prompts com as informações mais relevantes dos resultados da pesquisa de similaridade semântica e, em seguida, execute uma geração por meio de um LLM hospedado pelo LLM Gateway da AI Trust Layer.

Principais funcionalidades

Aqui estão alguns dos principais recursos do Embasamento de contexto:

• 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 Microsoft OneDrive & SharePoint and Google Drive: Context Grounding can access data directly stored in third-party applications.

Limitations and considerations

• 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 see, 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, see the Getting started section.