Acerca de la puesta a tierra del 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).

Proporcionar RAG como servicio a las experiencias de UiPath GenAI ayuda a:

• Supera las limitaciones de la ventana de contexto de LLM: tanto para modelos pequeños como grandes, RAG ayuda a mejorar la precisión, la fiabilidad, la escalabilidad y la eficiencia de los modelos a medida que interactúan con las bases de conocimiento.
• Reduzca el riesgo de alucinaciones mediante referencias a almacenes de datos reales.
• Da acceso a las aplicaciones generativas a fuentes de conocimiento especializadas y propietarias.
• Da acceso a las aplicaciones generativas a fuentes de información actualizadas.
• Habilita los bucles de retroalimentación positiva entre los almacenes de datos y las consultas de los usuarios.

Core components

The terminology and core components of Context Grounding include:

Figure 1. Context Grounding component architecture

Ingestión e indexación: prepara tus datos empresariales para 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.
• Interpreta la solicitud como una consulta para buscar a través de incrustaciones y produce los resultados más relevantes basados en la búsqueda de similitud de coseno. Estos resultados de búsqueda son un paso intermedio y precursor de RAG, para aumentar las solicitudes con el contexto relevante de los datos empresariales.

Retrieval Augmented Generation

• Aterriza y actualiza las solicitudes con la información más relevante de los resultados de la búsqueda de similitud semántica, luego ejecuta una generación a través de un LLM alojado a través de la puerta de enlace LLM de la capa de confianza de IA.

Características clave

Estas son algunas de las características clave de 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 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.