Mejores prácticas

Esta sección incluye información sobre cómo utilizar Context Grounding de forma eficaz.

Primeros pasos

To start using Context Grounding, follow these steps:

1. Asegúrate de utilizar la versión 2024.4 o posterior de Studio Web o Studio Desktop.
2. In Automation Cloud^TM, in Integration Service, establish a connection to the UiPath GenAI Activities connector.

   This allows you to use the GenAI Activities in Studio.

3. To create and manage indexes, access the Context Grounding tab in Automation Cloud™ > Admin > AI Trust Layer. You can then query indexes from Autopilot for everyone or from the GenAI Activities.

Context Grounding in UiPath GenAI Activities

Para utilizar Context Grounding necesitas un conjunto de datos (p. ej., un grupo de documentos) fácilmente disponible. Entonces, Context Grounding puede interactuar con tus datos en tres fases:

1. Establece tu origen de datos para Context Grounding.
   • Context Grounding follows shared folder permissions. Use a folder with appropriate access to manage and query from data.
   • Create a connection to the supported Integration Service data sources or add data to a shared Orchestrator bucket location.
2. Ingerir datos de tu origen de datos en Context Grounding.
   • Use the Context Grounding tab in the AI Trust Layer admin to create, sync, and delete indexes.
   • Use the Update Context Grounding Index activity to sync an index you have created. This allows non-admins to help manage the data freshness of an index based on new data.
3. Consultas y solicitudes de tierra con tus datos.
   • Use the Content Generation activity or Autopilot for everyone to query over documents and use information to augment or ground prompts.

Gestionar el proceso de ingestión

You can manage the ingestion pipelines in two ways:

• Through the Context Grounding tab in AI Trust Layer. See Governing contextual data for GenAI features.
• Through the Update Context Grounding Index activity, part of the UiPath GenAI activities package.

Querying data with Context Grounding

The Content Generation activity features two options for working with documents: File resource and Existing index.

Recurso de archivo

The File resource option allows you to use file variables from previous activities (like a document downloaded from Google Drive) and have Context Grounding perform a just-in-time (JIT) style of RAG. This means it ingests the document into an index, searches across it, augments the prompt, and then deletes the index, so the data is not persistent.

Nota:

• Mantén estos documentos más pequeños (menos de 50 páginas). Las actividades de Integration Service tienen una ventana de tiempo de espera en la que debe tener lugar todo el procesamiento anterior.
• Si tienes un PDF con imágenes escaneadas, recomendamos utilizar la opción OCR de Document Understanding en la actividad Extraer datos después de haber descargado un archivo para extraer el texto de estas imágenes (ya que Context Grounding aún no admite imágenes). Pasa esa salida extracted_data a la solicitud con ese recurso de archivo apuntando a tu archivo descargado.

Índice existente

The Existing index option allows you to use an index you have previously created through AI Trust Layer. You query across a persistent index into which you've ingested documents from your data source. You can re-use this index as many times as you like until you delete it.

Use the Log Message activity after Content Generation in the workflow sequence to gather detailed information:

• Input the Top Generated Text or Citations string output variables from Content Generation to see the LLM generation response after the workflow execution.
• Input the Citations string variable to see the semantic search results used to influence the generation output. This works only for PDF and JSON data types.