Häufig gestellte Fragen

What is Context grounding?

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.

Why is Context grounding important?

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.

How does Context grounding work?

Context grounding provides two services:

• Verwaltete Vektor-DB als Dienst: Wir machen es Ihnen leicht, Ihre Daten in Einbettungsdarstellungen zu konvertieren.
• 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.

How do I use Context grounding?

You can use Context grounding through UiPath GenAI Activities.

1. Index und Erfassung (öffentliche Vorschau): Erstellen Sie einen Index in der verwalteten Vektordatenbank und den zugehörigen Einbettungen. Der erstellte Index kann dann zur Laufzeit für RAG abgefragt werden. Sie müssen:
   1. Laden Sie Daten in Orchestrator-Bucket-Entitäten in freigegebenen Orchestrator-Ordnern hoch.
2. Index löschen (öffentliche Vorschau): Löschen Sie Indizes, die Sie in Ihrem Mandanten erstellen.
3. Content Generation: This activity includes a parameter for Context grounding, with two options:
   1. Vorhandener Index: Ermöglicht Ihnen die Abfrage für Dokumente im Index, der in der Aktivität Index und Erfassung (öffentliche Vorschau) erstellt wurde.
   2. Dateiressource: Ermöglicht das Erfassen und Abfragen einer einzelnen Dateiressourcenvariable (ein einzelnes Dokument), ohne einen Index zu erstellen.

Does Context grounding eliminate hallucinations?

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".

Do I have access to Context grounding?

Context grounding is now available in preview. It is accessible to all tenants and organizations. Context grounding is only hosted in the United States and European Union regions. Data leveraged by Context grounding is limited to these two regions. Other UiPath regions will be routed to these two regions.

Do I have to pay for Context grounding?

Context grounding is free while the feature is in preview.

Is Context grounding only in the cloud?

Yes, Context grounding is only available in UiPath Automation Cloud^TM.

Where is Context grounding hosted in the cloud?

Context grounding is available in the United States and European Union regions of UiPath Automation Cloud^TM.

What types of data can I use in Context grounding?

Context grounding currently works with PDF, JSON, and CSV objects. Future releases will bring additional support for structured and unstructured data formats.

Can I import additional business data into Context grounding?

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.

Is there a limit on the amount of data I can include in Context grounding?

Das Datenlimit, das Sie zum Erstellen Ihrer Aufforderungen verwenden können, basiert auf den Größenbeschränkungen der Token für das Modellkontextfenster. Beziehen Sie sich auf das Modell, das Sie zum Ausführen der RAG verwenden (z. B. in GenAI-Aktivitäten), um potenzielle Schwellenwerte für Tokenlimits zu bestimmen.

• Indexlimit: Es gibt ein Limit von zehn Indizes pro Mandant. Wir empfehlen Ihnen, eine 1:1-Beziehung zwischen den Orchestrator-Buckets beizubehalten, aus denen Sie Daten erfassen, um Datenverluste zwischen Ordnern zu verhindern und die logische Trennung von Daten sicherzustellen, die möglicherweise von verschiedenen Benutzern für unterschiedliche Zwecke abgefragt werden müssen. Kontextgrundlage nutzt die Ordnerautorisierungsberechtigungen, um diese Empfehlung zu erzwingen.
• Speicher: Es gibt keine Speicherbeschränkung für die Speicherung in oder innerhalb dieser Indizes. Wir legen jedoch einige Beschränkungen für Kunden auf, die übermäßige Datenmengen aufgenommen haben.

Is Context grounding the same as RAG?

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.

Which UiPath products and services support Context grounding?

Context grounding is currently available as part of the UiPath GenAI Activities activity package. You can use the service as standalone activities or as parameters in the activity.

How is my data stored or shared with Context grounding?

All data shared with UiPath is treated with standard enterprise compliance, encryption, and security standards. This includes features like Context grounding. Context grounding is also 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.

Wie gewährleistet man die Datensicherheit?

Context grounding is tenant-scoped and takes advantage of existing RBAC, AuthZ policies in UiPath, in addition to encrypting data at rest and in transit.

Da es sich um einen Mandanten-Scope handelt, werden keine Daten über Indizes innerhalb desselben Mandanten oder zwischen Mandanten hinweg freigegeben.

How is Context grounding permissioned?

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.

Kann ich dynamisch auswählen, welches LLM verwendet werden soll?

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.