Versions Compared

Version Old Version 4 New Version Current
Changes made by

sneha.tripathi

sneha.tripathi

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Info

Organization-specific custom templates are configured in Luma Knowledge to create Artifacts manually. Refer to /wiki/spaces/DOC/pages/26179469332for more details.

Creating an Artifact

Follow the below steps to create an Artifact using the Regular Template manually:

...

Info

If your tenant is enbaled to use Generative AI and tenant is Metadata-Search enabled, you can skip providing information in the summary field. The Summary is automatically generated based on the content.

Processing the Artifact

For Metadata Search:

Once the Artifact is added, Luma generates ontology for the artifact. The Metadata is added to the artifact, which is then used to identify Knowledge during the search. When Open AI features system performs the following:

...

Info

  • In case the Summary field is empty, information added to the Summary field on the selected template is automatically added as Artifact Summary and used to generate Ontology for the artifact. To add a different artifact summary, add the information in the Summary field.

  • Fields marked as Hidden in the selected template are not available for the curator while creating an Artifact manually. The fields are only used when the artifact is created by importing a Document with a template.

  • In case a Topic is not identified during the Ontology Generation, the Artifact is automatically linked to the default Topic under the selected Domain. You can update the Artifact and link it to the correct Topic in Knowledge Graph. Refer to Knowledge Graph for more information.

  • If the selected template contains a 'Redirect Link' field, any artifact associated with the template when accessed through Luma Virtual Agent redirects to the URL added to the field in a new browser window.

For Semantic Search:

Once the Artifact is added, No Curation of the artifact is required. Ontology, Summary, and FAQ generation are skipped for Semantic Search. The system automatically does the following to generate the searchable artifact content.

  • Data Extraction and Chunking: In this phase, text is collected or extracted from the source document. The extracted text is then divided into manageable chunks, typically at the semantic level (e.g., paragraphs).

  • Vectorization: The text chunks undergo embedding, where they are converted into vectors or numerical forms. This conversion is crucial for enabling efficient and accurate search capabilities. The resulting embeddings are stored in a vector database, ready for search and retrieval operations.

...

Reviewing Artifact

As a Curator, you should verify and ensure that the metadata generated by the system is correct and Artifact is related to the correct Topic. If the automatically generated Topic is not available in the Knowledge Graph, then the artifact is assigned to the default Topic of the selected domain.

...

  1. Click on Edit.

  2. Add the required keyword to metadata fields and Save Changes.

Publishing Artifact

Based on the Artifact Publishing Mode configuration for your tenant and the identified metadata, the Artifact state is determined :

...