Ingest content
Easily set up your knowledge base data in NLX
Last updated
Easily set up your knowledge base data in NLX
Last updated
Content, in its simplest form, refers to knowledge base data that your conversational AI draws from to deliver a response when a user's query is matched. When properly set up, your application retrieves your Knowledge base content during conversation, typically when a user's utterance (query) is unmatched to a flow, slot value or external value, or UI element.
When setting up your knowledge base, you may choose one of the following methods to ingest and host content:
Articles: Content that's entered locally and stored by NLX
Documents: File content that, once uploaded through NLX, is automatically managed for you in S3
Integration or Custom: Content hosted through a managed provider (e.g., Amazon Bedrock, Azure AI Search, Zendesk Sunshine, etc.) or your own custom vector store through S3 bucket hosting
Consider using the native NLX LLM to dynamically rephrase your content by turning on the Knowledge base's .
Articles allows you to provide question and answer pairings of knowledge base content and stores the content locally within NLX:
Select Resources from workspace menu > Choose Knowledge bases > New knowledge base
Provide a name to your Knowledge base
Select Articles as content type > Click Create knowledge base
Upload a CSV or JSON file, or select + Add article to manually enter question and answer pair
Repeat as needed with more articles
Click Save
Optional
After creating your Articles, the Publish tab makes your Articles data live and also updates your Knowledge base with any changes made since the last publish. These updates immediately become available to any application using an Articles Knowledge base.
Click the Publish tab of your Articles knowledge base
Select Create your first deployment button
Optional:
Enter a description of your deployment to keep track of changes
Click Publish knowledge base
To rollback your Articles Knowledge base to a previous state, select Rollback next to the desired version from the Deployment column.
Integration allows you to establish an API connection to your knowledge base content that is externally stored through a data store service, including Amazon Bedrock, Azure AI Search, Google Vertex AI, or Zendesk Sunshine.
When your conversational AI invokes the knowledge base to locate a response to an unknown user query, an API call is made to your custom service.
Select Resources from workspace menu > Choose Knowledge bases > New knowledge base
Provide a name to your Knowledge base
Select Integration as content type > Click Create knowledge base
Click Save
Documents is a document loader that allows you to ingest unencrypted PDFs, images, and text files of data that is then stored via S3 and managed through NLX.
Select Resources from workspace menu > Choose Knowledge bases > New knowledge base
Provide a name to your Knowledge base
Select Documents as content type > Click Create knowledge base
Click Save
Custom allows you to establish an API connection to your knowledge base content that is externally stored through a custom data store you manage. When your conversational AI invokes the knowledge base to locate a response to an unknown user query, an API call is made to your custom service.
Select Resources from workspace menu > Choose Knowledge bases > New knowledge base
Provide a name to your Knowledge base
Select External as content type > Click Create knowledge base
Click Save
Payload: Provide a URL along with the article response. Payload format:
Publishing new versions of your Articles Knowledge base content allows you to experience changes without needing to create a new application deployment following an initial .
This content implementation type supports in-line citations in generated responses. To enable this functionality, create a flow that includes a and activate the Include citations toggle during configuration.
This content implementation type supports in-line citations in generated responses. To enable this functionality, create a flow that includes a and activate the Include citations toggle during configuration.
This content implementation type supports Metadata filters during retrieval. To enable this functionality, provide .