Documentation Index Fetch the complete documentation index at: https://koreai.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
Back to NLP Topics
Build your Knowledge Graph in a CSV spreadsheet or JSON file, then import it into your AI Agent. This is useful when your FAQ data already exists outside the platform or when you need to make frequent bulk updates.
Steps:
Download the sample CSV or JSON file from the AI Agent.
Edit the file to add questions, responses, synonyms, etc.
Import the file. See Import a Knowledge Graph .
CSV File
Download the Sample
Go to Automation AI > Knowledge AI > FAQs > ⋯ (more) > Import .
Back up your existing KG when prompted (choose CSV or JSON format).
Click Proceed , then click Sample CSV to download.
CSV Structure
The CSV contains five section types, each preceded by a header row.
FAQ Section
Column Description FaqSection header; leave blank in data rows. Que IDAuto-generated by the platform. Leave blank for new FAQs; do not edit for existing ones. PathNode path for the FAQ. Prefix mandatory nodes with **; organizer nodes with !!. Primary QuestionThe main question. Leave blank to add an alternate answer to the previous question. Alternate QuestionOptional. Add one per row for multiple alternates. TagsTags for the question or alternate question. AnswerThe response. Supports plain text, scripts (SYS_SCRIPT; <js>), channel-specific (SYS_CHANNEL_<name> SYS_TEXT; <text>), or dialog trigger (SYS_INTENT; <dialog ref id>). Extended Answer-1 / Extended Answer-2Optional. Use when the response is lengthy. ReferenceIdOptional. External source reference. Display NameOptional. Shown to users in ambiguity scenarios.
Nodes Section
Column Description NodeSection header; leave blank in data rows. NodepathPath to the node/tag. TagRequired for tag settings; leave blank for node. PreconditionConditions required to qualify this node/tag. outputcontextContext populated by this node/tag. TraitsTraits for this node/tag.
Synonyms Section
Column Description SynonymsSection header; leave blank in data rows. PhraseThe term or phrase for which to add synonyms. SynonymsComma-separated synonym values.
To enable Bot Synonyms in KG term identification:
Use confidenceConfigs as the header.
Set parameter to useBotSynonyms and value to true or false.
KG Params Section
Column Description KG ParamsSection header; leave blank in data rows. langApp language code (e.g., en for English). stopwordsComma-separated stop words.
Traits Section
Column Description TraitsSection header; leave blank in data rows. langApp language code. GroupNameTrait group name. matchStrategyPattern or probability (ML-based).scoreThresholdThreshold (0-1) when matchStrategy is ML-based. TraitNameName of the trait. Training dataUtterances for the trait.
For Taxonomy-based KG (FAQs linked to other FAQs):
Field Description faqLinkedToQue ID of the source FAQ this FAQ is linked to.faqLinkedByQue IDs of FAQs linked to this FAQ.isSoftDeletedIdentifies FAQs that are deleted but still have linked FAQs.
JSON File
Download the Sample
Go to Automation AI > Knowledge AI > FAQs > ⋯ (more) > Import .
Back up when prompted, then click Proceed .
Click Sample JSON to download.
JSON Property Reference
Property Type Description FAQArray Contains question, answer, terms (leaf to first-level node), and alternate questions. questionString Primary question (inside FAQ array). answerString AI Agent response (inside FAQ array). termsArray Leaf node and parent nodes up to the first-level node. refIdString Optional external source reference. Alternate QuestionsArray Alternate questions and their terms (leaf to first-level node). SynonymsObject Arrays of terms and their synonyms. UnmappedpathArray Nodes with no questions, and their parents up to first-level node. TraitsObject Trait names as keys; arrays of utterances as values.
For Taxonomy-based KG:
Field Description faqLinkedToIdentifies the source FAQ. faqLinkedByLists the FAQs linked to this FAQ. isSoftDeletedIdentifies deleted FAQs that still have linked FAQs.