Importing and Exporting Bot Ontology

You can build a Knowledge Graph in a CSV or JSON file and upload it to a bot. Similarly, you can export existing Knowledge Graph to CSV or JSON. Exporting a Knowledge Graph helps you edit it in a spreadsheet or import it to another Bot.

Importing Knowledge Graph

1. Open Knowledge Graph.
2. You will find the Import option against the Knowledge Graph.
   
3. Click Import.
4. Do one of the following:
   • If you are creating the Knowledge Graph from scratch, click Proceed.
     -or-
   • If you have an existing Knowledge Graph, make sure to take a backup of the same to a CSV or JSON file, and then Proceed.
     Note: Importing an Knowledge Graph does not update it but replaces the entire existing Knowledge Graph.
5. Drag and drop the file in the Import window or click Browse to navigate to the file.
6. Click Next to begin the import.
7. After the importing is completed, the success message appears in a dialog. Click Done.
8. The hierarchy will be displayed in the Knowledge Graph and you can edit and train the same.

Exporting Knowledge Graph

To export a Knowledge Graph:

1. Open Knowledge Graph.
2. You will find the Export option against the Knowledge Graph.
   
3. Based on the preferred format: click Export JSON or Export CSV.
4. The Knowledge Graph file will be downloaded to your machine.

Creating Knowledge Graph

Instead of creating the Knowledge Graph from the platform UI, you might want to work in your preferred editor like Spreadsheet or as a JSON file. The platform gives you the option to create a Knowledge Graph in spreadsheet or JSON and use the same to Import it into the Bot.

This involves these steps:

1. Download sample CSV or a JSON file. You can download these sample files from a blank Knowledge Graph too.
2. Edit the file by adding rows corresponding to the questions, responses, synonyms, etc..
3. Import the file to your Bot.

From a CSV File

You can create the Knowledge Graph using a sample spreadsheet that can be downloaded from the bot. If you anticipate frequent changes to the Knowledge Graph, we recommend you to create it in a spreadsheet as it would easier to make bulk updates compared to the application UI.

Follow the instructions below to build your Knowledge Graph in a spreadsheet.

Downloading the Sample CSV file

1. Open the Knowledge Graph.
2. Click Import from the left section.
3. You will be prompted to back up the Knowledge Graph before proceeding. Choose the CSV or JSON format for the backup.
4. After backup, click Proceed.
5. On the next dialog, click Sample CSV. The CSV file is downloaded to your local computer.
   

Building the Knowledge Graph in a CSV (post rel7.3)

The format for the CSV file has been modified in the ver 7.3 of the Bots platform to cater for details regarding alternate answers, extended responses, and advanced responses. See below for the older format.  You are strongly recommended to use the new format since the older format would be deprecated in the upcoming releases.

• The following types of entries are supported:
  • Faq – the leaf level nodes with questions and answers.
  • Node – for node/tags, traits, preconditions, and output context.
  • Synonyms
  • KG Params
  • Traits
• Each of the above categories needs to be preceded by the appropriate header.
• The header helps identify the new vs old versions of the JSON file by the platform.

The following is the detailed information for each section and the content expected for each.

FAQ

This contains the actual questions and answers along with the alternate questions, answers, and extended answers.

Following are the column-wise details that can be given:

• Faq – mandatory entry in the header, should be left blank in the following rows.
• Que ID – the question id generated by the platform for each question.
• Path – to which the FAQ belongs
  • mandatory node names should be prefixed with ** and
  • organizer nodes with !!
• Primary Question – the actual question user might ask – when left blank the entry in the Answer column would be considered as the alternate answer to the previous primary question.
• Alternate Question – optional – alternate question to the primary question, if there are multiple alternate questions, they should be given in multiple rows.
• Tags – for each question or alternate question
• Answer – to the question, serves as an alternate answer when the primary question field is left blank. Answer format can be:
  • plain text
  • script with SYS_SCRIPT prefix i.e. SYS_SCRIPT <answer in javascript format>
  • channel-specific formatted response when prefixed with SYS_CHANNEL_<channel-name>, the answer can be simple or in script format:
    • SYS_CHANNEL_<channel-name> SYS_TEXT <answer>
    • SYS_CHANNEL_<channel-name> SYS_SCRIPT <answer in javascript format>
  • trigger a dialog then prefix with SYS_INTENT i.e. SYS_INTENT <dialog ref id>
• Extended Answer-1 – optional to be used in case the response is lengthy.
• Extended Answer-2 – optional to be used in case the response is lengthy.

Nodes

This section includes settings for both nodes and tags.

• Node – mandatory entry in the header, should be blank in the following rows.
• Que ID – mandatory when specifying settings for tags, leave blank for nodes.
• nodepath – path for reaching the node/tag.
• Tag – mandatory for tag settings, leave blank for node.
• precondition – for qualifying this node/tag.
• outputcontext – context to be populated by this node/tag.
• Traits – for this node/tag

Synonyms

Use this section to enter the synonyms as key-value pairs.

• Synonyms – mandatory entry in the header, should be blank in the following rows.
• Phrase – for which the synonym needs to be entered.
• Synonyms – comma-separated values.

Use of Bot Synonyms in KG term identification can be enabled using the following:

• confidenceConfigs – mandatory entry in the header, should be blank in the following rows.
• parameter – “useBotSynonyms” in this case
• value – true or false

KG Params

• KG Params – mandatory entry in the header, should be blank in the following rows.
• lang – bot language code for example en for English.
• stopwords – comma-separated values.

Traits

Trait related information can be specified as follows:

• Traits – mandatory entry in the header, should be blank in the following rows.
• lang – bot language code for example en for English.
• GroupName – trait group name.
• matchStrategy – pattern or probability (for ML-based).
• scoreThreshold – threshold value (between 0 and 1) when the matchStrategy above is set to ML-based.
• TraitName – the name of the trait.
• Training data – utterances for the trait.

From a JSON file

Kore.ai allows you to create the Knowledge Graph in JSON and upload it. You can download a sample JSON from the bot to understand its structure.

Follow the instructions below to build your Knowledge Graph using JSON:

Downloading the JSON sample

1. Open the Knowledge Graph.
2. Click Import from the left section.
3. You will be prompted to backup the Knowledge Graph before proceeding. Choose the CSV or JSON format for the backup.
4. After backup, click Proceed.
5. On the next dialog, click Sample JSON. The JSON file is downloaded to your local computer.
   

JSON Reference

Building the Knowledge Graph in a CSV (before rel 7.3)

NOTE: This format will be deprecated in upcoming releases

Open the downloaded Sample CSV file.

The details that you need to enter in each row of the CSV file differ based on the type of information. For example, the details you need to enter for an FAQ (Question, Answer, Nodes, Alternate Questions) differ from the details you need to enter for Synonyms (Term, Synonyms).

The bot interprets the data present in each row of the CSV file, depending on the information type specified in Column # 1 of the row. Below are the valid entries for Column#1 of the CSV file, which represent the different information types:

• faq: Represents a primary or Alternate question in the Knowlege Graph.
• unmappedpath: Represents nodes with no questions associated with it.
• synonyms: Represents global synonyms for terms.
• classes: Represents the trait names and their associated utterances.

The following sections provide the remaining details that you must fill for each information type:

FAQ

Primary Question

Note: Enter the names of all the parent nodes in separate columns until you reach the First-level node in the path.

Alternate Questions

Terms/Tags

• Mandatory tags and terms can be prefixed with **
• Organizer tags and terms can be prefixed with !!

Unmappedpath

Unmappedpath refers to nodes for which no question is added.

Global Synonyms

Path Synonyms

Traits