botium-connector-cognigy

Botium Connector for Cognigy AI

This is a Botium connector for testing your Cognigy AI chatbot.

Did you read the Botium in a Nutshell articles? Be warned, without prior knowledge of Botium you won't be able to properly use this library!

How it works

Botium connects to the REST Endpoint of your Cognigy AI chatbot.

It can be used as any other Botium connector with all Botium Stack components:

• Botium CLI
• Botium Bindings
• Botium Box

Requirements

• Node.js and NPM
• a Cognigy AI bot
• a project directory on your workstation to hold test cases and Botium configuration

Install Botium and Cognigy AI Connector

When using Botium CLI:

> npm install -g botium-cli
> npm install -g botium-connector-cognigy
> botium-cli init
> botium-cli run

When using Botium Bindings:

> npm install -g botium-bindings
> npm install -g botium-connector-cognigy
> botium-bindings init mocha
> npm install && npm run mocha

When using Botium Box:

Already integrated into Botium Box, no setup required

Connecting Cognigy AI chatbot to Botium

1. In your Cognigy project, deploy a REST Endpoint
2. Create a botium.json in your project directory and add your Cognigy Endpoint URL

{
  "botium": {
    "Capabilities": {
      "PROJECTNAME": "<whatever>",
      "CONTAINERMODE": "cognigy",
      "COGNIGY_URL": "https://endpoint-demo.cognigy.ai/xxxxxxxxxxxxxxxxxxxxxx",
    }
  }
}

3. (Optional) If you want to enable NLP Analytics (Intent Resolution, Confidence Score), follow these steps:

   3.1. Enable Collect Analytics in your Entpoint Settings

   3.2. Find your Cognigy OData Endpoint

   3.3. Create an Api Key in your Cognigy Profile

   3.4. Adjust the botium.json file:

    {
      "botium": {
        "Capabilities": {
          "PROJECTNAME": "<whatever>",
          "CONTAINERMODE": "cognigy",
          "COGNIGY_URL": "https://endpoint-demo.cognigy.ai/xxxxxxxxxxxxxxxxxxxxxx",
          "COGNIGY_NLP_ANALYTICS_ENABLE": true,
          "COGNIGY_NLP_ANALYTICS_ODATA_URL": "https://odata-demo.cognigy.ai",
          "COGNIGY_NLP_ANALYTICS_ODATA_APIKEY": "xxxxxxxxxxxxxxxxxxxxxxxxxx"
        }
      }
    }

4. To check the configuration, run the emulator (Botium CLI required) to bring up a chat interface in your terminal window:

> botium-cli emulator

Botium setup is ready, you can begin to write your BotiumScript files.

How to start samples

• Adapt botium.json in the sample directory
• Install packages, run the test

> cd ./samples/travelbook
> npm install && npm test

Supported Capabilities

Set the capability CONTAINERMODE to cognigy to activate this connector.

COGNIGY_ENDPOINT_TYPE

Can be 'REST' or 'SOCKETIO'

Default: 'REST'

COGNIGY_URL

Cognigy Endpoint URL

COGNIGY_USER_ID

User id

Optional. Will be a generated GUID by default.

COGNIGY_NLP_ANALYTICS_ENABLE

Enable NLP Analyics (Intent Resolution, Confidence Score)

Disable if you don't need this feature (faster responses)

COGNIGY_NLP_ANALYTICS_ODATA_URL

Cognigy OData Analyics Endpoint

Optional. Only needed if NLP Analyics is enabled.

More about Cognigy Odata Endpoint you can find in Cognigy Docs - OData Analyics Endpoint

COGNIGY_NLP_ANALYTICS_ODATA_APIKEY

OData Api Key

Optional. Only needed if NLP Analyics is enabled.

More about Cognigy Api Keys you can find in Cognigy Docs - Api Keys

COGNIGY_NLP_ANALYTICS_WAIT

Time to wait for fetching NLP Analyics Data after each Convo Step (in milliseconds)

Default: 5000

COGNIGY_API_URL

For downloading intents and user examples

COGNIGY_API_APIKEY

For downloading intents and user examples

Roadmap

• Support for additional channel and channel content
• Support for intent/entity asserter
• Support for sentiment analyze