@or-sdk/qna

QnA SDK

The @or-sdk/qna package provides a client for working with the QnA (Question and Answer) system in OneReach.ai. With this client, you can perform operations such as loading documents, creating collections, searching in collections, and asking questions to generate answers based on the loaded documents.

Installation

To install the package, run the following command:

$ npm install @or-sdk/qna

Usage

To use the QnA client, you need to create an instance of the class with the appropriate configuration options. You can either provide the direct API URL or the service discovery URL. Here is an example:

import { QnA } from '@or-sdk/qna';

// with direct api url
const qna = new QnA({
  token: 'my-account-token-string',
  serviceUrl: 'http://example.qna/endpoint'
});

// with service discovery(slower)
const qna = new QnA({
  token: 'my-account-token-string',
  discoveryUrl: 'http://example.qna/endpoint'
});

Once you have an instance of the QnA client, you can use its methods to interact with the OneReach.ai QnA system. The available methods are:

loadDocument

Load a document into a collection.

Params

• [0]: string - Collection name.
• [1]: string - Document name.
• [2]: CreateDocument - Document creation parameters.

Example

await qna.loadDocument('myCollection', 'myDocument', {
  url: 'https://example.com/document.pdf'
});

removeDocument

Remove a document from a collection.

Params

• [0]: string - Collection name.
• [1]: string - Document name.

Example

await qna.removeDocument('myCollection', 'myDocument');

createCollection

Create a new collection.

Params

• [0]: CreateCollection - Collection creation parameters.

Example

await qna.createCollection({ collection: 'myCollection' });

deleteCollection

Delete a collection.

Params

• [0]: string - Collection name.

Example

await qna.deleteCollection('myCollection');

search

Search in the collection.

Params

• [0]: string - Collection name.
• [1]: Search - Search parameters.
• [2]?: number - Optional limit of search results (defaults to 5).

Example

const searchResults = await qna.search('myCollection', { term: 'coffee' });
console.log(searchResults.documents);

ask

Answer a question.

Params

• [0]: string - Collection name.
• [1]: Ask - Ask question parameters.
• [2]?: number - Optional limit of search results (defaults to 5).

Example

const askResults = await qna.ask('myCollection', {
  question: 'What are the health benefits of coffee?',
  messages: [
    { role: 'user', content: 'Tell me about coffee' },
    { role: 'assistant', content: 'Coffee is a popular beverage...' }
  ]
});

console.log(askResults.result.content);