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.
Concepts
Collection
A collection is a group of searchable items, also known as passages. It allows you to organize and manage related documents and their passages together under a single entity. When you perform a search or ask a question, the QnA system will search through the passages within the specified collection.
Document
Documents are used to load a bulk of data into a collection. They can be any type of text-based file such as PDFs, text files, or web pages. When you provide a URL for a document, the QnA system downloads the content, splits it into smaller chunks (passages), and adds them to the collection.
Passage
A passage is an atomic piece of data that represents a portion of a document. It is the smallest searchable unit within a collection. When you search or ask a question, the QnA system uses vector similarity to find the most relevant passages from all the documents in the collection.
The search process involves comparing the vector representation of the input query (search term or question) with the vector representations of the passages in the collection. The results are ranked based on the similarity between the query and passages, with the most similar passages being returned as the search results.
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';
const qna = new QnA({
token: 'my-account-token-string',
serviceUrl: 'http://example.qna/endpoint'
});
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:
Methods
loadDocument
Load a document into a collection.
const collectionId = 'a1b2c3d4-uuid';
const document = await qna.loadDocument(collectionId, {
description: 'A sample document',
url: 'http://example.com/sample-document.pdf',
name: 'Sample Document',
});
{
id: 'e5f6g7h8-uuid',
accountId: 'i9j0k1l2-uuid',
collection: 'a1b2c3d4-uuid',
name: 'Sample Document',
description: 'A sample document'
}
createCollection
Create a new collection.
const collection = await qna.createCollection({
description: 'A sample collection',
name: 'Sample Collection',
});
{
id: 'a1b2c3d4-uuid',
accountId: 'i9j0k1l2-uuid',
name: 'Sample Collection',
description: 'A sample collection'
}
deleteCollection
Delete a collection by its ID.
const collectionId = 'a1b2c3d4-uuid';
await qna.deleteCollection(collectionId);
search
Search for documents in a collection.
const collectionId = 'a1b2c3d4-uuid';
const searchResults = await qna.search(collectionId, {
term: 'search term',
limit: 10,
});
[
{
id: 'e5f6g7h8-uuid',
distance: '0.1234',
content: 'Found passage content',
metadata: {}
}
]
ask
Ask a question and generate an answer based on the documents in a collection.
const collectionId = 'a1b2c3d4-uuid';
const askResults = await qna.ask(collectionId, {
question: 'What is the meaning of life?',
messages: [
{ role: 'user', content: 'Hello' },
{ role: 'assistant', content: 'Hi there!' },
],
limit: 10,
});
{
result: { role: 'assistant', content: 'The meaning of life is 42.' },
searchResult: {
id: 'e5f6g7h8-uuid',
distance: '0.1234',
content: 'Found passage content',
metadata: {}
}
}
updateDocument
Update a document's description.
const collectionId = 'a1b2c3d4-uuid';
const documentId = 'e5f6g7h8-uuid';
const updatedDocument = await qna.updateDocument(collectionId, documentId, {
description: 'Updated document description',
});
{
id: 'e5f6g7h8-uuid',
accountId: 'i9j0k1l2-uuid',
collection: 'a1b2c3d4-uuid',
name: 'Sample Document',
description: 'Updated document description'
}
updateCollection
Update a collection's description.
const collectionId = 'a1b2c3d4-uuid';
const updatedCollection = await qna.updateCollection(collectionId, {
description: 'Updated collection description',
});
{
id: 'a1b2c3d4-uuid',
accountId: 'i9j0k1l2-uuid',
name: 'Sample Collection',
description: 'Updated collection description'
}
getDocument
Get a document by its ID.
const collectionId = 'a1b2c3d4-uuid';
const documentId = 'e5f6g7h8-uuid';
const document = await qna.getDocument(collectionId, documentId);
{
id: 'e5f6g7h8-uuid',
accountId: 'i9j0k1l2-uuid',
collection: 'a1b2c3d4-uuid',
name: 'Sample Document',
description: 'A sample document'
}
getCollection
Get a collection by its ID.
const collectionId = 'a1b2c3d4-uuid';
const collection = await qna.getCollection(collectionId);
{
id: 'a1b2c3d4-uuid',
accountId: 'i9j0k1l2-uuid',
name: 'Sample Collection',
description: 'A sample collection'
}
listDocuments
List documents in a collection with optional pagination and query.
const collectionId = 'a1b2c3d4-uuid';
const documents = await qna.listDocuments(collectionId, {
query: 'search query',
limit: 10,
offset: 0,
});
```json
[
{
"id": "e5f6g7h8-uuid",
"accountId": "i9j0k1l2-uuid",
"collection": "a1b2c3d4-uuid",
"name": "Sample Document",
"description": "A sample document"
}
]
listCollections
List collections with optional pagination and query.
const collections = await qna.listCollections({
query: 'search query',
limit: 10,
offset: 0,
});
[
{
"id": "a1b2c3d4-uuid",
"accountId": "i9j0k1l2-uuid",
"name": "Sample Collection",
"description": "A sample collection"
}
]
removeDocument
Remove a document from a collection.
const collectionId = 'a1b2c3d4-uuid';
const documentId = 'e5f6g7h8-uuid';
await qna.removeDocument(collectionId, documentId);