❓ query

The .query() method empowers developers to ask questions and receive relevant answers through a user-friendly query API. Function signature is given below:

Parameters

userQuery · string · required

Question to ask

conversationId · string

The conversation ID to which the query belongs in case this is a chatbot scenario

customContext · Chunk[]

In case you want to pass along your own context information. Passing this parameter disables the default context generation.

Show Chunk properties

Returns

id · string

Unique identifier for the query response in a conversation

timestamp · Date

Unique identifier for the query response in a conversation

content · string

Unique identifier for the query response in a conversation

sources · SourceDetail[]

The individual sources that were used to generate the answer

Show SourceDetail properties

loaderId · string

Unique identifier for the loader

source · string

The source of the information

tokenUse · object

The number of tokens used to answer the query

Show properties

inputTokens · number | 'UNKNOWN'

The number of input tokens used to process the query

outputTokens · number | 'UNKNOWN'

The number of output tokens used to process the query

Usage

If you want to get the answer to question and return both answer and citations, use the following code snippet:

Code Example

import { RAGApplicationBuilder } from '@llm-tools/embedjs';
import { OllamaEmbeddings } from '@llm-tools/embedjs-ollama';
import { WebLoader } from '@llm-tools/embedjs-loader-web';
import { HNSWDb } from '@llm-tools/embedjs-hnswlib';

const ragApplication = await new RAGApplicationBuilder()
.setModel(new Ollama({ modelName: "llama3.2", baseUrl: 'http://localhost:11434' }))
.setEmbeddingModel(new OllamaEmbeddings({ model: 'nomic-embed-text', baseUrl: 'http://localhost:11434' }))
.setVectorDatabase(new HNSWDb())
.build();

ragApplication.addLoader({ urlOrContent: 'https://www.forbes.com/profile/elon-musk' })
ragApplication.addLoader({ urlOrContent: 'https://en.wikipedia.org/wiki/Elon_Musk' })

await ragApplication.query('What is the net worth of Elon Musk today?')
await ragApplication.query('Who is Elon Musk?' { conversationId: '1' })
/*

*/