> ## Documentation Index
> Fetch the complete documentation index at: https://llm-tools.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# ❓ 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

<ParamField path="userQuery" type="string" required>
  Question to ask
</ParamField>

<ParamField path="conversationId" type="string" optional>
  The conversation ID to which the query belongs in case this is a chatbot scenario
</ParamField>

<ParamField path="customContext" type="Chunk[]" optional>
  In case you want to pass along your own context information. Passing this parameter disables the default context generation.

  <Expandable title="Chunk properties">
    <ParamField name="pageContent" type="string">
      The context text that is passed to the LLM
    </ParamField>

    <ParamField name="metadata" type="Metadata">
      The metadata that is passed to EmbedJs

      <Expandable title="Metadata">
        <ParamField name="id" type="string">
          Unique identifier for the bit of information
        </ParamField>

        <ParamField name="uniqueLoaderId" type="string">
          The unique identifier for the group of information bits
        </ParamField>

        <ParamField name="source" type="string">
          The source string returned if this piece of info was used by the LLM
        </ParamField>
      </Expandable>
    </ParamField>
  </Expandable>
</ParamField>

### Returns

<ResponseField name="id" type="string">
  Unique identifier for the query response in a conversation
</ResponseField>

<ResponseField name="timestamp" type="Date">
  Unique identifier for the query response in a conversation
</ResponseField>

<ResponseField name="content" type="string">
  Unique identifier for the query response in a conversation
</ResponseField>

<ResponseField name="sources" type="SourceDetail[]">
  The individual sources that were used to generate the answer

  <Expandable title="SourceDetail properties">
    <ResponseField name="loaderId" type="string">
      Unique identifier for the loader
    </ResponseField>

    <ResponseField name="source" type="string">
      The source of the information
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="tokenUse" type="object">
  The number of tokens used to answer the query

  <Expandable title="properties">
    <ResponseField name="inputTokens" type="number | 'UNKNOWN'">
      The number of input tokens used to process the query
    </ResponseField>

    <ResponseField name="outputTokens" type="number | 'UNKNOWN'">
      The number of output tokens used to process the query
    </ResponseField>
  </Expandable>
</ResponseField>

## Usage

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

```ts Code Example theme={null}
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' })
/*

*/
```