Remy Reference/agent/queryDataSource

queryDataSource

Legacy v1 data sources. v2 apps should use `dataSources.defineDataSource()` from @mindstudio-ai/agent instead, which owns parsing, chunking, embedding and citations. Search a vector data source (RAG) and return relevant document chunks.

mindstudio.queryDataSource({ dataSourceId, query, maxResults }) → Result

Legacy v1: RAG search over a v1 data source, returning matching chunks. New apps use DataSource.search in this SDK, which adds reranking and citations.

Parameters

dataSourceId

string

RequiredID of the vector data source to query

query

string

RequiredThe search query to run against the data source

maxResults

number

RequiredMaximum number of chunks to return (recommended 1-3)

Call from a method

import { mindstudio } from '@mindstudio-ai/agent';

const result = await mindstudio.queryDataSource({
  dataSourceId: /* ... */,
  query: /* ... */,
  maxResults: /* ... */
});