RAG

Open a session with an embedding model, add documents, ask questions.

const session = await RunAnywhere.rag.open({ id: 'all-minilm-l6-v2' }, { id: 'qwen3-0.6b' })

await session.ingest(RagDocument.text(contents))

const answer = await session.query('What is the refund window?')
console.log(answer.text)

await session.close()

Opening

rag.open(embeddingModel: ModelRef, llmModel?: ModelRef, config?: RagConfig): Promise<RagSession>

Omit llmModel for a retrieval-only session: search works, query does not.

RagSession

session.ingest(document: RagDocument): Promise<void>
session.ingest(documents: readonly RagDocument[]): Promise<void>
session.search(query: string, topK?: number): Promise<Match[]>
session.query(question: string, options?: RagQueryOptions): Promise<RagResult>
session.queryStream(question: string, options?: RagQueryOptions): AsyncIterable<RagEvent>
session.stats(): Promise<RagStats>
session.clear(): Promise<void>
session.close(): Promise<void>

Ingesting a dropped file

dropZone.addEventListener('drop', async (event) => {
  event.preventDefault()

  for (const file of event.dataTransfer?.files ?? []) {
    const text = await file.text()
    await session.ingest(RagDocument.text(text, { sourceUri: file.name }))
  }
})

Ingestion chunks, embeds, and indexes. It is the slow part, so do it once and keep the session rather than re-ingesting per question. Show progress for anything larger than a page.

Retrieval without generation

const matches = await session.search('refund policy', 5)

Useful for showing sources, or for feeding matches into your own prompt.

Streaming an answer

for await (const event of session.queryStream('What is the refund window?')) {
  if (event.type === 'token') answer += event.text
  if (event.type === 'sources') renderSources(event.matches)
}

Sources usually arrive before the first token, which is what lets you show what the answer is based on while it is still being written.

Configuration

const session = await RunAnywhere.rag.open(
  { id: 'all-minilm-l6-v2' },
  { id: 'qwen3-0.6b' },
  { retrievalTopK: 5, chunkSize: 512, chunkOverlap: 64 }
)

Field	Meaning
`retrievalTopK`	Chunks retrieved per question
`chunkSize`	Characters per chunk
`chunkOverlap`	Overlap between neighbouring chunks
`similarityThreshold`	Drop matches below this score
`persistPath`	Where the index lives, for reuse across sessions

Overlap matters more than it looks. Without it, a sentence split across a chunk boundary is retrievable from neither half.

Two models at once

A RAG session holds an embedding model and a language model. In a tab that is real memory pressure, so prefer a small embedding model: all-minilm-l6-v2 is a fraction of the size of the language model beside it.

Closing

await session.close()

Close before opening another, and close on pagehide. Because the index is process-wide, a session you forget to close blocks every later one for the lifetime of the page.

window.addEventListener('pagehide', () => {
  void session?.close()
})

Swift SDK

Kotlin SDK

React Native SDK

Flutter SDK

Web SDK

Electron SDK

Opening

RagSession

Ingesting a dropped file

Retrieval without generation

Streaming an answer

Configuration

Two models at once

Closing

​Opening

​RagSession

​Ingesting a dropped file

​Retrieval without generation

​Streaming an answer

​Configuration

​Two models at once

​Closing

Opening

RagSession

Ingesting a dropped file

Retrieval without generation

Streaming an answer

Configuration

Two models at once

Closing