RAG

import { RunAnywhere } from '@runanywhere/core'

const session = await RunAnywhere.rag.open({
  embeddingModel: { id: 'all-minilm-l6-v2' },
  llmModel: { id: 'smollm2-360m-q8_0' },
})

await session.ingest({ text: 'RunAnywhere runs models on device.' })

await session.ingest([
  { text: 'The first document.', metadata: { source: 'notes' } },
  { text: 'The second document.', id: 'doc-2' },
])

await session.ingestAll(documents) // same work as ingest on an array

// Retrieval only
const matches = await session.search('battery life', 3)
for (const match of matches) {
  console.log(match.score, match.text, match.metadata)
}

// Grounded answer
const result = await session.query('How long does the battery last?')
console.log(result.answer)
console.log(result.sources.map((s) => s.score))

const result = await session.query(question, { reasoning: { mode: 'off' } })

const iterator = session.queryStream(question)[Symbol.asyncIterator]()
let answer = ''
try {
  let step = await iterator.next()
  while (!step.done) {
    const event = step.value
    if (event.type === 'retrieved') setSources(event.matches)
    if (event.type === 'token') {
      answer += event.text
      setAnswer(answer)
    }
    if (event.type === 'completed') console.log(event.result.tokensPerSecond)
    step = await iterator.next()
  }
} finally {
  await iterator.return?.()
}

const stats = await session.stats()
console.log(stats.documentCount, stats.chunkCount, stats.indexSizeBytes)

await session.clear() // drops every chunk, session stays open
await session.close() // releases the session and its index

import type { RagSession } from '@runanywhere/core'

const sessionRef = useRef<RagSession | null>(null)

const loadDocument = async (text: string) => {
  await sessionRef.current?.close()
  sessionRef.current = null

  const session = await RunAnywhere.rag.open({
    embeddingModel: { id: embeddingId },
    llmModel: { id: llmId },
  })
  sessionRef.current = session
  await session.ingest({ text })
}