Files
simstudioai--sim/apps/sim/lib/chunkers/text-chunker.ts
T
wehub-resource-sync d25d482dc2
Publish CLI Package / publish-npm (push) Waiting to run
Publish Python SDK / publish-pypi (push) Waiting to run
Publish TypeScript SDK / publish-npm (push) Waiting to run
CI / Migrate Dev DB (push) Has been skipped
CI / Detect Version (push) Has been cancelled
CI / Migrate DB (push) Has been cancelled
CI / Build Dev ECR (./docker/app.Dockerfile, ECR_APP) (push) Has been cancelled
CI / Build Dev ECR (./docker/db.Dockerfile, ECR_MIGRATIONS) (push) Has been cancelled
CI / Build Dev ECR (./docker/pii.Dockerfile, ECR_PII) (push) Has been cancelled
CI / Build Dev ECR (./docker/realtime.Dockerfile, ECR_REALTIME) (push) Has been cancelled
CI / Deploy Trigger.dev (Dev) (push) Has been cancelled
CI / Build AMD64 (./docker/app.Dockerfile, ECR_APP, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build AMD64 (./docker/db.Dockerfile, ECR_MIGRATIONS, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build AMD64 (./docker/pii.Dockerfile, ECR_PII, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build AMD64 (./docker/realtime.Dockerfile, ECR_REALTIME, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/app.Dockerfile, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/db.Dockerfile, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/pii.Dockerfile, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/realtime.Dockerfile, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Check Docs Changes (push) Has been cancelled
CI / Process Docs (push) Has been cancelled
CI / Create GitHub Release (push) Has been cancelled
CI / Test and Build (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:20:55 +08:00

109 lines
2.5 KiB
TypeScript

import type { Chunk, ChunkerOptions } from '@/lib/chunkers/types'
import {
addOverlap,
buildChunks,
cleanText,
estimateTokens,
resolveChunkerOptions,
splitAtWordBoundaries,
tokensToChars,
} from '@/lib/chunkers/utils'
export class TextChunker {
private readonly chunkSize: number
private readonly chunkOverlap: number
private readonly separators = [
'\n---\n',
'\n***\n',
'\n___\n',
'\n# ',
'\n## ',
'\n### ',
'\n#### ',
'\n##### ',
'\n###### ',
'\n\n',
'\n',
'. ',
'! ',
'? ',
'; ',
', ',
' ',
]
constructor(options: ChunkerOptions = {}) {
const resolved = resolveChunkerOptions(options)
this.chunkSize = resolved.chunkSize
this.chunkOverlap = resolved.chunkOverlap
}
private splitRecursively(text: string, separatorIndex = 0): string[] {
const tokenCount = estimateTokens(text)
if (tokenCount <= this.chunkSize) {
return text.trim() ? [text] : []
}
if (separatorIndex >= this.separators.length) {
const chunkSizeChars = tokensToChars(this.chunkSize)
return splitAtWordBoundaries(text, chunkSizeChars)
}
const separator = this.separators[separatorIndex]
const parts = text.split(separator).filter((part) => part.trim())
if (parts.length <= 1) {
return this.splitRecursively(text, separatorIndex + 1)
}
const chunks: string[] = []
let currentChunk = ''
for (const part of parts) {
const testChunk = currentChunk + (currentChunk ? separator : '') + part
if (estimateTokens(testChunk) <= this.chunkSize) {
currentChunk = testChunk
} else {
if (currentChunk.trim()) {
chunks.push(currentChunk.trim())
}
if (estimateTokens(part) > this.chunkSize) {
const subChunks = this.splitRecursively(part, separatorIndex + 1)
for (const subChunk of subChunks) {
chunks.push(subChunk)
}
currentChunk = ''
} else {
currentChunk = part
}
}
}
if (currentChunk.trim()) {
chunks.push(currentChunk.trim())
}
return chunks
}
async chunk(text: string): Promise<Chunk[]> {
if (!text?.trim()) {
return []
}
const cleaned = cleanText(text)
let chunks = this.splitRecursively(cleaned)
if (this.chunkOverlap > 0) {
const overlapChars = tokensToChars(this.chunkOverlap)
chunks = addOverlap(chunks, overlapChars)
}
return buildChunks(chunks, this.chunkOverlap)
}
}