style: prettier format

This commit is contained in:
AnotiaWang
2025-02-11 22:57:49 +08:00
parent 84f63abb3d
commit d027965013
23 changed files with 485 additions and 331 deletions

View File

@ -1,60 +1,60 @@
interface TextSplitterParams {
chunkSize: number;
chunkSize: number
chunkOverlap: number;
chunkOverlap: number
}
abstract class TextSplitter implements TextSplitterParams {
chunkSize = 1000;
chunkOverlap = 200;
chunkSize = 1000
chunkOverlap = 200
constructor(fields?: Partial<TextSplitterParams>) {
this.chunkSize = fields?.chunkSize ?? this.chunkSize;
this.chunkOverlap = fields?.chunkOverlap ?? this.chunkOverlap;
this.chunkSize = fields?.chunkSize ?? this.chunkSize
this.chunkOverlap = fields?.chunkOverlap ?? this.chunkOverlap
if (this.chunkOverlap >= this.chunkSize) {
throw new Error('Cannot have chunkOverlap >= chunkSize');
throw new Error('Cannot have chunkOverlap >= chunkSize')
}
}
abstract splitText(text: string): string[];
abstract splitText(text: string): string[]
createDocuments(texts: string[]): string[] {
const documents: string[] = [];
const documents: string[] = []
for (let i = 0; i < texts.length; i += 1) {
const text = texts[i];
const text = texts[i]
for (const chunk of this.splitText(text!)) {
documents.push(chunk);
documents.push(chunk)
}
}
return documents;
return documents
}
splitDocuments(documents: string[]): string[] {
return this.createDocuments(documents);
return this.createDocuments(documents)
}
private joinDocs(docs: string[], separator: string): string | null {
const text = docs.join(separator).trim();
return text === '' ? null : text;
const text = docs.join(separator).trim()
return text === '' ? null : text
}
mergeSplits(splits: string[], separator: string): string[] {
const docs: string[] = [];
const currentDoc: string[] = [];
let total = 0;
const docs: string[] = []
const currentDoc: string[] = []
let total = 0
for (const d of splits) {
const _len = d.length;
const _len = d.length
if (total + _len >= this.chunkSize) {
if (total > this.chunkSize) {
console.warn(
`Created a chunk of size ${total}, +
which is longer than the specified ${this.chunkSize}`,
);
)
}
if (currentDoc.length > 0) {
const doc = this.joinDocs(currentDoc, separator);
const doc = this.joinDocs(currentDoc, separator)
if (doc !== null) {
docs.push(doc);
docs.push(doc)
}
// Keep on popping if:
// - we have a larger chunk than in the chunk overlap
@ -63,81 +63,81 @@ which is longer than the specified ${this.chunkSize}`,
total > this.chunkOverlap ||
(total + _len > this.chunkSize && total > 0)
) {
total -= currentDoc[0]!.length;
currentDoc.shift();
total -= currentDoc[0]!.length
currentDoc.shift()
}
}
}
currentDoc.push(d);
total += _len;
currentDoc.push(d)
total += _len
}
const doc = this.joinDocs(currentDoc, separator);
const doc = this.joinDocs(currentDoc, separator)
if (doc !== null) {
docs.push(doc);
docs.push(doc)
}
return docs;
return docs
}
}
export interface RecursiveCharacterTextSplitterParams
extends TextSplitterParams {
separators: string[];
separators: string[]
}
export class RecursiveCharacterTextSplitter
extends TextSplitter
implements RecursiveCharacterTextSplitterParams
{
separators: string[] = ['\n\n', '\n', '.', ',', '>', '<', ' ', ''];
separators: string[] = ['\n\n', '\n', '.', ',', '>', '<', ' ', '']
constructor(fields?: Partial<RecursiveCharacterTextSplitterParams>) {
super(fields);
this.separators = fields?.separators ?? this.separators;
super(fields)
this.separators = fields?.separators ?? this.separators
}
splitText(text: string): string[] {
const finalChunks: string[] = [];
const finalChunks: string[] = []
// Get appropriate separator to use
let separator: string = this.separators[this.separators.length - 1]!;
let separator: string = this.separators[this.separators.length - 1]!
for (const s of this.separators) {
if (s === '') {
separator = s;
break;
separator = s
break
}
if (text.includes(s)) {
separator = s;
break;
separator = s
break
}
}
// Now that we have the separator, split the text
let splits: string[];
let splits: string[]
if (separator) {
splits = text.split(separator);
splits = text.split(separator)
} else {
splits = text.split('');
splits = text.split('')
}
// Now go merging things, recursively splitting longer texts.
let goodSplits: string[] = [];
let goodSplits: string[] = []
for (const s of splits) {
if (s.length < this.chunkSize) {
goodSplits.push(s);
goodSplits.push(s)
} else {
if (goodSplits.length) {
const mergedText = this.mergeSplits(goodSplits, separator);
finalChunks.push(...mergedText);
goodSplits = [];
const mergedText = this.mergeSplits(goodSplits, separator)
finalChunks.push(...mergedText)
goodSplits = []
}
const otherInfo = this.splitText(s);
finalChunks.push(...otherInfo);
const otherInfo = this.splitText(s)
finalChunks.push(...otherInfo)
}
}
if (goodSplits.length) {
const mergedText = this.mergeSplits(goodSplits, separator);
finalChunks.push(...mergedText);
const mergedText = this.mergeSplits(goodSplits, separator)
finalChunks.push(...mergedText)
}
return finalChunks;
return finalChunks
}
}