forked from FlowiseAI/Flowise
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request FlowiseAI#347 from FlowiseAI/feature/CodeTextSplitter
Feature/CodeSplitter
- Loading branch information
Showing
4 changed files
with
136 additions
and
58 deletions.
There are no files selected for viewing
128 changes: 128 additions & 0 deletions
128
packages/components/nodes/textsplitters/CodeTextSplitter/CodeTextSplitter.ts
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,128 @@ | ||
import { INode, INodeData, INodeParams } from '../../../src/Interface' | ||
import { getBaseClasses } from '../../../src/utils' | ||
import { | ||
RecursiveCharacterTextSplitter, | ||
RecursiveCharacterTextSplitterParams, | ||
SupportedTextSplitterLanguage | ||
} from 'langchain/text_splitter' | ||
|
||
class CodeTextSplitter_TextSplitters implements INode { | ||
label: string | ||
name: string | ||
description: string | ||
type: string | ||
icon: string | ||
category: string | ||
baseClasses: string[] | ||
inputs: INodeParams[] | ||
constructor() { | ||
this.label = 'Code Text Splitter' | ||
this.name = 'codeTextSplitter' | ||
this.type = 'CodeTextSplitter' | ||
this.icon = 'codeTextSplitter.svg' | ||
this.category = 'Text Splitters' | ||
this.description = `Split documents based on language-specific syntax` | ||
this.baseClasses = [this.type, ...getBaseClasses(RecursiveCharacterTextSplitter)] | ||
this.inputs = [ | ||
{ | ||
label: 'Language', | ||
name: 'language', | ||
type: 'options', | ||
options: [ | ||
{ | ||
label: 'cpp', | ||
name: 'cpp' | ||
}, | ||
{ | ||
label: 'go', | ||
name: 'go' | ||
}, | ||
{ | ||
label: 'java', | ||
name: 'java' | ||
}, | ||
{ | ||
label: 'js', | ||
name: 'js' | ||
}, | ||
{ | ||
label: 'php', | ||
name: 'php' | ||
}, | ||
{ | ||
label: 'proto', | ||
name: 'proto' | ||
}, | ||
{ | ||
label: 'python', | ||
name: 'python' | ||
}, | ||
{ | ||
label: 'rst', | ||
name: 'rst' | ||
}, | ||
{ | ||
label: 'ruby', | ||
name: 'ruby' | ||
}, | ||
{ | ||
label: 'rust', | ||
name: 'rust' | ||
}, | ||
{ | ||
label: 'scala', | ||
name: 'scala' | ||
}, | ||
{ | ||
label: 'swift', | ||
name: 'swift' | ||
}, | ||
{ | ||
label: 'markdown', | ||
name: 'markdown' | ||
}, | ||
{ | ||
label: 'latex', | ||
name: 'latex' | ||
}, | ||
{ | ||
label: 'html', | ||
name: 'html' | ||
}, | ||
{ | ||
label: 'sol', | ||
name: 'sol' | ||
} | ||
] | ||
}, | ||
{ | ||
label: 'Chunk Size', | ||
name: 'chunkSize', | ||
type: 'number', | ||
default: 1000, | ||
optional: true | ||
}, | ||
{ | ||
label: 'Chunk Overlap', | ||
name: 'chunkOverlap', | ||
type: 'number', | ||
optional: true | ||
} | ||
] | ||
} | ||
async init(nodeData: INodeData): Promise<any> { | ||
const chunkSize = nodeData.inputs?.chunkSize as string | ||
const chunkOverlap = nodeData.inputs?.chunkOverlap as string | ||
const language = nodeData.inputs?.language as SupportedTextSplitterLanguage | ||
|
||
const obj = {} as RecursiveCharacterTextSplitterParams | ||
|
||
if (chunkSize) obj.chunkSize = parseInt(chunkSize, 10) | ||
if (chunkOverlap) obj.chunkOverlap = parseInt(chunkOverlap, 10) | ||
|
||
const splitter = RecursiveCharacterTextSplitter.fromLanguage(language, obj) | ||
|
||
return splitter | ||
} | ||
} | ||
module.exports = { nodeClass: CodeTextSplitter_TextSplitters } |
8 changes: 8 additions & 0 deletions
8
packages/components/nodes/textsplitters/CodeTextSplitter/codeTextSplitter.svg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
52 changes: 0 additions & 52 deletions
52
packages/components/nodes/textsplitters/LatexTextSplitter/LatexTextSplitter.ts
This file was deleted.
Oops, something went wrong.
6 changes: 0 additions & 6 deletions
6
packages/components/nodes/textsplitters/LatexTextSplitter/latexTextSplitter.svg
This file was deleted.
Oops, something went wrong.