Jump to content

Connect SuperML | Leeroopedia MCP: Equip your AI agents with best practices, code verification, and debugging knowledge. Powered by Leeroo — building Organizational Superintelligence. Contact us at founders@leeroo.com.

Implementation:Infiniflow Ragflow Knowledge Constants

From Leeroopedia
Revision as of 11:21, 16 February 2026 by Admin (talk | contribs) (Auto-imported from implementations/Infiniflow_Ragflow_Knowledge_Constants.md)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Knowledge Sources
Domains Frontend, Knowledge_Base, Configuration
Last Updated 2026-02-12 06:00 GMT

Overview

Concrete knowledge base enums and preset configuration values for chunk methods, parser types, and retrieval modes in the RAGFlow frontend.

Description

The constants/knowledge.ts module defines the ChunkMethod enum (naive, manual, qa, table, paper, book, laws, presentation, picture, one, knowledge_graph, tag, email, audio, resume), default parser configurations per chunk method, and retrieval mode constants.

Usage

Import these constants when building dataset configuration forms, parser selection UIs, or any feature that needs to reference available chunking methods and their default settings.

Code Reference

Source Location

Signature

export enum ChunkMethod {
  Naive = 'naive',
  Manual = 'manual',
  QA = 'qa',
  Table = 'table',
  Paper = 'paper',
  Book = 'book',
  // ... additional methods
}

export const defaultParserConfig: Record<ChunkMethod, object>;

Import

import { ChunkMethod, defaultParserConfig } from '@/constants/knowledge';

I/O Contract

Inputs

Name Type Required Description
Module-level constants; no inputs

Outputs

Name Type Description
ChunkMethod enum All available chunking method identifiers
defaultParserConfig Record Default config per chunk method

Usage Examples

import { ChunkMethod, defaultParserConfig } from '@/constants/knowledge';

const config = defaultParserConfig[ChunkMethod.Naive];

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment