Implementation:Infiniflow Ragflow LLM Constants

Knowledge Sources	Infiniflow_Ragflow
Domains	Frontend, LLM, Configuration
Last Updated	2026-02-12 06:00 GMT

Overview

Concrete comprehensive registry of 60+ supported LLM provider factory names and model type definitions for the RAGFlow frontend.

Description

The constants/llm.ts module defines the complete registry of supported LLM providers (OpenAI, Azure, Anthropic, Google, HuggingFace, Tongyi, DeepSeek, Ollama, etc.), model type enums (chat, embedding, image2text, speech2text, tts, reranking), and provider-specific configuration metadata.

Usage

Import these constants when building LLM provider selection UIs, model configuration forms, or any feature that needs to enumerate or validate LLM provider options.

Code Reference

Source Location

• Repository: Infiniflow_Ragflow
• File: web/src/constants/llm.ts
• Lines: 1-186

Signature

export enum LlmModelType {
  Chat = 'chat',
  Embedding = 'embedding',
  Image2Text = 'image2text',
  Speech2Text = 'speech2text',
  TTS = 'tts',
  Reranking = 'reranking',
}

export const LlmFactoryList: string[];  // 60+ provider names

Import

import { LlmModelType, LlmFactoryList } from '@/constants/llm';

I/O Contract

Inputs

Name	Type	Required	Description
—	—	—	Module-level constants; no inputs

Outputs

Name	Type	Description
LlmModelType	enum	All LLM model type identifiers
LlmFactoryList	string[]	All supported LLM provider names

Usage Examples

import { LlmModelType, LlmFactoryList } from '@/constants/llm';

// Filter to chat models only
const chatProviders = LlmFactoryList.filter(p => supportsChatModel(p));

Related Pages

• Environment:Infiniflow_Ragflow_Frontend_Node_Environment