MCP (Model Context Protocol) 서버는 전체 멀티모드 지원으로 문서의 처리 및 쿼리 디렉토리에 대한 포괄적 인 RAG (Retrieval-Augmented Generation) 기능을 제공합니다.

특징

-End-to-End Document Processing: 다중화 콘텐츠 추출 완료

• **Multimodal RAG **: 이미지, 테이블, 방정식 및 텍스트 처리 지원
• ** 배치 처리**: 여러 파일 유형의 전체 디렉토리 처리
• ** 고급 쿼리**: 순수한 텍스트와 multimodal enhanced 쿼리 -Multiple Query Modes: 하이브리드, 로컬, 글로벌, 네이티브, 믹스, 바이패스 모드 -Vision Processing: GPT-4V를 이용한 고급 이미지 분석
• Persistent Storage: RAG 인스턴스는 효율적인 쿼리에 대한 디렉토리당 유지

사용 가능한 도구

process_directory

Multimodal 지원과 포괄적인 RAG 색인을 위한 디렉토리에 있는 모든 파일 처리.

필수 매개 변수:

• directory_path: 파일을 처리하는 디렉토리에 경로
• api_key: LLM 및 embedding 기능을 위한 OpenAI API 열쇠

** 옵션 매개 변수 : **

• working_dir: RAG 스토리지에 대한 사용자 정의 작업 디렉토리

RAG Anything MCP Server

An MCP (Model Context Protocol) server that provides comprehensive RAG (Retrieval-Augmented Generation) capabilities for processing and querying directories of documents using the raganything library with full multimodal support.

Features

• End-to-End Document Processing: Complete document parsing with multimodal content extraction
• Multimodal RAG: Support for images, tables, equations, and text processing
• Batch Processing: Process entire directories with multiple file types
• Advanced Querying: Both pure text and multimodal-enhanced queries
• Multiple Query Modes: hybrid, local, global, naive, mix, and bypass modes
• Vision Processing: Advanced image analysis using GPT-4V
• Persistent Storage: RAG instances maintained per directory for efficient querying

Available Tools

process_directory

Process all files in a directory for comprehensive RAG indexing with multimodal support.

Required Parameters:

• directory_path: Path to the directory containing files to process
• api_key: OpenAI API key for LLM and embedding functions

Optional Parameters:

• working_dir: Custom working directory for RAG storage
• base_url: OpenAI API base URL (for custom endpoints)
• file_extensions: List of file extensions to process (default: [‘.pdf’, ‘.docx’, ‘.pptx’, ‘.txt’, ‘.md’])
• recursive: Process subdirectories (default: True)
• enable_image_processing: Enable image analysis (default: True)
• enable_table_processing: Enable table extraction (default: True)
• enable_equation_processing: Enable equation processing (default: True)
• max_workers: Concurrent processing workers (default: 4)

process_single_document

Process a single document with full multimodal analysis.

Required Parameters:

• file_path: Path to the document to process
• api_key: OpenAI API key

Optional Parameters:

• working_dir: Custom working directory for RAG storage
• base_url: OpenAI API base URL
• output_dir: Output directory for parsed content
• parse_method: Document parsing method (default: “auto”)
• enable_image_processing: Enable image analysis (default: True)
• enable_table_processing: Enable table extraction (default: True)
• enable_equation_processing: Enable equation processing (default: True)

query_directory

Pure text query against processed documents using LightRAG.

Parameters:

• directory_path: Path to the processed directory
• query: The question to ask about the documents
• mode: Query mode - “hybrid”, “local”, “global”, “naive”, “mix”, or “bypass” (default: “hybrid”)

query_with_multimodal_content

Enhanced query with additional multimodal content (tables, equations, etc.).

Parameters:

• directory_path: Path to the processed directory
• query: The question to ask
• multimodal_content: List of multimodal content dictionaries
• mode: Query mode (default: “hybrid”)

Example multimodal_content:

[
  {