hwb96 / markdown-structure-splitterLinks
一个为RAG系统设计的Markdown文档工具,提供标题结构自动抽取和文档分割两大功能。完整保留文档层级结构,解决传统切分器丢失标题层级与破坏表格完整性的问题。A hierarchy-preserving Markdown document splitter for RAG (Retrieval-Augmented Generation) systems that maintains document structure and table integrity.
☆12Updated last year
Alternatives and similar repositories for markdown-structure-splitter
Users that are interested in markdown-structure-splitter are comparing it to the libraries listed below
Sorting:
- 基于 Dify + Langfuse 的自动化评估服务☆86Updated 7 months ago
- Convert files into markdown to help RAG or LLM understand, based on markitdown and MinerU, which could provide high quality pdf parser.☆130Updated 9 months ago
- LightRAG与GraphRAG在索引构建、检索测试中的耗时、模型请求次数、Token消耗金额、检索质量等方面进行对比☆154Updated last year
- Agentica: Effortlessly Build Intelligent, Reflective, and Collaborative Multimodal AI Agents! 构建智能的多模态AI Agent。☆230Updated last week
- Intelligent data apps and assets with LLMs☆179Updated 10 months ago
- dify's rag patch module☆277Updated 4 months ago
- A collection of RAG systems powered by LLM.☆208Updated 10 months ago
- PDF解析(文字,章节,表格,图片,参考),基于大模型(ChatGLM2-6B, RWKV)+langchain+streamlit的PDF问答,摘要,信息抽取☆216Updated 2 years ago
- MinerU API server☆84Updated last year
- A LLM RAG system runs on your laptop. 大模型检索增强生成系统,可以轻松部署在笔记本电脑上,实现本地知识库智能问答。企业级SaaS版本请访问:☆300Updated last month
- 通过paddle ocr实现pdf转markdown☆78Updated last year
- [ACL2025 demo track] ROGRAG: A Robustly Optimized GraphRAG Framework☆191Updated last month
- OpenSearch-SQL code☆163Updated 7 months ago
- MCP Agent Graph is a Multi-Agent System built on the principles of Context Engineering☆173Updated this week
- Dify 1.0 Plugin MCP HTTP with SSE or Streamable HTTP transport Tools☆179Updated 3 months ago
- DSPy中文文档☆47Updated last year
- 支持中文🇨🇳🇨🇳🇨🇳 的 microsoft/graphrag☆51Updated 9 months ago
- ☆46Updated 8 months ago
- A method and corresponding code for automatic description generation for Text-to-SQL☆102Updated 4 months ago
- gpt_server是一个用于生产级部署LLMs、Embedding、Reranker、ASR、TTS、文生图、图片编辑和文生视频的开源框架。☆243Updated 2 weeks ago
- E2M API, converting everything to markdown (LLM-friendly Format).☆138Updated last year
- ☆36Updated 2 months ago
- 基于LightRAG+Deepseek API框架的知识图谱测试☆58Updated 11 months ago
- 支持查询主流agent框架技术文档的MCP server(支持stdio和sse两种传输协议), 支持 langchain、llama-index、autogen、agno、openai-agents-sdk、mcp-doc、camel-ai 和 crew-ai☆151Updated 8 months ago
- langchain学习笔记,包含langchain源码解读、langchain中使用中文模型、langchain实例等。☆230Updated 2 years ago
- TianGong-AI-Unstructure☆69Updated 3 months ago
- 探索 LLM 在法律行业的应用潜力☆98Updated last year
- TorchV开源的解析代码仓库☆162Updated 2 months ago
- ✨🦋 illufly - 【幻蝶】基于记忆蒸馏、资料检索的自我进化智能体☆75Updated last month
- 本项目主要介绍prompt工程相关用例。包括模拟智能推荐客服系统构建和问答、思维链、自洽性、思维树等相关进阶demo,旨在帮助大家理解prompt。通过一份代码实现了同时支持多种大模型(如OpenAI、阿里通义千问等)并使用FastAPI对应用进行API封装。☆50Updated last year