Samge0/ragflow-upload

自动批量上传并解析文档至 RagFlow 知识库，省去手动操作，提升效率。

What it solves

This tool addresses the limitations of the default RAGFlow knowledge base upload interface, which often restricts the number of files that can be uploaded at once. It automates the process of importing large volumes of documents from local directories and subdirectories into a RAGFlow knowledge base, eliminating the need for manual batching and waiting.

How it works

It operates as a client (available as a standalone executable or Python script) that interacts with the RAGFlow API/SDK. The tool scans a specified local directory for supported file types (such as .md, .txt, .pdf, .docx), uploads them to a target knowledge base, and triggers the parsing and chunking process. It also supports custom metadata via accompanying .meta.json files.

Who it’s for

Users of RAGFlow (v0.26.2+) who need to migrate large datasets or local archives—such as a collection of notes or technical manuals—into their AI knowledge base efficiently.

Highlights

  • Automated Batching: Automatically traverses directories to upload and parse documents in bulk.
  • Progress Tracking: Monitors parsing progress in real-time and maintains a state record to skip already processed files if interrupted.
  • Metadata Support: Allows attaching custom metadata to documents via JSON files.
  • Flexible Chunking: Supports various RAGFlow chunking methods including naive, general, paper, book, laws, presentation, manual, and qa.
  • Standalone Client: Provides pre-compiled binaries for Windows, macOS, and Linux for users who do not want to run Python code.

Related

  • Project
    infiniflow/ragflow

    An open-source RAG engine that combines deep document understanding and agentic capabilities to create a high-fidelity context layer for LLMs using complex unstructured data.

  • Project
    pingcap/autoflow

    AutoFlow is an open-source Graph RAG knowledge base tool that enables users to create conversational search experiences using a built-in website crawler and TiDB Vector.

  • Project
    Kaggle/kagglehub

    A Python library for programmatically downloading, uploading, and loading Kaggle datasets, models, and competition resources into data science frameworks.

  • Project
    langflow-ai/openrag

    An intelligent agent-powered document search platform that enables users to upload, process, and query documents through a chat interface using RAG.

  • Project
    OpenDCAI/DataFlow

    DataFlow is an open‑source Python framework that lets you build, run, and share low‑code pipelines for generating, cleaning, and evaluating LLM training data. It provides a library of reusable operators, a visual WebUI, an AI‑assistant for auto‑creating pipelines, and a Ray‑based distributed execution layer.