OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Ragflow

Ragflow is an open-source retrieval-augmented generation engine and framework that combines retrieval and agent capabilities to provide a context layer for large language model applications.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Ragflow — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Ragflow when an LLM or agent application needs retrieval, knowledge compilation and context management as part of its architecture.

Who it is for

  • Developers building knowledge-grounded LLM applications
  • Teams creating agentic search or document-question-answering systems
  • Organizations that need a separately managed context layer for AI applications

Documented uses

  • Build a self-hosted knowledge-base question-answering system.
  • Ground agent responses in indexed organizational documents.
  • Create agentic search over a compiled knowledge collection.
  • Provide document-grounded LLM applications with managed retrieval context.
Before you choose

Requirements & limits

The project is publicly available as an open-source repository under the Apache-2.0 license. It is presented for self-hosted deployment and also references a cloud service.

  • Whether the project’s retrieval and context-layer approach matches the application architecture
  • Whether self-hosting or the referenced cloud service better fits the deployment model
  • Whether a Go-based open-source framework suits the development team

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Build RAGFlow Go Services from Source

Prepare the documented native dependencies and build RAGFlow's Go services locally.

Before you start

  • A Git installation.
  • The Go version specified in go.mod, currently Go 1.27.
  • Clang 20, LLD 20, CMake 4.0 or newer, and PCRE2 development files.
  • Python 3 with the requests and huggingface-hub packages.
  • Native libraries, model files, and tokenizer assets downloaded by the dependency script.

Steps

  1. Clone the repository and enter its directory: the command below followed by cd ragflow.

    Documented command
    git clone https://github.com/infiniflow/ragflow.git

  2. Create a Python virtual environment, install requests and huggingface-hub, and run ragflow_deps/download_deps.py to prepare native libraries and model resources.

  3. Build all Go services with the command below.

    Documented command
    bash build.sh --all

  4. If starting from outside the repository root, set DEEPDOC_MODEL_DIR to the absolute path of the prepared internal/rag/res/deepdoc resources.

Expected outcome

The documented native resources are prepared and the Go services are built from source.

Guide limitations

  • The evidence does not document the subsequent service-start procedure or a complete running deployment.
  • Node.js and npm are required only for React frontend development.
  • The source build depends on CGO and native static libraries.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
infiniflow/ragflow · Official homepage title · retained in its source language
How we review sourcesSuggest a correction