Dify
ActiveDescription
Dify is an open-source LLM application development platform with a visual agent orchestration interface, supporting workflows, knowledge bases, and multiple models.
Key Features
- Visual workflow orchestration — Drag-and-drop canvas for building AI workflows with branching, loops, and parallel nodes
- Multi-model integration — Seamless support for hundreds of LLMs (GPT, Llama, Mistral, etc.) including OpenAI-compatible APIs
- RAG pipeline — End-to-end document ingestion (PDF/PPT), vector storage, and retrieval-augmented generation
- Agent capabilities — Function Calling and ReAct agent modes with pre-built and custom tool support
- Prompt IDE — Visual prompt editor with multi-model comparison and add-on features like text-to-speech
- Observability integration — Built-in support for Opik, Langfuse, and Arize Phoenix monitoring tools
Use Cases
💡 Build enterprise customer service bots combining knowledge base retrieval with multi-turn dialogue
💡 Create document Q&A systems with RAG-based knowledge retrieval after uploading internal documents
💡 Develop data analysis agents that automate structured analysis tasks on CSV/databases via workflows
💡 Set up a multi-model evaluation platform to test different LLM output quality in a single interface
💡 Prototype internal AI applications to validate LLM workflow feasibility before production investment
Tags
Categories
Quick Start
# Clone the repo and enter the docker directory
git clone https://github.com/langgenius/dify.git
cd dify/docker
# Copy environment config
cp .env.example .env
# Start all services
docker compose up -d
# Visit http://localhost/install to initialize