{"id":16651,"date":"2024-12-11T12:26:01","date_gmt":"2024-12-11T20:26:01","guid":{"rendered":"https:\/\/www.couchbase.com\/blog\/?p=16651"},"modified":"2025-06-13T16:36:26","modified_gmt":"2025-06-13T23:36:26","slug":"couchbase-dify-ai-integration","status":"publish","type":"post","link":"https:\/\/www.couchbase.com\/blog\/couchbase-dify-ai-integration\/","title":{"rendered":"Couchbase + Dify: High-Power Vector Capabilities for AI Workflows"},"content":{"rendered":"

We’re excited to announce the new integration between <\/span>Couchbase<\/span><\/a> and <\/span>Dify.ai<\/span><\/a>, bringing Couchbase’s robust vector database capabilities into Dify\u2019s streamlined LLMops ecosystem. Dify empowers teams with a no-code solution to build, manage, and deploy AI-driven workflows efficiently. Now, with Couchbase support, users can leverage Couchbase\u2019s high-performance vector storage for rapid, accurate knowledge retrieval within their LLM-powered applications.<\/span><\/p>\n

Dify.ai is an innovative platform that simplifies the process of building AI-native applications. It provides developers with a comprehensive suite of tools for prompt engineering, model fine-tuning, and application deployment, making it easier than ever to harness the power of large language models (LLMs) in practical applications.<\/span><\/p>\n

In the following sections, we’ll explore some details of this integration and show how it can revolutionize building AI-native applications with Couchbase and Dify.ai.<\/span><\/p>\n

Installing Dify with Couchbase<\/span><\/h3>\n

The following instructions are based on <\/span>Dify\u2019s self-hosted Docker Compose installation guide<\/span><\/a>. Ensure the prerequisites on that guide are met.<\/span><\/p>\n

    \n
  1. \n
      \n
    1. \n
        \n
      1. Clone the Dify repository<\/span>\n
        git clone https:\/\/github.com\/langgenius\/dify.git<\/pre>\n<\/li>\n
      2. Navigate to the Docker directory and configure the environment<\/span>\n
        cd dify\/docker\r\ncp .env.example .env<\/pre>\n
        IMPORTANT –<\/b> in the duplicated docker\/.env<\/code> file, set:<\/p>\n
        VECTOR_STORE=couchbase<\/pre>\n<\/li>\n
      3. Launch Dify<\/span>\n
        docker compose up -d<\/pre>\n<\/li>\n
      4. Access Dify<\/span><\/span>Access administrator initialization page to set up the admin account:\n
        # Local environment\r\nhttps:\/\/localhost\/install\r\n\r\n# Server environment\r\nhttps:\/\/your_server_ip\/install<\/pre>\n
        Dify web interface address:<\/p>\n
        # Local environment\r\nhttps:\/\/localhost\r\n\r\n# Server environment\r\nhttps:\/\/your_server_ip<\/pre>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n
        Instructions for upgrading Dify versions can be found <\/span>here<\/span><\/a>, and more details about Dify docker deployment can be found in the <\/span>docker README<\/span><\/a>.<\/span><\/p>\n
        Adding knowledge and generating embeddings<\/span><\/h3>\n
        An <\/span>embedding<\/span><\/i> is a vector representation of text, enabling the “Knowledge” feature to understand and process the content.<\/span><\/p>\n
          \n
        1. \n
            \n
          1. Access the Dify web interface<\/span><\/li>\n
          2. Add model provider. This is <\/span>required<\/b> to generate embeddings:<\/span>\n