跳到主要内容

ai-rag

ai-rag 插件为大语言模型提供了检索增强生成（RAG）能力。它支持从外部数据源高效检索相关文档或信息，用于增强大语言模型的响应，从而提高生成输出的准确性和上下文相关性。

该插件支持使用 Azure OpenAI 和 Azure AI Search 服务来生成嵌入和执行向量搜索。

示例​

要跟随示例进行操作，请先创建一个 Azure 账户 并完成以下步骤：

将 API Key 和端点保存到环境变量中：

# 替换为你的配置值

AZ_OPENAI_DOMAIN=https://ai-plugin-developer.openai.azure.com
AZ_OPENAI_API_KEY=YOUR_AZURE_OPENAI_API_KEY
AZ_CHAT_ENDPOINT=${AZ_OPENAI_DOMAIN}/openai/deployments/gpt-4o/chat/completions?api-version=2024-02-15-preview
AZ_EMBEDDING_MODEL=text-embedding-3-large
AZ_EMBEDDINGS_ENDPOINT=${AZ_OPENAI_DOMAIN}/openai/deployments/${AZ_EMBEDDING_MODEL}/embeddings?api-version=2023-05-15

AZ_AI_SEARCH_SVC_DOMAIN=https://ai-plugin-developer.search.windows.net
AZ_AI_SEARCH_KEY=YOUR_AZURE_AI_SEARCH_API_KEY
AZ_AI_SEARCH_INDEX=vectest
AZ_AI_SEARCH_ENDPOINT=${AZ_AI_SEARCH_SVC_DOMAIN}/indexes/${AZ_AI_SEARCH_INDEX}/docs/search?api-version=2024-07-01

集成 Azure 以生成 RAG 增强响应​

以下示例演示了如何使用 ai-proxy 插件代理请求到 Azure OpenAI 大语言模型，并使用 ai-rag 插件生成嵌入并执行向量搜索，以增强大语言模型的响应。

创建路由如下：

curl "http://127.0.0.1:9180/apisix/admin/routes" -X PUT \
  -H "X-API-KEY: ${ADMIN_API_KEY}" \
  -d '{
  "id": "ai-rag-route",
  "uri": "/rag",
  "plugins": {
    "ai-rag": {
      "embeddings_provider": {
        "azure_openai": {
          "endpoint": "'"$AZ_EMBEDDINGS_ENDPOINT"'",
          "api_key": "'"$AZ_OPENAI_API_KEY"'"
        }
      },
      "vector_search_provider": {
        "azure_ai_search": {
          "endpoint": "'"$AZ_AI_SEARCH_ENDPOINT"'",
          "api_key": "'"$AZ_AI_SEARCH_KEY"'"
        }
      }
    },
    "ai-proxy": {
      "provider": "openai",
      "auth": {
        "header": {
          "api-key": "'"$AZ_OPENAI_API_KEY"'"
        }
      },
      "model": "gpt-4o",
      "override": {
        "endpoint": "'"$AZ_CHAT_ENDPOINT"'"
      }
    }
  }
}'

向该路由发送一个 POST 请求，请求体中包含向量字段名称、嵌入模型维度和输入提示词：

curl "http://127.0.0.1:9080/rag" -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "ai_rag":{
      "vector_search":{
        "fields":"contentVector"
      },
      "embeddings":{
        "input":"Which Azure services are good for DevOps?",
        "dimensions":1024
      }
    }
  }'

你应该收到类似于以下的 HTTP/1.1 200 OK 响应：

{
  "choices": [
    {
      "content_filter_results": {
        ...
      },
      "finish_reason": "length",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "Here is a list of Azure services categorized along with a brief description of each based on the provided JSON data:\n\n### Developer Tools\n- **Azure DevOps**: A suite of services that help you plan, build, and deploy applications, including Azure Boards, Azure Repos, Azure Pipelines, Azure Test Plans, and Azure Artifacts.\n- **Azure DevTest Labs**: A fully managed service to create, manage, and share development and test environments in Azure, supporting custom templates, cost management, and integration with Azure DevOps.\n\n### Containers\n- **Azure Kubernetes Service (AKS)**: A managed container orchestration service based on Kubernetes, simplifying deployment and management of containerized applications with features like automatic upgrades and scaling.\n- **Azure Container Instances**: A serverless container runtime to run and scale containerized applications without managing the underlying infrastructure.\n- **Azure Container Registry**: A fully managed Docker registry service to store and manage container images and artifacts.\n\n### Web\n- **Azure App Service**: A fully managed platform for building, deploying, and scaling web apps, mobile app backends, and RESTful APIs with support for multiple programming languages.\n- **Azure SignalR Service**: A fully managed real-time messaging service to build and scale real-time web applications.\n- **Azure Static Web Apps**: A serverless hosting service for modern web applications using static front-end technologies and serverless APIs.\n\n### Compute\n- **Azure Virtual Machines**: Infrastructure-as-a-Service (IaaS) offering for deploying and managing virtual machines in the cloud.\n- **Azure Functions**: A serverless compute service to run event-driven code without managing infrastructure.\n- **Azure Batch**: A job scheduling service to run large-scale parallel and high-performance computing (HPC) applications.\n- **Azure Service Fabric**: A platform to build, deploy, and manage scalable and reliable microservices and container-based applications.\n- **Azure Quantum**: A quantum computing service to build and run quantum applications.\n- **Azure Stack Edge**: A managed edge computing appliance to run Azure services and AI workloads on-premises or at the edge.\n\n### Security\n- **Azure Bastion**: A fully managed service providing secure and scalable remote access to virtual machines.\n- **Azure Security Center**: A unified security management service to protect workloads across Azure and on-premises infrastructure.\n- **Azure DDoS Protection**: A cloud-based service to protect applications and resources from distributed denial-of-service (DDoS) attacks.\n\n### Databases\n",
        "role": "assistant"
      }
    }
  ],
  "created": 1740625850,
  "id": "chatcmpl-B54gQdumpfioMPIybFnirr6rq9ZZS",
  "model": "gpt-4o-2024-05-13",
  "object": "chat.completion",
  "prompt_filter_results": [
    {
      "prompt_index": 0,
      "content_filter_results": {
        ...
      }
    }
  ],
  "system_fingerprint": "fp_65792305e4",
  "usage": {
    ...
  }
}