Get started with AI Search Open Platform

更新时间:
复制 MD 格式

AI Search Open Platform provides component-based services for intelligent search and Retrieval-Augmented Generation (RAG), including document parsing, document chunking, text embedding, retrieval, re-ranking, and large language model answer generation. The following example uses the text embedding service to show how to access the platform through the console, API, or SDKs.

Prerequisites

  • You have activated AI Search Open Platform. For more information, see Activate service.

  • To call the service via an API or SDK, you need an API key. For more information, see Manage API keys.

Try the service in the console

  1. Log on to the AI Search Open Platform console.

  2. Select the China (Shanghai) region, and then select the AI Search Open Platform service.

    Note
    • AI Search Open Platform is available only in the China (Shanghai) and Germany (Frankfurt) regions.

    • Users in the China (Hangzhou), China (Shenzhen), China (Beijing), China (Zhangjiakou), and China (Qingdao) regions can use a VPC endpoint to call AI Search Open Platform services across regions.

  3. In the navigation pane, choose Experience Center.

  4. For Service Category, select Text Embedding, and then select a specific vector service type.

  5. Use document to vectorize documents from a knowledge base. Use Query to vectorize search queries.

  6. Click Get Results to generate a text embedding for the input text.

    • Result: Shows the generated text embedding.

    • Result source code: Displays the response code. You can click Copy Code or Download File to save the code locally.

    • Sample code: Shows sample calls using curl and Python.

Call service via API or SDK

For more information, see text embedding and sparse text embedding.