Before You Start

Overview

Welcome to KooSearch, a leading retrieval-augmented generation (RAG) solution that integrates leading search models, a high-performance GaussDB vector database provided by the Cloud Search Service (CSS), and LLM models of your choice. KooSearch supports both structured and unstructured data, helping enterprises effortlessly build their own intelligent search and Q&A services. As a promising way to mitigate LLM hallucination, RAG helps LLMs generate more accurate, reliable, and secure answers. KooSearch offers a fully managed, distributed search service with LLM-powered content generation, delivering a seamless enterprise search experience.

This document provides KooSearch API description, syntax, parameters, and examples.

API Calling

KooSearch supports Representational State Transfer (REST) APIs, allowing you to call APIs using HTTPS.

For details, see Calling APIs.

Endpoints

An endpoint is the request address for calling an API. Endpoints vary depending on services and regions. For the endpoints of all services, see Regions and Endpoints.

Concepts

• Account

  An account is created upon successful registration with the cloud system. The account has full access permissions for all of its cloud services and resources. It can be used to reset user passwords and grant user permissions. The account is a payment entity. For security purposes, do not directly use the account to perform routine management. Instead, create IAM users and grant them permissions for routine management.

• User

  An IAM user is created under an account to use cloud services. Each user has its own identity credentials (password and access keys).

  API authentication requires information such as the account name, username, and password.

• Region

  A region is a geographic area in which cloud resources are deployed. Availability zones (AZs) in the same region can communicate with each other over an intranet, while AZs in different regions are isolated from each other. By creating cloud resources in different regions, you can design applications to better meet customer requirements and comply with local laws and regulations.

• AZ

  An AZ comprises of one or multiple physical data centers equipped with independent ventilation, fire, water, and electricity facilities. Computing, network, storage, and other resources in an AZ are logically divided into multiple clusters. AZs within a region are interconnected using high-speed optical fibers to allow you to build cross-AZ high-availability systems.

• Project

  A project corresponds to a region. Default projects are defined to group and physically isolate resources (including compute, storage, and network resources) between different regions. Users can be granted permissions in a default project to access all resources under their accounts in the region associated with the project. For more refined access control, create subprojects under a project and purchase resources in the subprojects. Users can then be assigned permissions to access only specific resources in the subprojects.

• Checkpoint: When an application consumes data, the latest SN of the consumed data is recorded as a checkpoint. When the data is consumed again, the consumption can be continued based on this checkpoint.
• APP: Multiple applications can access data in the same stream. Checkpoints generated for each application are used to record the consumed data in the stream by each application.
• Enterprise Project

  Enterprise projects group and manage resources across regions. Resources in enterprise projects are logically isolated from each other. An enterprise project can contain resources of multiple regions, and resources can be added to or removed from enterprise projects.

  For details about how to obtain enterprise project IDs and features, see Enterprise Management Service User Guide.