|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/mastering-vector-databases-for-ai-applications-arabic/
课程评论：没有评论
**课程名称：** **精通向量数据库用于人工智能应用 (Mastering Vector Databases for AI Applications)** **授课讲师：** Mohammed Agoor 工程师 **课程概述：** 本课程将带您踏上一段探索向量数据库（如 Pinecone 和 Qdrant）的旅程，并通过端到端项目学习如何最大化利用它们来构建和部署语义搜索引擎和图像搜索引擎。您将从头开始学习，直至完成部署和测试。 **学习内容：** * **向量数据库基础：** 了解向量数据库及其优势。 * **数据嵌入与特征提取：** 学习文本数据的嵌入表示方法以及图像的特征提取技术。 * **Pinecone 向量数据库：** * 深入了解 Pinecone 及其云服务。 * 熟悉 Pinecone 定价估算器，以及项目 (project)、索引 (index)、集合 (collection)、Pod 大小 (pod size) 和 Pod 类型 (pod type) 等概念。 * 学习如何连接 Pinecone。 * 使用 Pinecone 构建端到端的语义搜索引擎。 * 掌握 Pinecone 的核心功能：upsert, delete, update, fetch, query。 * 使用 FastAPI 部署 Pinecone 语义搜索项目。 * 创建用于搜索、更新（索引、删除）的 API 端点。 * 使用 Pinecone 构建端到端的图像搜索引擎。 * 使用 FastAPI 部署 Pinecone 图像搜索项目。 * 创建用于搜索、更新（索引、删除）的 API 端点。 * **Qdrant 向量数据库：** * 了解 Qdrant 向量数据库，以及集群 (cluster) 和集合 (collection) 等概念。 * 熟悉 Qdrant 控制面板。 * 学习如何连接 Qdrant。 * 使用 Qdrant 构建端到端的语义搜索引擎。 * 使用 FastAPI 部署 Qdrant 语义搜索项目。 * 创建用于搜索、更新（索引、删除）的 API 端点。 * 使用 Qdrant 构建端到端的图像搜索引擎。 * 使用 FastAPI 部署 Qdrant 图像搜索项目。 * 创建用于搜索、更新（索引、删除）的 API 端点。 **目标学员：** 无论您是人工智能爱好者、开发人员还是数据科学家，本课程都将为您提供使用向量数据库进行人工智能应用开发所需的知识和实践技能。 **课程目标：** 通过参与本课程，您将能够从零开始构建、部署和测试语义搜索引擎和图像搜索引擎，从而提升您的人工智能技能水平。
Welcome to this courseThis course is Mastering Vector Databases for AI Applications in Arabic by Eng/Mohammed Agoor.In this course, we are going on a journey to discover vector databases like (pinecone, Qdrant) and how to get the best benefit from them via end-to-end projects for building semantic search engines and image search engines from scratch up to deployment and testing.What we learn here is a lot, We will start by discussing the vector databases and their benefits, review embeddings for text data and feature extraction for images, then we will dive into the pinecone vector database and use it for building an end-to-end semantic search engine and an end-to-end image search engine. Then we will dive into another great vector database (Qdrant) and use it also for the same projects.Are you ready to take your AI skills to the next level? This course is designed to equip you with the knowledge and hands-on experience needed to build semantic search engines and image search engines from scratch to deployment and testing.What You'll Learn:Through a series of engaging modules, you'll explore a wealth of concepts and practical techniques:Vector databases, and their benefits Review embeddings for text data and feature extraction for imagesPinecone vector database and its cloud servicePinecone pricing estimator, and (project, index, collection, pod size, pod type) definitionsConnecting pineconeSemantic search project using pineconePinecone functions (upsert, delete, update, fetch, query)Deployment of semantic search with pinecone project using FastAPIEndpoint to search for semantic search with pinecone projectEndpoint to update (index, delete) for semantic search with pinecone projectImage search project using pineconeDeployment of image search with pinecone project using FastAPIEndpoint to search for image search with pinecone projectEndpoint to update (index, delete) for image search with pinecone projectQdrant vector database, (cluster, collection) definitionsQdrant dashboardConnecting qdrantSemantic search project using qdrantDeployment of semantic search with qdrant project using FastAPIEndpoint to search for semantic search with qdrant projectEndpoint to update (index, delete) for semantic search with qdrant projectImage search project using qdrantDeployment of image search with qdrant project using FastAPIEndpoint to search for image search with qdrant projectEndpoint to update (index, delete) for semantic search with qdrant projectWhether you're an AI enthusiast, developer, or data scientist, this course will empower you with the knowledge and practical skills necessary to excel in utilizing vector databases for AI applications.Join us now and embark on an enriching learning journey that will set you on the path to mastering vector databases for cutting-edge AI projects.Enroll today!
