Priyanka Makhija
Menjadi anggota sejak 2024
Diamond League
3193 poin
Menjadi anggota sejak 2024
Demonstrate the ability to create and deploy deterministic virtual agents using Dialgflow CX and augment responses by grounding results on your own data integrating with Vertex AI Agent Builder data stores and leveraging Gemini for summarizations. You will use the following technologies and Google Cloud services: Vertex AI Agent Builder Dialogflow CX Gemini
Demonstrate the ability to create and deploy generative virtual agents with natural language using Vertex AI Agent Builder and augment responses by integrating Gemini responses with third party APIs and your own data stores You will use the following technologies and Google Cloud services: Vertex AI Agent Builder Gemini Cloud Functions
In this Quest, the experienced user of Google Cloud will learn how to describe and launch cloud resources with Terraform, an open source tool that codifies APIs into declarative configuration files that can be shared amongst team members, treated as code, edited, reviewed, and versioned. In these nine hands-on labs, you will work with example templates and understand how to launch a range of configurations, from simple servers, through full load-balanced applications.
This Quest is most suitable for those working in a technology or finance role who are responsible for managing Google Cloud costs. You’ll learn how to set up a billing account, organize resources, and manage billing access permissions. In the hands-on labs, you'll learn how to view your invoice, track your Google Cloud costs with Billing reports, analyze your billing data with BigQuery or Google Sheets, and create custom billing dashboards with Looker Studio. References made to links in the videos can be accessed in this Additional Resources document.
This course on Integrate Vertex AI Search and Conversation into Voice and Chat Apps is composed of a set of labs to give you a hands on experience to interacting with new Generative AI technologies. You will learn how to create end-to-end search and conversational experiences by following examples. These technologies complement predefined intent-based chat experiences created in Dialogflow with LLM-based, generative answers that can be based on your own data. Also, they allow you to porvide enterprise-grade search experiences for internal and external websites to search documents, structure data and public websites.
In this course, you'll use text embeddings for tasks like classification, outlier detection, text clustering and semantic search. You'll combine semantic search with the text generation capabilities of an LLM to build Retrieval Augmented Generation (RAG) solutions, such as for question-answering systems, using Google Cloud's Vertex AI and Google Cloud databases.
This course explores Google Cloud technologies to create and generate embeddings. Embeddings are numerical representations of text, images, video and audio, and play a pivotal role in many tasks that involve the identification of similar items, like Google searches, online shopping recommendations, and personalized music suggestions. Specifically, you’ll use embeddings for tasks like classification, outlier detection, clustering and semantic search. You’ll combine semantic search with the text generation capabilities of an LLM to build Retrieval Augmented Generation (RAG) systems and question-answering solutions, on your own proprietary data using Google Cloud’s Vertex AI.
Menjelajahi teknologi, alat, dan aplikasi penelusuran yang didukung AI dalam kursus ini. Mempelajari penelusuran semantik dengan memanfaatkan embedding vektor, penelusuran campuran yang menggabungkan pendekatan semantik dan kata kunci, serta Retrieval-Augmented Generation (RAG) yang meminimalkan halusinasi AI sebagai agen AI yang di-grounding. Mendapatkan pengalaman praktis dengan Vertex AI Vector Search untuk membangun mesin telusur yang cerdas.
Kursus ini menjelaskan cara membuat model keterangan gambar menggunakan deep learning. Anda akan belajar tentang berbagai komponen model keterangan gambar, seperti encoder dan decoder, serta cara melatih dan mengevaluasi model. Pada akhir kursus ini, Anda akan dapat membuat model keterangan gambar Anda sendiri dan menggunakannya untuk menghasilkan teks bagi gambar.
Kursus ini memperkenalkan Anda pada arsitektur Transformer dan model Representasi Encoder Dua Arah dari Transformer (Bidirectional Encoder Representations from Transformers atau BERT). Anda akan belajar tentang komponen utama arsitektur Transformer, seperti mekanisme self-attention, dan cara penggunaannya untuk membangun model BERT. Anda juga akan belajar tentang berbagai tugas yang dapat memanfaatkan BERT, seperti klasifikasi teks, menjawab pertanyaan, dan inferensi natural language. Kursus ini diperkirakan memakan waktu sekitar 45 menit untuk menyelesaikannya.
Kursus ini memberi Anda sinopsis tentang arsitektur encoder-decoder, yang merupakan arsitektur machine learning yang canggih dan umum untuk tugas urutan-ke-urutan seperti terjemahan mesin, ringkasan teks, dan tanya jawab. Anda akan belajar tentang komponen utama arsitektur encoder-decoder serta cara melatih dan menyalurkan model ini. Dalam panduan lab yang sesuai, Anda akan membuat kode pada penerapan simpel arsitektur encoder-decoder di TensorFlow untuk pembuatan puisi dari awal.
Kursus ini membekali para praktisi machine learning dengan alat, teknik, dan praktik terbaik penting untuk mengevaluasi model AI generatif dan prediktif. Evaluasi model adalah disiplin ilmu yang sangat penting untuk memastikan sistem ML memberikan hasil yang andal, akurat, dan berperforma tinggi dalam produksi. Peserta akan mendapatkan pemahaman yang mendalam mengenai berbagai metrik evaluasi, metodologi, dan penerapannya yang sesuai di berbagai jenis model dan tugas. Kursus ini akan berfokus pada tantangan unik yang dibuat oleh model AI generatif dan memberikan strategi untuk mengatasinya secara efektif. Dengan memanfaatkan platform Vertex AI di Google Cloud, para peserta akan belajar cara mengimplementasikan proses evaluasi yang kuat untuk melakukan pemilihan, pengoptimalan, dan pemantauan berkelanjutan pada model.
Kursus ini memperkenalkan model difusi, yaitu kelompok model machine learning yang belakangan ini menunjukkan potensinya dalam ranah pembuatan gambar. Model difusi mengambil inspirasi dari fisika, khususnya termodinamika. Dalam beberapa tahun terakhir, model difusi menjadi populer baik di dunia industri maupun penelitian. Model difusi mendasari banyak alat dan model pembuatan gambar yang canggih di Google Cloud. Kursus ini memperkenalkan Anda pada teori yang melandasi model difusi dan cara melatih serta men-deploy-nya di Vertex AI.
Dalam kursus ini Anda akan diperkenalkan dengan mekanisme atensi, yakni teknik efektif yang membuat jaringan neural berfokus pada bagian tertentu urutan input. Anda akan mempelajari cara kerja atensi, cara penggunaannya untuk meningkatkan performa berbagai tugas machine learning, termasuk terjemahan mesin, peringkasan teks, dan menjawab pertanyaan.
Ini adalah kursus pengantar pembelajaran mikro yang dimaksudkan untuk menjelaskan responsible AI, alasan pentingnya responsible AI, dan cara Google mengimplementasikan responsible AI dalam produknya. Kursus ini juga memperkenalkan 7 prinsip AI Google.
In the last installment of the Dataflow course series, we will introduce the components of the Dataflow operational model. We will examine tools and techniques for troubleshooting and optimizing pipeline performance. We will then review testing, deployment, and reliability best practices for Dataflow pipelines. We will conclude with a review of Templates, which makes it easy to scale Dataflow pipelines to organizations with hundreds of users. These lessons will help ensure that your data platform is stable and resilient to unanticipated circumstances.
This course is part 1 of a 3-course series on Serverless Data Processing with Dataflow. In this first course, we start with a refresher of what Apache Beam is and its relationship with Dataflow. Next, we talk about the Apache Beam vision and the benefits of the Beam Portability framework. The Beam Portability framework achieves the vision that a developer can use their favorite programming language with their preferred execution backend. We then show you how Dataflow allows you to separate compute and storage while saving money, and how identity, access, and management tools interact with your Dataflow pipelines. Lastly, we look at how to implement the right security model for your use case on Dataflow.
In this course you will get hands-on in order to work through real-world challenges faced when building streaming data pipelines. The primary focus is on managing continuous, unbounded data with Google Cloud products.
In this intermediate course, you will learn to design, build, and optimize robust batch data pipelines on Google Cloud. Moving beyond fundamental data handling, you will explore large-scale data transformations and efficient workflow orchestration, essential for timely business intelligence and critical reporting. Get hands-on practice using Dataflow for Apache Beam and Serverless for Apache Spark (Dataproc Serverless) for implementation, and tackle crucial considerations for data quality, monitoring, and alerting to ensure pipeline reliability and operational excellence. A basic knowledge of data warehousing, ETL/ELT, SQL, Python, and Google Cloud concepts is recommended.
While the traditional approaches of using data lakes and data warehouses can be effective, they have shortcomings, particularly in large enterprise environments. This course introduces the concept of a data lakehouse and the Google Cloud products used to create one. A lakehouse architecture uses open-standard data sources and combines the best features of data lakes and data warehouses, which addresses many of their shortcomings.
Selesaikan badge keahlian tingkat menengah Membangun Data Warehouse dengan BigQuery untuk menunjukkan keterampilan Anda dalam hal berikut: menggabungkan data untuk membuat tabel baru, memecahkan masalah penggabungan, menambahkan data dengan union, membuat tabel berpartisi tanggal, serta menggunakan JSON, array, dan struct di BigQuery. Badge keahlian adalah badge digital eksklusif yang diberikan oleh Google Cloud sebagai pengakuan atas kemahiran Anda dalam menggunakan produk dan layanan Google Cloud serta menguji kemampuan Anda dalam menerapkan pengetahuan di lingkungan yang interaktif. Selesaikan kursus badge keahlian ini dan challenge lab penilaian akhir, untuk menerima badge keahlian yang dapat Anda bagikan dengan jaringan Anda.
This course explores the implementation of data load and transformation pipelines for a BigQuery Data Warehouse using Dataproc.
Looking to build or optimize your data warehouse? Learn best practices to Extract, Transform, and Load your data into Google Cloud with BigQuery. In this series of interactive labs you will create and optimize your own data warehouse using a variety of large-scale BigQuery public datasets. BigQuery is Google's fully managed, NoOps, low cost analytics database. With BigQuery you can query terabytes and terabytes of data without having any infrastructure to manage or needing a database administrator. BigQuery uses SQL and can take advantage of the pay-as-you-go model. BigQuery allows you to focus on analyzing data to find meaningful insights. Looking for a hands on challenge lab to demonstrate your skills and validate your knowledge? On completing this quest, enroll in and finish the additional challenge lab at the end of this quest to receive an exclusive Google Cloud digital badge.
This course helps learners create a study plan for the PDE (Professional Data Engineer) certification exam. Learners explore the breadth and scope of the domains covered in the exam. Learners assess their exam readiness and create their individual study plan.