APIs, Blog, Engineering and Scripts - Customer Contact Central

Build an image search engine with Amazon Kendra and Amazon Rekognition

AWS Machine Learning

MAY 5, 2023

To address the problems associated with complex searches, this post describes in detail how you can achieve a search engine that is capable of searching for complex images by integrating Amazon Kendra and Amazon Rekognition. A Python script is used to aid in the process of uploading the datasets and generating the manifest file.

Engineering

Engineering APIs Scripts Enterprise

Amazon SageMaker model parallel library now accelerates PyTorch FSDP workloads by up to 20%

AWS Machine Learning

DECEMBER 22, 2023

In particular, we cover the SMP library’s new simplified user experience that builds on open source PyTorch Fully Sharded Data Parallel (FSDP) APIs, expanded tensor parallel functionality that enables training models with hundreds of billions of parameters, and performance optimizations that reduce model training time and cost by up to 20%.

Scripts

Scripts APIs Engineering Finance

Accelerate ML workflows with Amazon SageMaker Studio Local Mode and Docker support

AWS Machine Learning

APRIL 23, 2024

You can run the script by choosing Run in Code Editor or using the CLI in a JupyterLab terminal. ipynb notebook in blog/pytorch_cnn_cifar10. The only way to access and interact with Docker images is via the exposed Docker API operations. LCCs are scripts that SageMaker runs during events like space creation. Python 3.10

Scripts

Scripts APIs Engineering Feedback

Webinars

How to Optimize Call Monitoring: Automate QA and Elevate Customer Experience

MORE WEBINARS

Modernizing data science lifecycle management with AWS and Wipro

AWS Machine Learning

JANUARY 5, 2024

Wipro further accelerated their ML model journey by implementing Wipro’s code accelerators and snippets to expedite feature engineering, model training, model deployment, and pipeline creation. Wipro has used the input filter and join functionality of SageMaker batch transformation API.

Management

Management APIs Engineering Government

How Sportradar used the Deep Java Library to build production-scale ML platforms for increased performance and efficiency

AWS Machine Learning

APRIL 19, 2023

Our data scientists train the model in Python using tools like PyTorch and save the model as PyTorch scripts. Ideally, we instead want to load the model PyTorch scripts, extract the features from model input, and run model inference entirely in Java. They use the DJL PyTorch engine to initialize the model predictor.

Engineering

Engineering APIs Scripts Education

Run machine learning inference workloads on AWS Graviton-based instances with Amazon SageMaker

AWS Machine Learning

NOVEMBER 14, 2022

You need to complete three steps to deploy your model: Create a SageMaker model: This will contain, among other parameters, the information about the model file location, the container that will be used for the deployment, and the location of the inference script. (If The inference script URI is needed in the INFERENCE_SCRIPT_S3_LOCATION.

Scripts

Scripts APIs Best practices Engineering

How Earth.com and Provectus implemented their MLOps Infrastructure with Amazon SageMaker

AWS Machine Learning

JUNE 27, 2023

This blog post is co-written with Marat Adayev and Dmitrii Evstiukhin from Provectus. Earth.com didn’t have an in-house ML engineering team, which made it hard to add new datasets featuring new species, release and improve new models, and scale their disjointed ML system. Endpoints had to be deployed manually as well.

Engineering

Engineering APIs Scripts Entertainment

Build ML features at scale with Amazon SageMaker Feature Store using data from Amazon Redshift

AWS Machine Learning

AUGUST 17, 2023

Perform feature engineering and ingest features into SageMaker Feature Store In this section, we present the steps for all three options to perform feature engineering and ingest processed features into SageMaker Feature Store. Here is one end-to-end data flow in the scenario of PLACE feature engineering.

APIs

APIs Engineering Scripts Analytics

Optimize AWS Inferentia utilization with FastAPI and PyTorch models on Amazon EC2 Inf1 & Inf2 instances

AWS Machine Learning

JULY 24, 2023

If the model changes on the server side, the client has to know and change its API call to the new endpoint accordingly. We demonstrate the use of Neuron Top at the end of this blog. Clone the Github repository The GitHub repo provides all the scripts necessary to deploy models using FastAPI on NeuronCores on AWS Inferentia instances.

Scripts

Scripts APIs Engineering Best practices

Simplify access to internal information using Retrieval Augmented Generation and LangChain Agents

AWS Machine Learning

SEPTEMBER 14, 2023

Amazon API Gateway hosts a REST API with various endpoints to handle user requests that are authenticated using Amazon Cognito. Finally, the response is sent back to the user via a HTTPs request through the Amazon API Gateway REST API integration response. The web application front-end is hosted on AWS Amplify.

APIs

APIs Healthcare Scripts Engineering

Best practices to build generative AI applications on AWS

AWS Machine Learning

MARCH 14, 2024

We provide an overview of key generative AI approaches, including prompt engineering, Retrieval Augmented Generation (RAG), and model customization. Building large language models (LLMs) from scratch or customizing pre-trained models requires substantial compute resources, expert data scientists, and months of engineering work.

Best practices

Best practices Engineering Chatbots Enterprise

Connecting Amazon Redshift and RStudio on Amazon SageMaker

AWS Machine Learning

DECEMBER 29, 2022

Users can also interact with data with ODBC, JDBC, or the Amazon Redshift Data API. In this blog post, we will show you how to use both of these services together to efficiently perform analysis on massive data sets in the cloud while addressing the challenges mentioned above. Solution overview.

APIs

APIs Engineering Analytics Scripts

Amazon SageMaker Domain in VPC only mode to support SageMaker Studio with auto shutdown Lifecycle Configuration and SageMaker Canvas with Terraform

AWS Machine Learning

SEPTEMBER 11, 2023

You must also associate a security group for your VPC with these endpoints to allow all inbound traffic from port 443: SageMaker API: com.amazonaws.region.sagemaker.api. This is required to communicate with the SageMaker API. Solution walkthrough In this blog post, we demonstrate how to deploy the Terraform solution.

Scripts

Scripts APIs Management Engineering

Automate SMS Marketing With VirtualPBX Webhooks

VirtualPBX

NOVEMBER 5, 2020

We talk about Zapier a lot on our blog because it makes automation of business tasks so simple; you can even use it for free with the most basic plan. Using The VirtualPBX API to Assist. You can also manage your hooks outside of the VirtualPBX web interface by taking advantage of our API. Combining SMS, Webhooks, and Zapier.

Marketing

Marketing APIs voip Scripts

Introducing an image-to-speech Generative AI application using Amazon SageMaker and Hugging Face

AWS Machine Learning

MAY 19, 2023

In this blog post we walk you through the Solution Architecture behind “Describe For Me”, and the design considerations of our solution. The DescribeForMe web app invokes the backend AI services by sending the Amazon S3 object Key in the payload to Amazon API Gateway Amazon API Gateway instantiates an AWS Step Functions workflow.

APIs

APIs Scripts Engineering Best practices

Create Amazon SageMaker models using the PyTorch Model Zoo

AWS Machine Learning

DECEMBER 19, 2022

This blog post demonstrates how to perform ML inference using an object detection model from the PyTorch Model Zoo within SageMaker. Setting up these ML models as a SageMaker endpoint or SageMaker Batch Transform job for online or offline inference is easy with the steps outlined in this blog post. Solution overview. Step 1: Setup.

Automotive

Automotive APIs Engineering Scripts

Train gigantic models with near-linear scaling using sharded data parallelism on Amazon SageMaker

AWS Machine Learning

OCTOBER 31, 2022

Data scientists and machine learning engineers are constantly looking for the best way to optimize their training compute, yet are struggling with the communication overhead that can increase along with the overall cluster size. To get started, follow Modify a PyTorch Training Script to adapt SMPs’ APIs in your training script.

Scripts

Scripts Benchmark APIs Engineering

Build a powerful question answering bot with Amazon SageMaker, Amazon OpenSearch Service, Streamlit, and LangChain

AWS Machine Learning

MAY 25, 2023

We implement the RAG functionality inside an AWS Lambda function with Amazon API Gateway to handle routing all requests to the Lambda. We implement a chatbot application in Streamlit which invokes the function via the API Gateway and the function does a similarity search in the OpenSearch Service index for the embeddings of user question.

APIs

APIs Enterprise Accountability Chatbots

Achieve high performance with lowest cost for generative AI inference using AWS Inferentia2 and AWS Trainium on Amazon SageMaker

AWS Machine Learning

MAY 4, 2023

Both AWS Inferentia2 and Trainium accelerators have two NeuronCores-v2 , 32 GB HBM memory stacks, and dedicated collective-compute engines, which automatically optimize runtime by overlapping computation and communication when doing multi-accelerator inference. For more details on the architecture, refer to Trainium and Inferentia devices.

APIs

APIs Scripts Engineering Chatbots

New performance improvements in Amazon SageMaker model parallel library

AWS Machine Learning

DECEMBER 16, 2022

You can learn more about Stability AI’s mission and partnership with AWS in the talk of Stability AI CEO at AWS re:Invent 2022 or in this blog post. In this blog post, we’ll first present our latest performance improvements in the SageMaker model parallel library. You can find an example in the same training script train_gpt_simple.py.

Benchmark

Benchmark Engineering APIs Scripts

Build a serverless meeting summarization backend with large language models on Amazon SageMaker JumpStart

AWS Machine Learning

MAY 17, 2023

The events trigger Lambda functions to make API calls to Amazon Transcribe and invoke the real-time endpoint hosting the Flan T5 XL model. Once created, the endpoint can be invoked with the InvokeEndpoint API. For additional posts on ML at AWS, visit the AWS ML Blog. Download the generated text file to view the transcription.

APIs

APIs Scripts Engineering Management

Build a centralized monitoring and reporting solution for Amazon SageMaker using Amazon CloudWatch

AWS Machine Learning

AUGUST 10, 2023

In addition to the SageMaker native events, AWS CloudTrail publishes events when you make API calls, which also streams to EventBridge so that this can be utilized by many downstream automation or monitoring use cases. Additionally, you need the following: Node.js Input Description Example Home Region The Region where the workloads run.

Scripts

Scripts Accountability Metrics APIs

Build custom code libraries for your Amazon SageMaker Data Wrangler Flows using AWS Code Commit

AWS Machine Learning

MARCH 21, 2023

It contains over 300 built-in data transformation steps to aid with feature engineering, normalization, and cleansing to transform your data without having to write any code. For more information about available transformation steps and implementation, refer to Transform Data and the Data Wrangler blog. Choose Preview.

Scripts

Scripts Banking APIs Best practices

Build high-performance ML models using PyTorch 2.0 on AWS – Part 1

AWS Machine Learning

JUNE 6, 2023

Run your DLC container with a model training script to fine-tune the RoBERTa model. After model training is complete, package the saved model, inference scripts, and a few metadata files into a tar file that SageMaker inference can use and upload the model package to an Amazon Simple Storage Service (Amazon S3) bucket.

Scripts

Scripts APIs Benchmark Management

Build and train ML models using a data mesh architecture on AWS: Part 2

AWS Machine Learning

JULY 29, 2022

For data processing and feature engineering, they can run SageMaker processing jobs with an Athena data source and output results back to Amazon Simple Storage Service (Amazon S3). Now that you have a subset of the data as a dataframe, you can start exploring the data and see what feature engineering updates are needed for model training.

Scripts

Scripts Analytics Accountability Engineering

Build a cross-account MLOps workflow using the Amazon SageMaker model registry

AWS Machine Learning

NOVEMBER 16, 2022

For the purposes of this blog we are leveraging the following accounts: Data science account – An account where data scientists have access to the training data and create the models. Workload accounts – These are commonly QA and prod environments where software engineers are able to build applications to consume the ML model.

Accountability

Accountability Best practices Scripts Engineering

Identify key insights from text documents through fine-tuning and HPO with Amazon SageMaker JumpStart

AWS Machine Learning

NOVEMBER 21, 2022

Organizations across industries such as retail, banking, finance, healthcare, manufacturing, and lending often have to deal with vast amounts of unstructured text documents coming from various sources, such as news, blogs, product reviews, customer support channels, and social media. Text classification.

Scripts

Scripts Metrics APIs Healthcare

Architect defense-in-depth security for generative AI applications using the OWASP Top 10 for LLMs

AWS Machine Learning

JANUARY 26, 2024

The goal of this post is to empower AI and machine learning (ML) engineers, data scientists, solutions architects, security teams, and other stakeholders to have a common mental model and framework to apply security best practices, allowing AI/ML teams to move fast without trading off security for speed.

Best practices

Best practices Government Engineering Accountability

Build repeatable, secure, and extensible end-to-end machine learning workflows using Kubeflow on AWS

AWS Machine Learning

SEPTEMBER 9, 2022

This is a guest blog post cowritten with athenahealth. Example components of the standardized tooling include a data ingestion API, security scanning tools, the CI/CD pipeline built and maintained by another team within athenahealth, and a common serving platform built and maintained by the MLOps team.

Engineering

Engineering Healthcare APIs Scripts

Run secure processing jobs using PySpark in Amazon SageMaker Pipelines

AWS Machine Learning

APRIL 11, 2023

When processing large-scale data, data scientists and ML engineers often use PySpark , an interface for Apache Spark in Python. SageMaker provides prebuilt Docker images that include PySpark and other dependencies needed to run distributed data processing jobs, including data transformations and feature engineering using the Spark framework.

Calibration

Calibration Scripts Engineering Best practices

How Amp on Amazon used data to increase customer engagement, Part 1: Building a data analytics platform

AWS Machine Learning

SEPTEMBER 9, 2022

Amp wanted a scalable data and analytics platform to enable easy access to data and perform machine leaning (ML) experiments for live audio transcription, content moderation, feature engineering, and a personal show recommendation service, and to inspect or measure business KPIs and metrics. Data Engineer for Amp on Amazon.

Analytics

Analytics Engineering APIs Metrics

Improve price performance of your model training using Amazon SageMaker heterogeneous clusters

AWS Machine Learning

OCTOBER 27, 2022

AI Engineering, Mobileye. For more information, refer to Using the SageMaker Python SDK and Using the Low-Level SageMaker APIs. After you have defined the instance groups, you need to modify your training script to read the SageMaker training environment information that includes heterogeneous cluster configuration.

Scripts

Scripts Benchmark Metrics Transportation

Hosting YOLOv8 PyTorch models on Amazon SageMaker Endpoints

AWS Machine Learning

MARCH 7, 2023

Deploying models at scale can be a cumbersome task for many data scientists and machine learning engineers. Our last blog post and GitHub repo on hosting a YOLOv5 TensorFlowModel on Amazon SageMaker Endpoints sparked a lot of interest from our readers. PyTorch model. The model weights yolov8l.pt The model weights yolov8l.pt

APIs

APIs Scripts Engineering Accountability

Quickly build high-accuracy Generative AI applications on enterprise data using Amazon Kendra, LangChain, and large language models

AWS Machine Learning

MAY 3, 2023

With Amazon Bedrock , you will be able to choose Amazon Titan , Amazon’s own LLM, or partner LLMs such as those from AI21 Labs and Anthropic with APIs securely without the need for your data to leave the AWS ecosystem. For the best results, a GenAI app needs to engineer the prompt based on the user request and the specific LLM being used.

Enterprise

Enterprise APIs Chatbots Government

Fine-tune Falcon 7B and other LLMs on Amazon SageMaker with @remote decorator

AWS Machine Learning

SEPTEMBER 14, 2023

To improve the quality of output, approaches like n-short learning, Prompt engineering, Retrieval Augmented Generation (RAG) and fine tuning are used. The code presented in this blog can also be used to fine-tune other FMs, such as Llama-2 13b. This is done by a Hugging Face Transformers Tokenizer.

Accountability

Accountability APIs Scripts Engineering

Enabling hybrid ML workflows on Amazon EKS and Amazon SageMaker with one-click Kubeflow on AWS deployment

AWS Machine Learning

NOVEMBER 16, 2022

The use case in this blog will specifically focus on SageMaker integration with Kubeflow on AWS that could be added to your existing Kubernetes workflows enabling you to build hybrid machine learning architectures. Automated deployment options have been improved and simplified using Kustomize scripts and Helm charts.

Metrics

Metrics Scripts Enterprise APIs

Your Customers Are Talking, But Are You Listening?

Call Journey

OCTOBER 20, 2018

It was originally published on Genesys blog. This trend is further spurred by the API economy and a rise of marketplaces such as AppFoundry, offering specialized, highly sophisticated, yet light solutions. Agent Script Adherence. This post was co-authored by Juergen Tolksdorf, Director of Innovations Group at Genesys.

Scripts

Scripts Customer emotions industry standards Engineering

Everything You Need to Know About Custom Web Development

OctopusTech

AUGUST 18, 2023

Learn the details of professional custom website development, from its definition to its importance, here in this blog. Back-end developers work with libraries, data architecture, APIs, code that interacts with databases, and more because they are interested in how a website operates. What Is Custom Web Development?

Construction

Construction Engineering APIs Enterprise

Using Voice Communication to Create Lasting Customer Impressions

aircall

JUNE 11, 2021

2015 — An open API (applied programming interface) technology was invented to allow software applications to sync and share data between them. A discussion of voice communications isn’t complete without VoIP (voice over internet protocol) and an open API (applied programming interface) technology. Telecommunication Now.

voip

voip APIs Call Center Telecommunications

Gemma is now available in Amazon SageMaker JumpStart

AWS Machine Learning

MARCH 13, 2024

. * The `if __name__ == "__main__"` block checks if the script is being run directly or imported. estimator.set_hyperparameters(chat_dataset="True", peft_type="lora", max_input_length="2048", epoch="3") estimator.fit({"training": }) Underlying the training scripts, JumpStart uses HuggingFace SFTTrainer with QLoRA and FlashAttention.

Benchmark

Benchmark Scripts APIs Feedback

Build a GNN-based real-time fraud detection solution using Amazon SageMaker, Amazon Neptune, and the Deep Graph Library

AWS Machine Learning

AUGUST 11, 2022

Additionally, it’s challenging to construct a streaming data pipeline that can feed incoming events to a GNN real-time serving API. It starts from a RESTful API that queries the graph database in Neptune to extract the subgraph related to an incoming transaction. The code used in this solution is available in src/scripts/glue-etl.py.

Construction

Construction APIs Accountability Scripts

How to Build a Nightscout Notifier with Nexmo Messages and Python – Part Two

Nexmo

FEBRUARY 27, 2020

Copy these values to.env as follows: NEXMO_API_KEY="YOUR API KEY HERE" NEXMO_API_SECRET="YOUR API SECRET HERE". We must create an application that uses the Voice API and Messages API. To send messages using the Messages API, we need our API Key and API Secret. env ), so we simply get them ??

APIs

APIs Accountability Engineering Scripts

Create high-quality images with Stable Diffusion models and deploy them cost-efficiently with Amazon SageMaker

AWS Machine Learning

MAY 26, 2023

NVIDIA Triton model repository and configuration The model repository contains the model serving script, model artifacts and tokenizer artifacts, a packaged conda environment (with dependencies needed for inference), the Triton config file, and the Python script used for inference. Vikram Elango is a Sr.

APIs

APIs Scripts Engineering Best practices

Build production-ready generative AI applications for enterprise search using Haystack pipelines and Amazon SageMaker JumpStart with LLMs

AWS Machine Learning

AUGUST 14, 2023

This blog post is co-written with Tuana Çelik from deepset. You can serialize pipelines to YAML files , expose them via a REST API , and scale them flexibly with your workloads, making it easy to move your application from a prototype stage to production. script to preprocess and index the provided demo data.

Enterprise

Enterprise Scripts Best practices Analytics

Build an image search engine with Amazon Kendra and Amazon Rekognition

Amazon SageMaker model parallel library now accelerates PyTorch FSDP workloads by up to 20%

Webinars

Trending Sources

Accelerate ML workflows with Amazon SageMaker Studio Local Mode and Docker support

Webinars

Modernizing data science lifecycle management with AWS and Wipro

How Sportradar used the Deep Java Library to build production-scale ML platforms for increased performance and efficiency

Run machine learning inference workloads on AWS Graviton-based instances with Amazon SageMaker

How Earth.com and Provectus implemented their MLOps Infrastructure with Amazon SageMaker

Build ML features at scale with Amazon SageMaker Feature Store using data from Amazon Redshift

Optimize AWS Inferentia utilization with FastAPI and PyTorch models on Amazon EC2 Inf1 & Inf2 instances

Simplify access to internal information using Retrieval Augmented Generation and LangChain Agents

Best practices to build generative AI applications on AWS

Connecting Amazon Redshift and RStudio on Amazon SageMaker

Amazon SageMaker Domain in VPC only mode to support SageMaker Studio with auto shutdown Lifecycle Configuration and SageMaker Canvas with Terraform

Automate SMS Marketing With VirtualPBX Webhooks

Introducing an image-to-speech Generative AI application using Amazon SageMaker and Hugging Face

Create Amazon SageMaker models using the PyTorch Model Zoo

Train gigantic models with near-linear scaling using sharded data parallelism on Amazon SageMaker

Build a powerful question answering bot with Amazon SageMaker, Amazon OpenSearch Service, Streamlit, and LangChain

Achieve high performance with lowest cost for generative AI inference using AWS Inferentia2 and AWS Trainium on Amazon SageMaker

New performance improvements in Amazon SageMaker model parallel library

Build a serverless meeting summarization backend with large language models on Amazon SageMaker JumpStart

Build a centralized monitoring and reporting solution for Amazon SageMaker using Amazon CloudWatch

Build custom code libraries for your Amazon SageMaker Data Wrangler Flows using AWS Code Commit

Build high-performance ML models using PyTorch 2.0 on AWS – Part 1

Build and train ML models using a data mesh architecture on AWS: Part 2

Build a cross-account MLOps workflow using the Amazon SageMaker model registry

Identify key insights from text documents through fine-tuning and HPO with Amazon SageMaker JumpStart

Architect defense-in-depth security for generative AI applications using the OWASP Top 10 for LLMs

Build repeatable, secure, and extensible end-to-end machine learning workflows using Kubeflow on AWS

Run secure processing jobs using PySpark in Amazon SageMaker Pipelines

How Amp on Amazon used data to increase customer engagement, Part 1: Building a data analytics platform

Improve price performance of your model training using Amazon SageMaker heterogeneous clusters

Hosting YOLOv8 PyTorch models on Amazon SageMaker Endpoints

Quickly build high-accuracy Generative AI applications on enterprise data using Amazon Kendra, LangChain, and large language models

Fine-tune Falcon 7B and other LLMs on Amazon SageMaker with @remote decorator

Enabling hybrid ML workflows on Amazon EKS and Amazon SageMaker with one-click Kubeflow on AWS deployment

Your Customers Are Talking, But Are You Listening?

Everything You Need to Know About Custom Web Development

Using Voice Communication to Create Lasting Customer Impressions

Gemma is now available in Amazon SageMaker JumpStart

Build a GNN-based real-time fraud detection solution using Amazon SageMaker, Amazon Neptune, and the Deep Graph Library

How to Build a Nightscout Notifier with Nexmo Messages and Python – Part Two

Create high-quality images with Stable Diffusion models and deploy them cost-efficiently with Amazon SageMaker

Build production-ready generative AI applications for enterprise search using Haystack pipelines and Amazon SageMaker JumpStart with LLMs

Stay Connected