Flyte’s Post

Great collaboration with David Espejo and Shalabh Chaudhri from Union.ai to build and validate an end-to-end ML solution on AKS - check out our engineering blog and get started with the reference code below!

Another great post on the AKS Engineering Blog. In this post, Sachi Desai shows how you can quickly spin up an end-to-end ML solution on AKS with Flyte.

💬 Want to create an AI chatbot with Retrieval-Augmented Generation? Check out this serverless sample using LangChain.js, #Azure, and #AzureCosmosDB! Get started: https://lnkd.in/ezJs8is5

Discover Puluminary Tyler Mulligan's latest guest blog on seamlessly adding data to Pinecone with S3 and Embedchain, powered by Pulumi on #AWS. Elevate your AI Slack bot capabilities with this comprehensive guide. Read more: https://hubs.ly/Q02zvGwV0 #LLM #cloud #SoftwareDevelopment

Customers want to build AI models using their data, so their data teams want to do repeatable A/B testing experiments. A solution uses infrastructure as code to define the process of retrieving and preparing data for experiments. #aws #awscloud #cloud #amazonbedrock #artificialintelligence #awssdkforpython #generativebi #technicalhowto #aiml #amazonmachinelearning #generativeai

Enhance #RAG AI accuracy with power of data with #Elastic , highly recommended approach to accelerate outcomes with #AI and open source AI models on hybrid cloud #iwork4dell Red Hat https://lnkd.in/gwfksGP5

Interesting news in generative AI and Langchain space... langchain now provides an integration package for Amazon Web Services (AWS), allowing users to access Bedrock supported models from Anthropic, Mistral AI, Cohere, AI21 Labs etc. using langchain connector! For the complete list of AWS integrations refer the link below... https://lnkd.in/ggdBKbfU #aws #awscloud #generativeai #llm #machinelearning #langchain

AI chatbots need fresh, context-rich data to generate more accurate outputs and results. Confluent Cloud for Apache Flink's "AI Model Inference feature" provides the ability to analyze the information you process with Confluent Cloud using large language models. Developers can extract the most important records from a data stream and summarizing text. It makes it possible for developers to use simple Structured Query Language statements to make calls to remote model endpoints, including OpenAI, AWS Sagemaker, Google Cloud’s Vertex AI and Microsoft Azure’s OpenAI Service, so as to orchestrate data cleaning and processing tasks in real time. Check out the Getting started Guide - https://lnkd.in/geXKDW_f