Patrick Do

Scalable RAG with Azure Cosmos DB and DiskANN | Studio15 We’ll talk a bit about Cosmos DB and DiskANN, before delving into a quick coding example of vector search using #AzureCosmosDB’s #Python SDK in a Jupyter Notebook. https://lnkd.in/ehT5b7pS

1

Spark doesn't always interpret JSON how we'd like. For example, if each key/value pair in a JSON object is conceptually one item, Spark won't give you a row per item by default. This article, by Ian Griffiths, shows how to nudge Spark in the right direction using #MicrosoftFabric. https://lnkd.in/ebwzPca4

2

Useful scripts ahead

1

Improve quality of grounding information with hybrid retrieval and semantic ranking. See how companies like AT&T use Azure AI Search for their internal RAG platform. https://lnkd.in/gGhtSpDT Enhance your apps with retrieval-augmented generation (RAG) capabilities and the power of Azure AI Search. Manage large-scale datasets while maintaining high-quality search results by leveraging binary quantization, oversampling, and Matryoshka Representation Learning (MRL). Experience significant cost savings and improved performance by optimizing your vector indexes without compromising quality. Azure AI Search enables seamless integration of semantic ranking and hybrid search functionalities, allowing you to deliver personalized responses and insights. #AzureAISearch

7

🚀 Automate Your CI/CD Pipeline with Snowflake and GitHub Actions 🚀 Our Senior Data Engineer, Jaime Salas, shares an insightful guide on integrating GitHub Actions with Snowflake to streamline your CI/CD pipeline. Learn how to: 🔹 Set up key pair authentication 🔹 Create and manage Snowflake users and schemas 🔹 Automate tests and merges using GitHub Actions Enhance your development workflow with these powerful automation techniques! https://hubs.ly/Q02BWXC10 👉 Read the full article #DataEngineering #Snowflake #GitHubActions #CICD #Automation

15

👋 🛠️ Say goodbye to complex troubleshooting. With Synthia, the AI assistant built into Sisense's Compose SDK, developers get real-time guidance—no technical jargon needed. Whether you’re a seasoned coder or new to the game, Synthia makes navigating Compose SDK seamless, solving challenges and optimizing workflows faster. Start your 30-day free trial 👉 https://bit.ly/4dGzK7j #AI #SaaS #DataScience

30

#AzureMachineLearning is comprised of several key components that all come together to facilitate the machine learning process and Alexander Walters explains the processes in our blog article here -> https://lnkd.in/gpDxWyaa

2

📣 At Databricks, we want to help customers build more #inference-friendly #llms. Our MixAttention architecture demonstrates that reductions in KV cache size make it possible to maintain model quality while improving inference speed and reducing memory footprint. Read our latest blog post to learn more: https://lnkd.in/gcHxM4DX

133

3 Comments

Come join me for another presentation - this time we'll be using Microsoft's Semantic Kernel API in .NET. We'll cover how to get started, an overview of the Semantic Kernel API in its current state, how to store your proprietary data/embeddings in a separate vector database, and more!

16

🔍 Want to master RAG with Semantic Kernel and #AzureCosmosDB for #MongoDB? This session covers everything from setting up vector search to deploying Azure OpenAI models. 🚀 https://lnkd.in/eUj2jZ2X

5

What's the relationship between DataStax and the Apache Cassandra project? Learn about power of collaboration (and the pitfalls of divergence) from Apache Cassandra committer Patrick McFadin. From SAI to vector search, he shares how the collaboration drives innovation and benefits the entire community. ➡️https://dtsx.io/47Y7DhZ #DataStax #ApacheCassandra #OpenSourceCommunity #InnovationDriven #DataManagement #DatabaseSystems #TechInnovation

12

1 Comment

Tired of wrangling complex JSON configurations for your data products? Managing configurations can be a daunting task, if you are wrestling with JSON configurations. Maybe its time to default to YAML, especially within a data mesh architecture! 🙌 Why YAML is a game-changer for data product configurations: -Unmatched readability: YAML's clean syntax lets you and your team grasp configurations at a glance, fostering seamless collaboration. -Data as Code FTW! Treating configurations as code aligns perfectly with data mesh principles, enabling version control, reliable change management -Automation's best friend: YAML plugs directly into your tools, streamlining the entire data mesh lifecycle – provisioning, monitoring, and data share! #dataarchitecture #dataengineering #datamesh #datacontract

19

2 Comments

Boost query speed, reduce latency, and enhance cost efficiency without sacrificing accuracy by moving in-memory I/O traffic to SSDs. See how DiskANN is now built into #AzureCosmosDB. #DiskANN https://lnkd.in/evc49kWB

8

New Blog Alert: Maximize your fine-tuned model performance with the new Azure AI Evaluation SDK! In the journey of distilling large models like Meta Llama 3.1 405B into efficient smaller versions, evaluating the performance is crucial to ensure efficacy, accuracy, and readiness for deployment. 🔍 Learn how the Azure AI Evaluation SDK can: - Enhance your model assessment with advanced metrics - Provide insights with GPT-model based and math based evaluations - Enable bulk metric evaluation for comprehensive analysis Join me as we compare distilled models against baseline performance and explore valuable metrics that can drive continuous improvement. Whether you're in AI development or in search of efficient deployment strategies, this blog post is tailored for you. 👉 Read more: https://lnkd.in/gfQbNy3p #AzureAI #MachineLearning #AIEvaluation #AICommunity #ArtificialIntelligence #TechInnovation

30

Here is a series of useful instructional videos on LLMOps.

7

1 Comment

Our last poll was about data and transparency. Today, Databricks has created The State Reader API , a new capability to help users have access and analyze internal state data for full transparency and ease of use __ Will this new capability make a real difference from what we are used to use so far? #Databricks #Newcapability #datatransparency #accessibility #easeofuse #nuboTed

2

2 Comments

Boost query speed, reduce latency, and enhance cost efficiency without sacrificing accuracy by moving in-memory I/O traffic to SSDs. See how DiskANN is now built into Azure Cosmos DB. #DiskANN https://lnkd.in/evc49kWB

11

💻Generative AI, from your local machine to Azure with LangChain.js Great blog on building with GenAI in Javascript ecosystem Covers how to get started with local models (via Ollama) and then use model from Azure https://lnkd.in/gYEVUeMB

324

4 Comments