The MLOps Blog

JUNE 27, 2023

” – James Tu, Research Scientist at Waabi Play with this project live For more: Dive into documentation Get in touch if you’d like to go through a custom demo with your team Comet ML Comet ML is a cloud-based experiment tracking and optimization platform. Dolt Dolt is an open-source relational database system built on Git.

Machine Learning 134

Machine Learning Machine Learning ML ML 134

BAIR

FEBRUARY 17, 2024

We frequently see this with LLM users, where a good LLM creates a compelling but frustratingly unreliable first demo, and engineering teams then go on to systematically raise quality. AI applications have always required careful monitoring of both model outputs and data pipelines to run reliably. Systems can be dynamic.

AI 145

AI AI DataOps Data Pipeline 145

AWS Machine Learning Blog

DECEMBER 6, 2023

With the right underlying embedding model, capable of producing accurate semantic representations of the input document chunks and the input questions, and an efficient semantic search module, this solution is able to answer questions that require retrieving existent information in a database of documents.

SQL 126

SQL AWS Analytics Analytics 126

phData

OCTOBER 25, 2024

It’s common to have terabytes of data in most data warehouses, data quality monitoring is often challenging and cost-intensive due to dependencies on multiple tools and eventually ignored. This results in poor credibility and data consistency after some time, leading businesses to mistrust the data pipelines and processes.

Data Quality 52

Data Quality Data Pipeline Data Governance Database 52

Iguazio

JANUARY 22, 2024

Demo: How to Build a Smart GenAI Call Center App How we used LLMs to turn call center conversation audio files of customers and agents into valuable data in a single workflow orchestrated by MLRun. The data pipeline - Takes the data from different sources (document, databases, online, data warehouses, etc.),

Data Pipeline 52

Data Pipeline ML ML Data Warehouse 52

phData

JULY 5, 2024

For enterprises, the value-add of applications built on top of large language models is realized when domain knowledge from internal databases and documents is incorporated to enhance a model’s ability to answer questions, generate content, and any other intended use cases.

AI 52

AI AI Database AWS 52

AWS Machine Learning Blog

SEPTEMBER 24, 2024

An optional CloudFormation stack to deploy a data pipeline to enable a conversation analytics dashboard. This is where the content for the demo solution will be stored. For the demo solution, choose the default ( Claude V3 Sonnet ). For the hotel-bot demo, try the default of 4. Do not specify an S3 prefix.

AWS 101

AWS AI AI Analytics 101

ODSC - Open Data Science

SEPTEMBER 20, 2023

Tuesday is the first day of the AI Expo and Demo Hall , where you can connect with our conference partners and check out the latest developments and research from leading tech companies. Finally, get ready for some All Hallows Eve fun with Halloween Data After Dark , featuring a costume contest, candy, and more. What’s next?

Data Wrangling 52

Data Wrangling Data Science Machine Learning Machine Learning 52

phData

MARCH 1, 2024

This functionality eliminates the need for manual schema adjustments, streamlining the data ingestion process and ensuring quicker access to data for their consumers. As you can see in the above demo, it is incredibly simple to use INFER_SCHEMA and SCHEMA EVOLUTION features to speed up data ingestion into Snowflake.

Data Engineer 52

Data Engineer Data Engineering Data Engineering Data Engineering 52

Alation

APRIL 19, 2022

Data producers and consumers alike are working from home and hybrid locations more often. And in an increasingly remote workforce, people need to access data systems easily to do their jobs. This might mean that they’re accessing a database from a smartphone, computer, or tablet. Today, data dwells everywhere.

Data Governance 52

Data Governance Cloud Data Database Data Silos 52

phData

APRIL 5, 2024

Snowflake Solution In the past, companies would hire employees whose focus was scanning, entering, and correcting data from documents into an organized table or database. Before we dive into the demo, the next section covers a couple of the key technologies that enable Document AI. That’s where Document AI comes in!

AI 52

AI AI Natural Language Processing Tableau 52

phData

JULY 29, 2023

Operational Risks identify operational risks such as data loss or failures in the event of an unforeseen outage or disaster. Performance Optimization identify and fix bottlenecks in your data pipelines so that you can get the most out of your Snowflake investment.

SQL 52

SQL Database Data Pipeline 52

Iguazio

FEBRUARY 20, 2024

Building MLOpsPedia This demo on Github shows how to fine tune an LLM domain expert and build an ML application Read More Building Gen AI for Production The ability to successfully scale and drive adoption of a generative AI application requires a comprehensive enterprise approach. Let’s dive into the data management pipeline.

AI 52

AI AI Data Pipeline Analytics 52

phData

JULY 2, 2024

Developers can seamlessly build data pipelines, ML models, and data applications with User-Defined Functions and Stored Procedures. conda activate snowflake-demo ). Validating the Deployment in Snowflake Existence – The newly created Python UDF should be present under the Analytics schema under the HOL_DB database.

Python 52

Python SQL Data Pipeline ML 52

phData

JANUARY 31, 2024

For a short demo on Snowpark, be sure to check out the video below. Utilizing Streamlit as a Front-End At this point, we have all of our data processing, model training, inference, and model evaluation steps set up with Snowpark. that were previously all needed to put your app into production.

Machine Learning 52

Machine Learning Machine Learning Python Data Scientist 52

phData

SEPTEMBER 7, 2023

This is commonly handled in code that pulls data from databases, but you can also do this within the SQL query itself. If you’re interested in learning more about our Toolkit or getting a demo around the functionality and how it could help your organization, give us a shout !

SQL 52

SQL Data Profiling Data Pipeline Database 52

ODSC - Open Data Science

JANUARY 3, 2025

Finally, Week 4 ties it all together, guiding participants through the practical builder demos from cloning compound AI architectures to building production-ready applications. These hands-on demo workshops and live demonstrations show attendees how to use cutting-edge tools to create impactful AI applications in real-time.

AI 40

AI AI ML ML 40

Snorkel AI

MAY 26, 2023

What’s really important in the before part is having production-grade machine learning data pipelines that can feed your model training and inference processes. And that’s really key for taking data science experiments into production. Let’s go and talk about machine learning pipelining.

SQL 52

SQL ML ML Python 52

Snorkel AI

MAY 26, 2023

What’s really important in the before part is having production-grade machine learning data pipelines that can feed your model training and inference processes. And that’s really key for taking data science experiments into production. Let’s go and talk about machine learning pipelining.

SQL 52

SQL ML ML Python 52

Mlearning.ai

JUNE 16, 2023

GPT-4 Data Pipelines: Transform JSON to SQL Schema Instantly Blockstream’s public Bitcoin API. The data would be interesting to analyze. From Data Engineering to Prompt Engineering Prompt to do data analysis BI report generation/data analysis In BI/data analysis world, people usually need to query data (small/large).

AI 52

AI AI Data Analysis Data Analysis 52

BAIR

FEBRUARY 18, 2024

We frequently see this with LLM users, where a good LLM creates a compelling but frustratingly unreliable first demo, and engineering teams then go on to systematically raise quality. AI applications have always required careful monitoring of both model outputs and data pipelines to run reliably. Systems can be dynamic.

AI 40

AI AI DataOps Data Pipeline 40

phData

JUNE 7, 2023

Vector Database : A vector database is a specialized database designed to efficiently store, manage, and retrieve high-dimensional vectors, also known as vector embeddings. Vector databases support similarity search operations, allowing users to find vectors most similar to a given query vector.

AI 59

AI AI Machine Learning Machine Learning 59

The MLOps Blog

MARCH 21, 2023

An ML platform standardizes the technology stack for your data team around best practices to reduce incidental complexities with machine learning and better enable teams across projects and workflows. We ask this during product demos, user and support calls, and on our MLOps LIVE podcast. Why are you building an ML platform?

Machine Learning 69

Machine Learning Machine Learning Data Scientist ML 69

Iguazio

OCTOBER 20, 2024

In this blog post, we provide a staged approach for rolling out gen AI, together with use cases, a demo and examples that you can implement and follow. Demo: IguaJewels Now let’s see such a gen AI chatbot in action. They also had access to a database with client data and a database with product data.

AI 95

AI AI Database Data Wrangling 95