Patterson Consulting provides comprehensive LLM, Data Engineering, and DevOps Services for Fortune 500 companies
Services Offered:
Custom Large Language Model Applications
We help customers design, build, and deploy augmented reasoning large language model applications. Download our e-Book on "An Introduction to Large Language Models"Data Engineering
We help customers design, build, and orchestrate complex data pipelines.Cloud DevOps
We help customers build out and deploy platforms built on the Cloud.Managed Platforms
We can run your infrastructure for you, on-premise or in the cloud.
Who is Patterson Consulting?
- Our customer list includes multiple Fortune 100 banks, insurance, telecoms, and healthcare organizations
- We are trusted by partners such as Cube, Amazon Web Services, Snowflake, and Confluent to work with their own critical customers
- Members of our team co-created the Deeplearning4j Deep Learning Library
- Our Deep Learning book has 7 translations published and is cited in many scientific papers
Our Large Language Model Demo in Cube's Booth at this Year's Snowflake Summit 2023
Demo Overview
This year we'll be giving a live demo of a next generation enterprise large language model that takes advantage of Cube's semantic layer for better knowledge repository integration. Included in the demo:
- A walk-through of an example enterprise LLM-application built with LangChain
- This applications shows how we can support any analyst role (here, a meteorologist) with an expert assistant to do ground work while they focus on higher-level analysis work
- We explain the architecture of the system for each of the types of natural language commands
- And how Cube's semantic layer supports certain types of queries, supplying knowledge from the corporate Snowflake cloud data warehouse to support the Augmented Reasoning engine
- Tuesday, June 27th @ 1pm
- Wednesday, June 28th @ 1pm
Want to know more about building enterprise applications with large language models?
Download our e-Book on "An Introduction to Large Language Models".
We Also Offer Different Lines of Snowflake Workshops
Selected Entries and Series from Our Blog
Detecting Credit Card Fraud with Snowflake, Snowpark, and Amazon SageMaker Studio
- Part 1: Loading the Credit Card Transaction Data Into Snowflake
- Part 2: Scalable Feature Engineering with Snowpark
- Part 3: Connecting AWS Sagemaker Studio Lab to Snowflake
- Part 4: Grid Search Model Selection with AWS Sagemaker Studio Lab and Shap Hypertune
- Part 5: Deploying the Model as a Streamlit Application
Building an End-to-End Cloud Predictive Maintenance System with Snowflake
- Part 1: Making the Business Case for Predictive Maintenance
- Part 2: Sensor Data Ingest, Storage, and Analysis with Snowflake
- Part 3: Exploratory Data Analysis
- Part 4: Machine Learning Workflows with Sci-Kit Learn to Build Predictive Maintenance Models
- Part 5: Analyzing the Results
- Part 6: Going to Production with Snowpark
Other Selected Articles on Our Blog
- DBT Hello World: Part 1 and Part 2
- AWS Spend Forecasting: Forecasting Your AWS Cloud GPU Spend
- Understanding Cloud Resource Value: A Cloud GPU Value Model for NVIDIA Multi-Instance GPUs (MIG)
- Computer Vision: GANs for Unsupervised Anomaly Detection in Manufacturing
- Machine Learning Model Serving on Kubernetes: Deploying a HuggingFace NLP Model with KFServing
- Tutorial: Setting Up Kafka on Amazon Web Services