Blog

Overcoming Self-Service BI Hurdles with Generative AI

Explore challenges of self-service business intelligence (BI) including the hurdles of information discovery, flexibility limitations, and consistency. Discover how tailored Generative AI solutions are revolutionizing data exploration, streamlining resources, and propelling businesses forward in an ever-evolving digital landscape.

NSQL-Llama-2-7b: Advancing SQL Foundation Models for Personalized Analytics

This blog introduces NSQL-Llama-2-7b, Numbers Station's new SQL generation foundation model built off of Meta's Llama 2. NSQL-Llama-2-7b achieves up to a 15.5-point execution accuracy improvement over the previous NSQL 6b model while narrowing the performance gap with GPT-4 on standard SQL benchmarks.

Introducing NSQL: Open-source SQL Copilot Foundation Models

This blog explores the release of NSQL, a new family of open-source large foundation models designed specifically for SQL generation tasks. With NSQL 350M, NSQL 2B, and NSQL 6B, we're advancing the progress in open-source models, with NSQL 6B outperforming all existing open-source models on standard SQL benchmarks.

4 Key Challenges: Establishing a Semantic Layer for Your Enterprise

Unlock the power of your data with a semantic layer, but beware of the challenges involved in setting it up. Learn about the four greatest pain points organizations face when implementing a semantic layer. From aligning on business metric definitions to navigating data integration complexities and managing changes, these challenges can hinder progress.

The Semantic Layer: critical to the enterprise modern data stack

Explore the challenges faced by enterprises in the data-driven business landscape and how self-service BI tools can lead to misaligned teams, duplicated work, inconsistent metrics, and untrusted results. Learn about the role of a semantic layer in addressing these challenges by standardizing metrics and providing a framework for consistent and reliable insights.

Numbers Station Interview with Mark Nelson, former CEO of Tableau

Mark Nelson, former CEO of Tableau, shares insights with Chris Aberger, CEO of Numbers Station, on the past, present, and future of data analytics. They discuss the evolution of the modern data stack and the gaps that remain, traditional and new roles in data and analytics, and the future of data analytics with foundation models.

Introducing Numbers Station Labs

Numbers Station Labs is a research lab dedicated to bringing foundation model technology to the modern data stack. The lab was founded by a group of PhDs from the Stanford AI lab where the term foundation models (FMs) was coined. Our mission is to remove the high barrier to entry currently associated with the modern data stack and to open up new possibilities for enterprise data automation. We believe that continued dedication to research-based innovation is key to their impact on the modern data stack and the success of their customers. Learn more about our research agenda.

Prototype then Deploy: shrinking foundation model quality into small models

Foundation Models (FMs) such as GPT-4 promise a natural language interface for data analysts to perform complicated transformation tasks and gain insights from their data. Despite the wide success of FMs, there are still high barriers to use on enterprise data such as hard to prompt, privately owned, and a high cost to run (a single run of 1M rows could cost more than $3.7K!). At Numbers Station, our goal is to bring state of the art FM technology to all data analysts. With a few natural language examples from an analyst, Numbers Station customizes a small FM on the analyst’s task and data. Our smaller FMs match the capabilities of proprietary large FMs and can be up to 2000x times cheaper. At Numbers Station, we are excited to take the first step towards making FM technology accessible to all enterprise analysts.

SQL Coding Assistants Customized to Enterprise Logs

Numbers Station wants to bring the productivity of foundation models (FM) for code to the data analyst and help them generate SQL to transform their data. SQL FMs need to be heavily personalized to the data and infrastructure the analyst interacts with, but customizing FMs is difficult because they are difficult to prompt, prohibitively expensive to finetune over enterprise data, and not applicable over private data. Numbers Station introduces Data Transformation Assistant to help the enterprise customize their own smaller SQL FM that can be deployed locally. Numbers Stations produces competitive models on two benchmark datasets – even outperforming GPT-4 - and can be more than 2,000 times cheaper than conventional approaches.