GraphBI: Expanding Analytics to All Data Through the Combination of GenAI, Graph, & Visual Analytics // Paco Nathan & Weidong Yang // #310

Key takeaways

GraphBI represents a significant advancement in how organizations can leverage combined data sources for analytics.
Generative AI facilitates the transformation of unstructured data into graph format, enabling more effective analytics.
Visual analytics are crucial for deriving actionable insights, allowing users to discover relationships within complex datasets.
Contextual understanding of data is essential for meaningful analysis, bridging the gap between different domains.
The emergence of graph technologies presents new opportunities for organizations to harness the full potential of their data.

Summary

Introduction to GraphBI

In this episode of the MLOps Podcast, hosts Amitrios, Paco Nathan, and Weidong Yang dive into GraphBI, a methodology integrating generative AI (GenAI), graph technologies, and visual analytics. They explore how existing Business Intelligence (BI) solutions primarily handle structured data, which constitutes only about 20% of available information, leaving the majority untapped. GraphBI aims to unlock this untapped potential through dynamic data transformation.

Data Processing and Integration

The conversation highlights how GenAI plays a critical role in transforming unstructured data into a graph-based format for analysis, enabling a transparent and reliable step-by-step workflow. The guests discuss the challenges of combining structured and unstructured data for analysis, emphasizing that traditional systems often fail to adequately process the vast amounts of unstructured information.

Visual Analytics and Meaningful Insights

Weidong and Paco discuss the significance of visual analytics in data interpretation, enhancing comprehension by allowing users to visualize relationships and derive insights from complex data interactions. The ability to visually mutate graphs enables users to dynamically explore datasets to identify patterns and answer key business questions.

Philosophical Underpinnings of Data Processing

The episode also touches on the contrasting philosophies of Eastern and Western data practices. They argue that successful data analysis requires not only technical expertise but also deep contextual understanding to navigate complex relationships represented within graph structures.

The Future of Graph Technologies

The discussion anticipates a growing relevance of graph technologies alongside advancements in model capabilities, particularly the promise of integrating AI to intelligently handle and analyze data connections. They advocate for a shift in how organizations perceive data relationships, noting that collaboration among different domains can significantly enhance understanding and usability.

Show notes

GraphBI: Expanding Analytics to All Data Through the Combination of GenAI, Graph, & Visual Analytics // MLOps Podcast #310 with Paco Nathan, Principal DevRel Engineer at Senzing & Weidong Yang, CEO of Kineviz.

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

// Abstract

Existing BI and big data solutions depend largely on structured data, which makes up only about 20% of all available information, leaving the vast majority untapped. In this talk, we introduce GraphBI, which aims to address this challenge by combining GenAI, graph technology, and visual analytics to unlock the full potential of enterprise data.

Recent technologies like RAG (Retrieval-Augmented Generation) and GraphRAG leverage GenAI for tasks such as summarization and Q&A, but they often function as black boxes, making verification challenging. In contrast, GraphBI uses GenAI for data pre-processing—converting unstructured data into a graph-based format—enabling a transparent, step-by-step analytics process that ensures reliability.

We will walk through the GraphBI workflow, exploring best practices and challenges in each step of the process: managing both structured and unstructured data, data pre-processing with GenAI, iterative analytics using a BI-focused graph grammar, and final insight presentation. This approach uniquely surfaces business insights by effectively incorporating all types of data.

// Bio

Paco Nathan

Paco is a "player/coach" who excels in data science, machine learning, and natural language, with 40 years of industry experience. He leads DevRel for the Entity Resolved Knowledge Graph practice area at Senzing.com and advises Argilla.io, Kurve.ai, KungFu.ai, and DataSpartan.co.uk, and is a lead committer for the pytextrank and kglab open source projects. Formerly: Director of Learning Group at O'Reilly Media, and Director of Community Evangelism at Databricks.

Weidong Yang

Weidong Yang, Ph.D., is the founder and CEO of Kineviz, a San Francisco-based company that develops interactive visual analytics-based solutions to address complex big data problems. His expertise spans Physics, Computer Science, and Performing Arts, with significant contributions to the semiconductor industry and quantum dot research at UC, Berkeley, and Silicon Valley. Yang also leads Kinetech Arts, a 501(c) non-profit blending dance, science, and technology. An eloquent public speaker and performer, he holds 11 US patents, including the groundbreaking Diffraction-based Overlay technology, vital for sub-10-nm semiconductor production.

// Related Links

Website: https://www.kineviz.com/

Blog: https://medium.com/kineviz

Website: https://derwen.ai/pacohttps://huggingface.co/pacoid

https://github.com/ceterihttps://neo4j.com/developer-blog/entity-resolved-knowledge-graphs/

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm