RT Avi Chawla (@_avichawla)Build human-like memory for your Agents (open-source)!Every agentic and RAG system struggles with real-time knowledge updates and fast data retrieval.Zep solves these issues with its continuously evolving and temporally-aware Knowledge Graph.Like humans, Zep organizes an Agent's memories into episodes, extracts entities and their relationships from these episodes, and stores them in a knowledge graph:(refer to the image below as you read)1) Episode Subgraph: Captures raw data with ...

If you found it insightful, reshare it with your network.Find me → @_avichawlaEvery day, I share tutorials and insights on DS, ML, LLMs, and RAGs.Avi Chawla (@_avichawla):Build human-like memory for your Agents (open-source)!Every agentic and RAG system struggles with real-time knowledge updates and fast data retrieval.Zep solves these issues with its continuously evolving and temporally-aware Knowledge Graph.Like humans, Zep organizes an https://t.co/fwI2RZjwdZ ...

Build human-like memory for your Agents (open-source)!Every agentic and RAG system struggles with real-time knowledge updates and fast data retrieval.Zep solves these issues with its continuously evolving and temporally-aware Knowledge Graph.Like humans, Zep organizes an Agent's memories into episodes, extracts entities and their relationships from these episodes, and stores them in a knowledge graph:(refer to the image below as you read)1) Episode Subgraph: Captures raw data with timestamps, retaining ever ...

[Music] We are talking about graph rack today. That's the graph rack trick of course. Uh and we want to look at patterns for successful graph applications uh for um making LLMs a little bit smarter by putting knowledge graph into the picture.My name is Michael Hunga. I'm VP at of product innovation at Neo Forj. My name is Steven Shin.I lead the developer relations at Neo Forj. And um actually we're we're both co-authoring. This is fun because we're both already authors and finally we've been friends for yea ...

[Music] I'm here today to tell you that there's no onesizefits all memory. Um, and why you need to model your memory after your business domain. So, if you saw me a little bit earlier and I was talking about Graffiti, Zep's open-source temporal graph framework, um, you might have seen me just speak to how you can build custom entities and edges in the graffiti graph for your particular business domain.So, business objects from your business domain. What I'm going to demo today is actually how Zep implements ...

[Music] to quickly introduce myself. My name is Mitesh. I lead the develop advocate team at Nvidia.And the goal of my team is to uh create technical workflows, notebooks uh for different applications and then we release that codebase uh on GitHub. So developers in general which is me and you all of us together we can harness that uh that knowledge and take it further for the application or use case that you're working on. So that is what my uh my team does including myself.In today's talk, I'm I'm I'm going ...

[Music] So, as you come in, we have here a server set up with everything you'll need. If you want to follow along, you should have gotten a post-it note. If you don't, just raise your hand and my colleague Alex over here will come find you and we'll provide you with one.Uh, basically what you're going to do is you're just going to go, if you have a number 160 or below, you go to this link here, the QR code on top as well. Um, and if you have a number that's 2011 or above, you go to the second link or the QR ...

[Music] I'm going to go over today graph rag particularly dealing with multiple data sources. Uh so both unstructured and structured data sources and kind of why you would want to ever do that in the first place even. So I prepared uh some notebooks here.I was going to make slides, but then I thought it would just be easier to walk through some of what this looks like in practice. Um, so there's a link here, and I can share it with you at the booth later, um, if you have follow-up questions. But basically, ...

Problem Statement - Data readiness is a myth, and achieving perfect data for AI is an unattainable pipe dream [1][2][3] - Fortune 500 companies lose an average of $250 million due to poor data quality [7] - Traditional semantic layers and knowledge graphs are insufficient for capturing the nuances of business language and tribal knowledge [8][9][10][11][12][13][14] Solution: Agentic Semantic Layer (PromQL) - PromQL is presented as a "day zero smart analyst" AI system that learns and improves over time through course correction and steering [17][18][19][20] - It uses a domain-specific language (DSL) for data retrieval, computation, aggregation, and semantics, decoupling LLM plan generation from execution [21][22] - The system allows for editing the AI's "brain" to correct its understanding and guide its learning [28] - It incorporates a prompt learning layer to improve the semantic graph and create a company-specific business language [31] - The semantic layer is version controlled, allowing for fallback to previous builds [33] Key Features and Benefits - Correctable, explainable, and steerable AI that improves with use [19] - Ability to handle messy data and understand business context [24][25] - Reduces months of work into immediate start, enabling faster AI deployments [37] - Self-improving and achieves 100% accuracy on complex tasks [37] Demonstrated Capabilities - The system can understand what revenue means and perform calculations [23] - It can identify and correct errors in data, such as incorrect status values [24] - It can integrate data from multiple databases and SAS applications [25][27] - It can summarize support tickets and extract sentiment [26][29] - It can learn the meaning of custom terms and relationships between tables [35][36] Customer Validation - A Fortune 500 food chain company and a high-growth fintech company achieved 100% accurate AI using PromQL [38]

Snowflake (SNOW) Update Summary Company Overview - **Company**: Snowflake Inc. (SNOW) - **Event**: Update/Briefing on June 11, 2025 - **Key Speakers**: Ruby (Head of Partner Marketing for APJ), Mike Garnan (CRO), Ash Willis (VP of Partner Alliance for APJ) Key Points Industry and Market Position - Snowflake is experiencing significant growth, with over 20,000 attendees at their recent summit, doubling their growth from the previous year [4][5] - The company is a sponsor for the LA 2028 Olympics, indicating strong brand visibility and market engagement [7] Financial Performance - Snowflake reported a billion-dollar revenue quarter, representing a **26% year-on-year growth** [18] - The company's **net revenue retention rate** is at **124%**, indicating that existing customers are expanding their contracts [18] - Remaining revenue obligation (RPO) stands at **$6.7 billion**, a **34% year-on-year increase**, suggesting strong future revenue potential [18][24] Customer Engagement and Product Adoption - Snowflake has a total of **11,200 customers**, with **451 new customers** added in Q1 [19] - Approximately **50% of customers** are actively using Snowflake's AI and ML products, showcasing strong adoption of advanced technologies [19] - The company emphasizes the importance of simplifying AI initiatives for customers, which is a key selling point [20] Strategic Focus and Partnerships - Snowflake is focusing on building a robust partner ecosystem to drive consumption and accelerate migrations from legacy systems [25][27] - The company is targeting traditional warehousing technologies like Teradata and Oracle Exadata for migration opportunities [26] - A unique compensation structure is in place where sales teams are incentivized based on consumption rather than contract bookings, aligning interests with customer success [25] AI and Innovation - Snowflake is leveraging AI to enhance productivity and drive business outcomes, with examples of AI applications improving operational efficiency [35][36] - The partnership with Spark New Zealand and Relational AI is highlighted as a strategic move to enhance decision-making capabilities through AI [75][90] Summit Insights - The recent summit showcased a strong network effect, with **70% of content delivered by customers**, emphasizing real-world applications of Snowflake's technology [40] - The event attracted a diverse audience, including business leaders and technical experts, indicating a shift towards business impact rather than just technology [39] Future Outlook - Snowflake plans to invest significantly in its partner ecosystem, including traditional resellers and systems integrators, to scale its business efficiently [48][50] - The company aims to activate its channel to potentially exceed **35% growth** in the future [52] Customer Case Studies - Spark New Zealand is leveraging AI to streamline processes, such as call summarization, which enhances data quality and operational efficiency [84][89] - Relational AI is working with Snowflake to create a relational knowledge graph, addressing knowledge silos within organizations [97][100] Additional Insights - The emphasis on AI is not about job replacement but enhancing productivity and enabling existing employees to work more efficiently [35][36] - The partnership approach is seen as crucial for future innovation, with a focus on collaborative growth and shared success [109][110] This summary encapsulates the key insights and strategic directions discussed during the Snowflake update, highlighting the company's robust growth, innovative use of AI, and commitment to building a strong partner ecosystem.