🎥 Once a month, we'll meet, socialize, and hear speakers present topics on unstructured data and generative AI. This event was sponsored by Zilliz and Arize AI.
Timeline:
01:00 - Speaker Jiang Chen, Improving RAG with Knowledge Graph + Multimodality + Milvus
15:11 - Speaker Yi Ding, Small to Slide: RAG using MultiModal LLMs
46:58 - Speaker Kunal Sonalkar, Transformers4rec: Harnessing NLP Advancements for Cutting-Edge Recommender Systems
01:06:45 - Speaker Hakan Tekgul, Evaluating RAG pipelines built on unstructured data
~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~
🎥 Playlist [ Ссылка ]--
🖥️ Website: [ Ссылка ]
X Twitter - [ Ссылка ]
🔗 Linkedin: [ Ссылка ]
😺 GitHub: [ Ссылка ]
🦾 Invitation to join discord: [ Ссылка ]
~~~~~~~~~~~~~~ MEETUP VIDEO CONTENTS ~~~~~~~~~~~~~~
1. Host & Speaker 1: Jiang Chen, Head of Ecosystem and Developer Relations, Zilliz
LinkedIn: [ Ссылка ]
Talk title: Improving RAG with Knowledge Graph + Multi-modality + Milvus
Slides: [ Ссылка ]
2. Speaker 2: Yi Ding, ex-LlamaIndex TS
LinkedIn: [ Ссылка ]
Talk Title: Small to Slide: RAG using MultiModal LLMs.
Abstract: With the advent of LLMs understanding multimodal inputs, document understanding has a new tool in the arsenal. Elliot Kang and I built an example using Milvus and a real slide deck to show how you can use retrieval in combination with multimodal input to get better results from your existing powerpoint slides.
Slides: [ Ссылка ]
3. Speaker 3: Kunal Sonalkar, Data Scientist, Nordstrom
LinkedIn: [ Ссылка ]
Talk title: Transformers4rec: Harnessing NLP Advancements for Cutting-Edge Recommender Systems
Abstract: Transformers4rec is a powerful open-source library by NVIDIA that bridges the gap between natural language processing (NLP) and recommender systems. We will review how it leverages state-of-the-art Transformer architectures from NLP to enhance sequential and session-based recommendation tasks.
Slides: [ Ссылка ]
4. Speaker 4: Hakan Tekgul, Solutions Architect, Arize
LinkedIn: [ Ссылка ]
Talk title: Evaluating RAG pipelines built on unstructured data
Abstract: This talk will cover different techniques for evaluating a RAG pipeline built on unstructured data. Standing up a basic RAG pipeline is becoming easier every day, however identifying weak points in your application or dataset remains a challenge. We'll review how you can use traditional assertion-based evaluation techniques, LLM-as-a-Judge approaches, and embedding visualization tools to improve your pipeline using Arize Phoenix.
Slides: [ Ссылка ]
