Weaviate Podcast

Join the 97th Weaviate Podcast with Nils Reimers and Erika Cardenas as they delve into AI-powered search technology. Topics include Compass embeddings, multi-aspect chunking, ColBERT, RAG Evaluation, and more. Discover the challenges and solutions in embeddings, LLMs, smart chunking strategies, evaluating chatbots, and optimizing vector databases with quantization methods.

Letitia Parcalabescu, a Ph.D. student at the University of Heidelberg and creator of the YouTube channel AI Coffee Break, shares insights on AI and content creation. She discusses the evolution of deep learning, emphasizing the shift from traditional models to transformers. The conversation dives into innovative techniques in algorithm optimization and the complexities of large language models. Letitia also highlights the new Mamba architecture and the future of multimodal AI, advocating for a balance between AI capabilities and human oversight.

Dai Vu, a representative from Google specializing in cloud technologies, teams up with Bob van Luijt, Co-Founder of Weaviate. They dive into the evolving Google Cloud Marketplace, discussing advancements in AI and the rise of open-source models. The conversation highlights how AI-native applications are reshaping data services and cloud strategies. Dai shares his 'aha' moment in AI, while they both explore the future of specialized language models and the critical interplay of data gravity in cloud computing.

Join Magdalen Dobson Manohar, a brilliant scientist, on a journey into Approximate Nearest Neighbor Search. Explore topics like Parallel Computing, Lock Contention in HNSW, ParlayANN development, Filtered Vector Search, and exciting future directions in Vector Search technology.

Kyle Davis, the creator of RAGKit, discusses RAG systems covering topics like Knowledge Graph RAG, Function Calling, Tool Selection, Re-ranking, and Quantization. The discussion challenges traditional views on 'Agents' and aims to provide clarity for those working with LLMs / Generative AI.

Entrepreneur David de Matheu discusses pivoting from Neum AI to VetRec focusing on RAG technology for Veterinarians, ETL space, and technical opportunities. They explore transitioning to new domains, optimizing workflow efficiency, and enhancing veterinary diagnosis with connected systems. The podcast delves into challenges faced by developers, evolution of data work perception, and the value of external solutions in the industry.

Tengyu Ma, Co-Founder of Voyage AI and Assistant Professor at Stanford University, discusses embedding model training, contrastive learning theory, fine-tuning models for Langchain documentation, challenges in serving embeddings API, and optimizations for query inference and batch embeddings on the Weaviate Podcast.

Explore the innovative self-discovery feature in DSPy, enhancing problem-solving with reasoning modules, and the importance of human-AI collaboration. Learn about Chris Dossman's Self-Discover implementation in DSPy and his entrepreneurial journey in the AI field. Dive into the evolving landscape of Artificial Intelligence and the exciting advancements in AI technology.

Join the 89th Weaviate Podcast on Matryoshka Embeddings with Aditya Kusupati, Zach Nussbaum, and Zain Hasan. Learn about challenges in training Matryoshka embeddings, experiences building embeddings API, Aditya's research on differentiable ANN indexes, and more!

Jason Liu, creator of Instructor, a leading LLM framework, discusses the benefits of structured output parsing with language models and the future of function calling. The podcast also explores selecting tools, organizing prompts, using Go library for reranking, and the capabilities of modal API for serverless GPU compute. The importance of fine-tuning embedding models for improved performance is emphasized.