Скачать с ютуб LIVE! Feb SF Unstructured Data Meetup в хорошем качестве

LIVE! Feb SF Unstructured Data Meetup

​​​5:30 - 6:00 - Welcome/Networking/Registration 6:00 - 6:20 - Stefan Webb, Combining Lexical and Semantic Search with Milvus 2.5 6:20 - 6:40 - Arnab Sinha & Jean Malha, Come learn about Bedrock’s Latest feature: Bedrock Data Automation (Preview) to simplify processing unstructured data 6.40 - 7:00 - Anushrut Gupta, Pushing AI's accuracy on unstructured data to 100% with PromptQL 7:00 - 8:30 - Milvus Office hours and networking Tech Talk 1: Combining Lexical and Semantic Search with Milvus 2.5 Speaker: Stefan Webb, DevRel, Zilliz Abstract: In short, lexical search is a way to search your documents based on the keywords they contain, in contrast to semantic search, which compares the similarity of embeddings. We’ll be covering: ​- Why, when, and how should you use lexical search ​- What is the BM25 distance metric ​- How exactly does Milvus 2.5 implement lexical search ​- How to build an improved hybrid lexical + semantic search with Milvus 2.5 ​Tech Talk 2: Come learn about Bedrock’s Latest feature: Bedrock Data Automation (Preview) to simplify processing unstructured data Speakers: Arnab Sinha (Senior Solutions Architect) & Jean Malha (Senior Specialist Solutions Architect), AWS Bedrock Abstract: Bedrock Data Automation (BDA) is a cloud-based service that simplifies the process of extracting valuable insights from unstructured content—such as documents, images, video, and audio. Come learn how BDA leverages generative AI to automate the transformation of multi-modal data into structured formats, enabling developers to build applications and automate complex workflows with greater speed and accuracy. ​Tech Talk 3: Pushing AI's accuracy on unstructured data to 100% with PromptQL Speaker: Anushrut Gupta, Product Lead, Generative AI, Hasura Abstract: Explore a next-gen approach with dynamic query planning, programmatic runtime and structured memory that dramatically outperforms traditional RAG techniques. Learn how this approach transforms the integration of unstructured data—from vector databases and text corpora to large-scale document repositories—delivering 100% accuracy in benchmarks and ensuring robust, repeatable, and scalable results.