SF Unstructured Data Meetup February 20 2024
🎥 Once a month, we'll meet, socialize, and hear speakers present topics on unstructured data and generative AI.
Timeline:
0:57 - Speaker Yury Malkov, Approximate Nearest Neighbor Search in Recommender Systems
27:31 - Speakers Jithin James and Shahul Es, Metrics Driven Development of RAGs
55:27 - Speaker Hakan Tekgul, LLM System Evaluations and Observability
1:18:54 - Speaker Nikon Rasumov, https://maxime.tools, Legal LLM + Due Diligence tool, built on Milvus and Zilliz
~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~
🎥 Playlist https://www.youtube.com/playlist?list=PLPg7_faNDlT7SC3HxWShxKT-t-u7uKr--
🖥️ Website: https://www.meetup.com/unstructured-data-bay-area/events/
X Twitter - https://twitter.com/milvusio
🔗 Linkedin: https://www.linkedin.com/company/zilliz
😺 GitHub: https://github.com/milvus-io/milvus
🦾 Invitation to join discord: https://discord.gg/FjCMmaJng6
~~~~~~~~~~~~~~ MEETUP VIDEO CONTENTS ~~~~~~~~~~~~~~
1. Host: Christy Bergman
Linkedin: https://www.linkedin.com/in/christybergman/
2. Speaker: Yury Malkov, Research Scientist at OpenAI
Title: Approximate Nearest Neighbor Search in Recommender Systems
Abstract: I am going to discuss problems and research regarding Approximate Nearest Neighbor Search in Recommender Systems. In particular, the role of fast Approximate Nearest Neighbor (ANN) search in the multi-stage funnel design or a typical Recommender System. I'll discuss research on ANN search with neural ranking distances and its impact on the end-to-end funnel design.
3. Speakers: Jithin James, CEO and Shahul ES, Co-Founder, Ragas
Title: Metrics Driven Development of RAGs
Abstract: We will be walking through a RAG application from scratch with a metrics-driven approach. We'll start off with a very basic RAG system, identify problem areas, and make improvements along the way guided by proper evaluations of the RAG pipeline. Hopefully you will see how you can make more informed decisions during the development cycle, pre-deployment.
4. Speaker: Hakan Tekgul
Title: Path to Production: LLM System Evaluations and Observability
Abstract: Over half (53.3%) of machine learning teams are planning production deployments of LLMs in the next year, but many continue to cite issues like hallucinations and responsible deployment as barriers in moving LLM-powered systems into the real world. In evaluating LLM-powered apps, human feedback is paramount – but in practice is not available for most. This talk covers how teams can achieve fast and accurate LLM-assisted evaluations and apply data science rigor to the testing of model and template combinations post-deployment.
5. Community Demo: Nikon Rasumov gave a demo of Maxime Tools, https://maxime.tools/, a Legal LLM + Due Diligence tool, built on Milvus and Zilliz. Upload thousands of legal documents. Gather prompt-engineered questions and download all the best possible answers all at once, neatly organized in a spreadsheet! This is a Legal Chatbot on steroids, powered by prompt engineering.
社交媒体聆听
SF Unstructured Data Meetup February 20 2024
🎥 Once a month, we'll meet, socialize, and hear speakers present topics on unstructured data and generative AI. Timeline: 0:57 - Speaker Yury Malkov, Approximate Nearest Neighbor Search in Recommender Systems 27:31 - Speakers Jithin James and Shahul Es, Metrics Driven Development of RAGs 55:27 - Speaker Hakan Tekgul, LLM System Evaluations and Observability 1:18:54 - Speaker Nikon Rasumov, https://maxime.tools, Legal LLM + Due Diligence tool, built on Milvus and Zilliz ~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~ 🎥 Playlist https://www.youtube.com/playlist?list=PLPg7_faNDlT7SC3HxWShxKT-t-u7uKr-- 🖥️ Website: https://www.meetup.com/unstructured-data-bay-area/events/ X Twitter - https://twitter.com/milvusio 🔗 Linkedin: https://www.linkedin.com/company/zilliz 😺 GitHub: https://github.com/milvus-io/milvus 🦾 Invitation to join discord: https://discord.gg/FjCMmaJng6 ~~~~~~~~~~~~~~ MEETUP VIDEO CONTENTS ~~~~~~~~~~~~~~ 1. Host: Christy Bergman Linkedin: https://www.linkedin.com/in/christybergman/ 2. Speaker: Yury Malkov, Research Scientist at OpenAI Title: Approximate Nearest Neighbor Search in Recommender Systems Abstract: I am going to discuss problems and research regarding Approximate Nearest Neighbor Search in Recommender Systems. In particular, the role of fast Approximate Nearest Neighbor (ANN) search in the multi-stage funnel design or a typical Recommender System. I'll discuss research on ANN search with neural ranking distances and its impact on the end-to-end funnel design. 3. Speakers: Jithin James, CEO and Shahul ES, Co-Founder, Ragas Title: Metrics Driven Development of RAGs Abstract: We will be walking through a RAG application from scratch with a metrics-driven approach. We'll start off with a very basic RAG system, identify problem areas, and make improvements along the way guided by proper evaluations of the RAG pipeline. Hopefully you will see how you can make more informed decisions during the development cycle, pre-deployment. 4. Speaker: Hakan Tekgul Title: Path to Production: LLM System Evaluations and Observability Abstract: Over half (53.3%) of machine learning teams are planning production deployments of LLMs in the next year, but many continue to cite issues like hallucinations and responsible deployment as barriers in moving LLM-powered systems into the real world. In evaluating LLM-powered apps, human feedback is paramount – but in practice is not available for most. This talk covers how teams can achieve fast and accurate LLM-assisted evaluations and apply data science rigor to the testing of model and template combinations post-deployment. 5. Community Demo: Nikon Rasumov gave a demo of Maxime Tools, https://maxime.tools/, a Legal LLM + Due Diligence tool, built on Milvus and Zilliz. Upload thousands of legal documents. Gather prompt-engineered questions and download all the best possible answers all at once, neatly organized in a spreadsheet! This is a Legal Chatbot on steroids, powered by prompt engineering.