Weaviate Podcast

Hey everyone! Thank you so much for watching the Generative Feedback Loops Podcast! We have also created a blog post and GitHub repository for more information! Chapters 0:00 Bob the Podcast Host 1:20 Retrieval-Augmented Generation 4:10 Hallucination in LLMs 6:15 Solving Hallucination with RLHF 7:44 LLM Monster - Reasoning and Knowledge 10:12 Feedback Loops 11:00 Hands-on Code Demo 26:00 Demo Analysis from Bob and Connor 30:35 Star Wars Wes Anderson Generated Video 34:12 Multimodal Vector Databases 36:00 Speculative Design Theory Links: John Schulman - Reinforcement Learning from Human Feedback: Progress and Challenges: https://www.youtube.com/watch?v=hhiLw5Q_UFg Colin Nesh (HaystackUS 2023 slide deck) - Ground is NOT all you need, Stop hallucinations & defects in generative search: https://docs.google.com/presentation/d/1uycLEUeRuF8A85Uso_A3OU6EF-qq4aYswWVxkPWHBKI/edit#slide=id.p Generative Starwars video source - https://twitter.com/CuriousRefuge/status/1652412004626497536 Speculative Design Theory - https://readings.design/PDF/speculative-everything.pdf Aggregation Theory - https://stratechery.com/aggregation-theory/

Hey everyone! Thank you so much for watching the Weaviate 1.19 release podcast! We have all sorts of cool new features, in addition to the database and module features, I really want to encourage readers to see the `groupBy` search discussed at 14:32, quite an interesting idea for improving search performance! Chapters 0:00 Welcome Etienne! 0:38 gRPC API 9:50 Generative Cohere 14:32 groupBy search 19:33 Bitmap or BM25 index tuning 22:20 Additional Tokenization Options 24:05 Tunable Consistency

Thank you so much for watching the 43rd episode of the Weaviate Podcast with Roman Grebennikov and Vesvolod Goloviznin from Metarank, as well as Erika Cardenas from Weaviate! This podcast is a masterclass on Ranking models, additionally touching on the connection between Search and Recommendation. Learning-to-rank is an exciting idea where we use models that produce more fine-grained relevance scores than the offline indexing techniques of vector search and bm25, however with the tradeoff of the speed of these inferences. Romand and Vsevolod touched on another extremely interesting part of these ranking models which is the estimation of features such as Click-through-Rates and how they use streaming technology to do this. I learned so much from this podcast about the directions in ranking, I hope you enjoy it as well! As always, we are more than happy to answer any questions or discuss any ideas with you! In reflecting on this podcast, Erika and I wrote up our latest thoughts on Ranking Models in a Weaviate blogpost, check it out here if interested: https://weaviate.io/blog/ranking-models-for-better-search. Chapters 0:00 Welcome Everyone! 0:40 Recommendation with Weaviate 4:20 Metarank - Founding Story 8:20 Ranking MLOps 9:52 User Friendliness Perspective 15:10 Retrieval vs. Ranking 17:45 Ranking Optimization 25:20 Multi-Vector Object Representations 27:55 Click-through-Rate Feature Streaming 33:06 Weaviate Properties vs. Feature Stores 40:06 Cold-Start Recommendation Problem 46:04 Ranklens Demo - RecSys Datasets 52:02 Cross Encoders

Thank you so much for watching the 42nd episode of the Weaviate Podcast! Ethan Steininger is the founder of Mixpeek, an intelligence layer that sits on top of your S3 bucket, so you can search and analyze unstructured data at scale. Ethan has also created Collie with the headline of "Enter your website and Collie will fetch every asset, then give you an embedded search bar that wows your users". Ethan began the podcast by describing his background at MongoDB and integrating the database with full text search functionality. Ethan then presented the founding vision of Mixpeek and some of the most outstanding problems with adapting the latest AI technologies to solve business problems. This lead us to discuss a massive range of topics around the AI landscape from the Llama / Alpaca models to ChatGPT Plugins, the paradigm shift in coding and serverless GPUs. I really enjoyed speaking with Ethan about all these things, I hope you enjoy listening! We would more than happy to discuss any ideas you have with you or answer any questions, thanks again for watching! Chapters 0:00 Welcome Ethan Steininger! 0:50 Entry into Search from MongoDB 6:45 Founding Vision of Mixpeek 10:15 Data Ingestion 13:45 ChatGPT Plugins 16:25 Paradigm shift in Coding with GPT-4 18:54 Alpaca Models 22:42 Tuning LLMs with Retrieval 31:45 Adding Structure to Code Repo Search 35:06 Re-Ranking / Learning-to-Rank 43:30 AGI Monopoly 49:10 Hybrid Search! Zero-Shot + BM25 54:20 Open-Source Business 59:35 Serverless GPUs 1:11:18 Ethan’s Advice for Stress Management 1:13:00 Existential AI Fear Links: Mixpeek - https://mixpeek.com/ Collie - https://collie.ai/ An Open-Source, Personalized Generative Model Framework - https://esteininger.medium.com/an-open-source-personalized-generative-model-framework-6df865de51bf Teaching GPT-4 to write code from research papers - https://esteininger.medium.com/teaching-gpt-4-to-write-code-from-research-papers-889a880fb4f0 The Need for an AI Content Verification Layer - https://esteininger.medium.com/the-need-for-an-ai-content-verification-layer-10be9379b354 Building the ML Stack of the Future - https://esteininger.medium.com/building-the-ml-stack-of-the-future-d66c8a8b566a Vertical Integration is Key to Winning the AI Race - https://esteininger.medium.com/vertical-integration-is-key-to-winning-the-ai-race-44c8e4bd3b30

Chapters 0:00 Welcome Dennis Xu! 0:30 Founding Vision of Mem 4:18 Personalized Embeddings 6:02 GPT-4, How will this change everything? 11:00 Writing code with LLMs 13:18 Embeddings at Mem 17:10 Structure in Vector Search 19:10 Zero-Shot vs. Fine-Tuned Models 25:05 Ranking Models and LLM Distillation

Chapters 0:00 Weaviate 1.18!!! 0:32 Bitmap Indexing! 11:40 HNSW PQ 25:33 Cursor API 30:03 Filters in Hybrid Search 32:55 WAND Scoring 40:35 Replication 49:10 Building a Database in Golang 1:00:55 Thank you!

Check out the website here! https://openverkiezingen.nl/

Hey everyone! Thank you so much for watching the 38th episode of the Weaviate podcast! This episode features Leo Boystov, an expert in Information Retrieval technology! We discussed a very wide range of topics from an overview of IR methods such as BM25, Neural Bi-Encoder and Cross-Encoder rankers, and a super exciting new work Leo has co-authored on using Large Language Models to generate training data for Neural Ranking models titled "InPars-Light: Cost-Effective Unsupervised Training of Efficient Rankers." We also discussed Leo's work on Non-Metric Space Search, the challenge of long document ranking, Robustness in Generalization Testing, and ended with some thoughts on Hybrid Rank Fusion. I really hope you enjoy the podcast, more than happy to answer any questions you have or clarify anything! In-Pars Light: Cost-Effective Unsupervised Training of Efficient Rankers - https://arxiv.org/abs/2301.02998 Google Scholar Leo Boystov - https://scholar.google.com/citations?... Chapters 0:00 Introduction 1:08 Information Retrieval Research 25:20 Ranker Inference Requirements 40:40 Non Metric Space Search 52:38 Code Libraries for IR Research 59:40 Long Document Ranking 1:07:00 Robustness Generalization 1:15:40 Hybrid Rank Fusion

Hey everyone! Thank you so much for watching the 37th episode of the Weaviate podcast! This episode discusses some of the ideas behind GPT Index. GPT Index presents really exciting ideas about how we use LLMs to index our data and then traverse these data structures. We began the podcast by discussing the origins of the tool and the ideas behind the Tree Index. We then discussed generalizing these trees to graphs and whether we are headed to the Knowledge Graph 2.0. Another really interesting topic we covered is the inference cost of building and traversing LLM indices like this! I really hope you enjoy this podcast I think these are some of the most cutting edge ideas in AI and Search! Check out GPT Index (now LlamaIndex here - https://gpt-index.readthedocs.io/en/l...) Chapters 0:00 Introduction 0:18 Origin Story of GPT Index 2:22 GPT Tree Index 5:53 Search Examples - Podcast Clips 11:22 Knowledge Graph 2.0? 16:05 LLM Writing Data to DB 20:18 Weaviate Classes and Index Hierarchy 23:53 Subindices vs. Tool Use 28:50 Inference Requirements for GPT Index 35:53 Design of GPT Index 37:40 Impact of Cheaper LLMs for this 40:02 Name Change for GPT Index? 42:04 Llama Hub 45:07 Relationship in Software Stack 48:15 Extension to Multimodal, e.g. Vision-Language

Hey everyone! Thank you so much for watching the 36th episode of the Weaviate podcast! This episode continues on the marriage between LLMs and Semantic Search, welcoming back Weaviate CEO and Co-Founder Bob van Luijt! Enter LangChain and its creator, Harrison Chase, providing the glue between LLMs and tools, such as semantic search. LangChain provides a set of abstractions around chaining multiple language model calls with different prompts, strategies for overcoming the 4096 token limit, and connecting LLMs with their tools. LangChain Hub is a collection of these chains if you want to check it out yourself! Huge thank you to Harrison and Bob for joining the podcast, this was such an information packed podcast with some great predictions for the future of LLMs + Vector Databases!   Check out LangChain here! https://langchain.readthedocs.io/en/latest/ Chapters 0:00 Welcome 0:14 Origin Story of LangChain 1:27 What are LLM Chains? 4:00 Adding Weaviate Search 7:30 LLM Orchestration and Tool Use 11:24 Extension to Multi-Modal 14:00 Natural Language Interaction with Software 20:36 Will Prompt Engineering Last? 21:00 More on Tool Use 25:47 Favorite Prompts 29:54 Temperature in LLMs 31:00 Reasoning and Knowledge 32:50 LLM as Router 35:50 Model Diversity 39:45 No GPUs before PMF 41:35 Virality of LangChain 43:40 Future of LangChain