0-10 subscribers
Gå offline med appen Player FM !
Podcasts der er værd at lytte til
SPONSORERET


Jeff Huber of Chroma: Building the open-source toolkit for AI Engineering
Manage episode 446639343 series 3586305
This week on High Agency, Raza Habib is joined by Chroma founder Jeff Huber. They cover the evolution of vector databases in AI engineering, challenge common assumptions about RAG and share insights from Chroma's journey. Jeff shares insights from Chroma's development, including their focus on developer experience and observations about real-world usage patterns. They also get into whether or not we can expect a super AI any time soon and what is over and under hyped in the industry today.
00:00 - Introduction
02:30 - Why vector databases matter for AI
06:00 - Understanding embeddings and similarity search
12:00 - Chroma early days
15:45 - Problems with existing vector database solutions
19:30 - Workload patterns in AI applications
23:40 - Real-world use cases and search applications
27:15 - The problem with RAG terminology
31:45 - Dynamic retrieval and model interactions
35:30 - Email processing and instruction management
39:15 - Context windows vs vector databases
42:30 - Enterprise adoption and production systems
45:45 - The journey from GPT-3 to production AI
48:15 - Internal vs customer-facing applications
51:00 - Advice for AI engineers
--------------------------------------------------------------------------------------------------------------------------------------------------
Humanloop is an Integrated Development Environment for Large Language Models. It enables product teams to develop LLM-based applications that are reliable and scalable. To find out more go to humanloop.com
32 episoder
Manage episode 446639343 series 3586305
This week on High Agency, Raza Habib is joined by Chroma founder Jeff Huber. They cover the evolution of vector databases in AI engineering, challenge common assumptions about RAG and share insights from Chroma's journey. Jeff shares insights from Chroma's development, including their focus on developer experience and observations about real-world usage patterns. They also get into whether or not we can expect a super AI any time soon and what is over and under hyped in the industry today.
00:00 - Introduction
02:30 - Why vector databases matter for AI
06:00 - Understanding embeddings and similarity search
12:00 - Chroma early days
15:45 - Problems with existing vector database solutions
19:30 - Workload patterns in AI applications
23:40 - Real-world use cases and search applications
27:15 - The problem with RAG terminology
31:45 - Dynamic retrieval and model interactions
35:30 - Email processing and instruction management
39:15 - Context windows vs vector databases
42:30 - Enterprise adoption and production systems
45:45 - The journey from GPT-3 to production AI
48:15 - Internal vs customer-facing applications
51:00 - Advice for AI engineers
--------------------------------------------------------------------------------------------------------------------------------------------------
Humanloop is an Integrated Development Environment for Large Language Models. It enables product teams to develop LLM-based applications that are reliable and scalable. To find out more go to humanloop.com
32 episoder
Alle episoder
×
1 From 0 to $40M in 5 Months: Bolt.new Story with Eric Simons 41:33

1 Saving Pharma Companies Billions with AI l Patrick Leung from Faro Health 48:04

1 100x Hiring Speed with Superhuman Recruiters l Metaview Co-Founder 53:07

1 AI Will Replace Command Lines I Ex-Google Tech Lead and Founder at Warp 47:45

1 Google Is Dead: How This 144-GPU Startup Is Building Einstein-Level AI Search I Will Bryk | Exa CEO 38:44

1 $100M raised: How Decagon is building better AI agents I Jesse Zhang 41:45

1 How GitHub Copilot Became the First LLM-Powered Developer Tool with Ryan Salva 38:53

1 What Gives an AI Founder Staying Power I James Theuerkauf, CEO of Syrup Tech I Sara Ittelson, Partner at Accel 43:36

1 How to build great AI products with Vanta Software Developer Noam Rubin 40:57

1 Predictions for AI in 2025 I Ex-OpenAI, Ex-Stripe researcher Stanislav Polu 44:27

1 How Replicate is Democratizing AI with Open-Source Resources 36:15

1 The Principles for Building Excellent AI Features with Superhuman’s Lorilyn McCue 42:35

1 Jeff Huber of Chroma: Building the open-source toolkit for AI Engineering 54:59

1 How to Create AI Strategy in Enterprises with Peter Gostev from Moonpig 39:54

1 Ex-Coinbase CPO's Next Big Thing: AI Employees I Surojit Chatterjee 44:43

1 Why Your AI Product Needs Evals with Hamel Husain and Swyx 1:09:02

1 How AI is Changing Product Management with Raz Nussbaum from Gong AI 30:03

1 From Fiction to Reality: Sudowrite's Journey in AI-Assisted Creative Writing 56:43

1 Building the Nervous System for AI with Russ d'Sa from LiveKit 49:29

1 From PyTorch to Fireworks AI: Lin Qiao on Building AI Infrastructure 41:30

1 How Paras Jain is building the future of AI video creation 48:45

1 AI at Scale: Lessons from Gusto's $9.5 billion journey with Eddie Kim & Ali Rowghani 55:57

1 Building the first LLM-based search engine for developers with Michael Royzen 57:08

1 Contrarian Guide to AI: Jason Liu on Betting Against Agents while Doubling Down on RAG & Fine-Tuning 55:27

1 What comes after Open AI? Logan Kilpatrick on how you should prepare for the future of LLMs 44:37

1 AI's Memory Upgrade: Max Rumpf on how to build advanced RAG systems 46:47

1 Building AI Products at Scale: Lessons from Zapier's CEO 40:51


1 Building an AI coding assistant with Beyang Liu CTO of Sourcegraph 51:01

1 Evaluating LLMs the Right Way: Lessons from Hex's Journey 45:39

1 Building reliable AI agents with Cai GoGwilt CTO of Ironclad 51:04

Velkommen til Player FM!
Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.