Anton Troynikov, cofounder of Chroma, joins Nathan Labenz to discuss the importance of keeping the retrieval-augmented generation (RAG) loop in house, what it means for Chroma to be in “wartime” mode right now, and how much of the data going into Chroma has never been in a database before. If you need an ERP platform, check out our sponsor NetSuite: http://netsuite.com/cognitive.

SPONSORS: NetSuite | Omneky
NetSuite has 25 years of providing financial software for all your business needs. More than 36,000 businesses have already upgraded to NetSuite by Oracle, gaining visibility and control over their financials, inventory, HR, eCommerce, and more. If you're looking for an ERP platform ✅ head to NetSuite: http://netsuite.com/cognitive and download your own customized KPI checklist.

Omneky is an omnichannel creative generation platform that lets you launch hundreds of thousands of ad iterations that actually work customized across all platforms, with a click of a button. Omneky combines generative AI and real-time advertising data. Mention "Cog Rev" for 10% off.

LINKS:
Part 1 with Anton: https://youtu.be/ogy37CdIljg

X/SOCIAL:
@labenz (Nathan)
@atroyn (Anton)
@eriktorenberg (Erik)
@CogRev_Podcast

TIMESTAMPS:
(00:00:00) - Introduction by Nathan, setting up the conversation with Anton
(00:02:16) - Anton articulates Chroma's mission to build a horizontally scalable system
(00:03:06) - Rise in popularity of retrieval-augmented generation (RAG)
(00:05:00) - Anton explains what it means for Chroma to be in "wartime" mode right now
(00:06:03) - Chroma's focus on delivering a horizontally scalable cloud service for vector search and storage
(00:08:07) - Nathan describes his experience building a RAG application for a client profiling use case
(00:10:27) - Anton advises measuring retrieval quality and maximizing relevant information returned
(00:15:05) - Sponsors: Netsuite | Omneky
(00:17:02) - Popular use of open source vs. proprietary embedding models like Anthropic's Ada
(00:19:30) - The importance of keeping the RAG loop in house and not relying solely on external APIs
(00:23:31) - Approaches for adapting the embedding space based on user feedback
(00:27:41) - The huge amount of unstructured data that can now be processed by AI
(00:30:40) - Providing a unified interface to structured and unstructured data
(00:31:21) - Chroma's plans to bring more intelligence into the data layer
(00:32:13) - Analogies to Salesforce and Oracle in enterprise software partnerships
(00:33:15) - Much of the data going into Chroma has never been in a database before
(00:38:47) - Categories of organizations adapting to AI: legacy, AI-native, and AI-first
(00:40:55) - Where Chroma is seeing most of its growth right now
(00:42:48) - Retrieval as an important component for developing good agents
(00:46:20) - Interpretability work like Anthropic's circuit evaluation
(00:52:23) - Anton believes new tooling can make latent spaces accessible without AI expertise
(01:03:32) - Thinking of data as a control loop rather than static
(01:06:08) - Scaling constraints between search indexes vs. application databases
(01:09:10) - Potential for time as a dimension in embedding spaces
(01:10:55) - Language models discovering implicit representations of time and space
(01:13:46) - Likelihood of missing results due to representational issues vs. approximate nearest neighbor
(01:15:22) - Automatically handling small data sets without needing elaborate indexing
(01:16:11) - Partnerships with AI labs to mutually reinforce RAG applications
(01:17:20) - Anton's perspective on whether OpenAI will build its own database
(01:19:43) - Partnering with OpenAI and other labs to increase use of their models
(01:21:19) - Anton's experiments probing GPT's reasoning abilities with Game of Life
(01:25:41) - Closing thoughts on the conversation