Using Kaskada to Do Real Time AI
summary
Kaskada is an open source Python + Rust framework (Apache Arrow for processing) that converts event timelines into features and native time travel for ML so you can audit model inputs. Demo shows using Astra Cassandra, OpenAI Ada-002 embeddings and a 1,500‑dim vector per question to build a RAG chatbot in 5 minutes by storing SQuAD vectors, nearest‑neighboring the top 3 hits, and sending those to GPT‑3.5. Claims: rewrote 63 pages of Spark code into two pages, often an order‑of‑magnitude faster than DuckDB, and native vector search parity beating Pinecone on latency and throughput.
AI-written summary · about
chapters (12)
- 0:00Kaskada and real-time AI
- 4:54What is Kaskada
- 6:43Time-series data with Kaskada
- 11:42Predictive ML with Kaskada
- 12:43Generative AI and RAG
- 14:53Live RAG chatbot demo
- 23:10Real-time + generative AI
- 26:18Slack bot example
- 30:30AI democratization challenges
- 31:12Changing app stacks
- 35:51Modern data platforms
- 39:45Cassandra 5 features
related talks
41mUsing Kaskada to Do Real Time AI
33mUsing Kaskada to do Real Time Machine Learning
40mOvercoming data infrastructure limitations with a new paradigm for ML
58mAI-Enhanced Big Data: Integrating Private LLMs and Vector Databases
45mManaging Data & Analytics Projects Effectively
18mKeynote: Data = AI: Leading the Future of Gen AI with Apache Cassandra
19mBuild Real time, AI powered Apps
57mEnter The Brave New World of GenAI with Vector Search