Keynote: Unlocking Corporate Data with Retrieval-Augmented Generation
Talkat Cassandra Summit 2023 · on Tuesday, 2023-12-12· at 09:15· Grand Ballroom BC (Concourse Exhibit Level)·
summary
Retrieval-augmented generation handles simple fact lookup but fails on multi‑step comparison, SQL‑style filtering, and structured analytics; solution is an LLM agent layer that decomposes queries, selects tools, and calls a RAG pipeline as a tool. The framework demos a five‑line LlamaIndex quickstart, implements ReAct‑style reasoning, and ships a dogfooded open‑source SEC insights template (MIT) that wires agent + RAG into a full‑stack app with PDF viewer, citations, and working end‑to‑end results.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 0:43LlamaIndex and RAG
- 2:28Naive RAG limitations
- 4:11Agents for complex queries
- 5:36Agents enhance RAG
- 7:04Agent-based RAG components
- 7:47Financial analysis with RAG
- 8:50Enterprise RAG resources
- 10:16Call to action
related talks
10mKeynote: Unlocking Corporate Data with Retrieval-Augmented Generation
50mRetrieval Augmented Generation Beyond Toy Demos
53mFrom RAG to Riches: Secrets of Data-Augmented LLMs
48mGoing Beyond Prompt Engineering
15mRAG Beyond Chatbots
01h 30mOptimizing Retrieval for Agentic Systems
48mAn Introduction to Retrieval Augmented Generation
21mHow RAG is Redefining AI Capabilities