Video Description

A huge promise for LLMs is being able to answer questions and solve tasks of arbitrary complexity over an arbitrary number of data sources. The world has started to shift from simple RAG stacks, which are mostly good for answering pointed questions, to agents that can more autonomously reason over a diverse set of inputs over complex multi-modal data, and interleave retrieval and tool use to produce sophisticated outputs. In this talk we talk about the core ingredients needed to build an advanced, agentic knowledge assistant: good data/retrieval, an agent layer to process inputs, more sophisticated output generation, and full-stack/deployment tooling. Slides linked here: https://www.figma.com/slides/frXiHyeq5kjU1wU5Jx5LWR/From-RAG-to-Knowledge-Assistants-(October-22-2024)?node-id=66-320&t=sBPRcGUxJJ4JmqVk-1 LlamaCloud signup: https://cloud.llamaindex.ai/ For enterprise usage, come talk to us: https://www.llamaindex.ai/contact