Going Meta – Ep 27: Building a Reflection Agent with LangGraph

27 Mar, 2024



Episode 27 of Going Meta – a series on graphs, semantics and knowledge Jesús Barrasa: https://twitter.com/BarrasaDV Repository: https://github.com/jbarrasa/goingmeta Knowledge Graph Book: https://neo4j.com/knowledge-graphs-practitioners-guide/ Previous Episodes: https://neo4j.com/video/going-meta-a-series-on-graphs-semantics-and-knowledge/ Links: GenAI Ecosystem: https://neo4j.com/labs/genai-ecosystem/ Is RAG dead? https://docs.google.com/presentation/d/1mJUiPBdtf58NfuSEQ7pVSEQ2Oqmek7F1i4gBwR6JDss/edit#slide=id.g26c0cb8dc66_0_131 What’s next for AI agentic workflows (Andrew Ng): https://www.youtube.com/watch?v=sal78ACtGTc Reflection Agents: https://blog.langchain.dev/reflection-agents/ LangGraph: https://python.langchain.com/docs/langgraph Supply Chain Dataset: https://www.kaggle.com/datasets/shashwatwork/dataco-smart-supply-chain-for-big-data-analysis Crime Dataset: https://www.kaggle.com/datasets/sahirmaharajj/crime-data-from-2020-to-present-updated-monthly Dataflow BigQuery: https://neo4j.com/docs/dataflow-bigquery/ 0:00 Intro 18:30 Reflection Agents with SupplyChain Data in a Notebook 35:00 Orchestrate with LangGraph 47:24 Same Logic with Crime Data 56:00 Summary and Outlook 1:00:49 Wrap-Up #neo4j #graphdatabase #knowledgegraph #langchain #llm #genai #rag #graphrag

Related Videos