Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Fetch: LLMs for Product Catalogs
Learn how to use LangChain with Neo4j to query a multi‑million‑product knowledge graph, extracting counts, brand lists, and active offers from hierarchical categories.
At Fetch, we have a product catalog consisting of millions of products, in extremely granular levels of detail (even more specific than UPCs are!). It can be difficult to easily get summary stats about those products because of the hierarchical structure of the product categories, so I built a knowledge graph on top of the catalog. The cherry on top is a LangChain-driven interface to ask questions like “how many brands do we have in the Red Wine category?” or “what offers are we running right now for snack products?”
- LangChainThe open-source framework for building and deploying reliable, data-aware Large Language Model (LLM) applications.LangChain is the essential framework for engineering LLM-powered applications: it simplifies connecting models (like GPT-4 or Claude) to external data, computation, and APIs. The platform provides a modular set of components—Chains, Agents, Tools, and Memory—allowing developers to quickly build complex workflows like Retrieval-Augmented Generation (RAG) pipelines and sophisticated conversational agents. Its Python and JavaScript libraries, combined with LangChain Expression Language (LCEL), offer a standardized interface for rapid prototyping and moving applications to production with confidence.
- Neo4jNeo4j is the world's leading native graph database, purpose-built for high-performance management and traversal of connected data.Neo4j is the leading native graph database, leveraging the Property Graph Model (nodes, relationships, properties) for data storage and retrieval . It is an ACID-compliant, high-performance platform designed for managing highly connected data at scale (billions of nodes) . Queries execute using the declarative Cypher query language, which simplifies complex traversals that would cripple relational systems with numerous JOINs . This architecture delivers orders of magnitude performance improvements (often minutes to milliseconds) for relationship-based queries . Major use cases include fraud detection, recommendation engines, and knowledge graphs for AI, trusted by 84 of the Fortune 100 .
- Knowledge GraphA Knowledge Graph (KG) is a semantic network: it models real-world entities (nodes) and their relationships (edges) to provide context and structure for machine reasoning.Knowledge Graphs structure data as interconnected entities (nodes) and explicit relationships (edges), shifting data organization from 'strings to things' (Neo4j). This graph-based model enables systems to understand context, not just keywords. Major applications include Google’s Knowledge Graph (over 500 million objects) for enhanced search results and enterprise use cases like AI-powered recommendation engines (Netflix) and financial crime prevention (KYC/AML). KGs integrate disparate datasets, providing a unified, explainable knowledge base critical for advanced AI and data analytics.
Related projects
LLM drives a web browser
New York City
This talk demonstrates an open-source interface that enables large language models to interact with web pages through a…
Using LLM's for Social Good: A Chicago Public Schools Case Study
Chicago
Learn how web crawling and large language models were combined to build a searchable directory of before‑and after‑school…
How function calling really works
Chicago
Explains logit biasing to enforce structured outputs and demonstrates an open-source LLM’s function-calling mechanism for selecting tools, with…
Taming the LLM Herd - Effortless Multi-Model Integration with LangChain
Chicago
This talk demonstrates how to integrate multiple large language models using a new LangChain extension, featuring a Streamlit…
Thinking LLMs
Los Angeles
This talk explains how to generate synthetic data for training custom o1 style language models using methods from…
Building AI Powered Surveys with Smarter JSON
Chicago
This talk explores using JSON schemas and tool calling with LLMs to efficiently edit and integrate JSON, demonstrated…