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?”
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…