Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
OpenAI Assistants: JSON and Tools
Explore OpenAI Assistants API: configuration, JSON output strategies, threads/runs, and a live NextJS demo with function calls and vector store integration.
Assistants are a new (beta) part of OpenAI’s API. They are powerful but also have some interesting quirks. In this talk, I’ll start with the basics of configuring an Assistant in the Playground. Next I will show a few different ways of getting assistants to respond with JSON output, including workarounds for current limitations when using function calling or file search/vector store. Then we’ll get into working via the API - understanding concepts like threads, runs and the various flows needed to programmatically engage with Assistants. I’ll conclude by discussing our observations about accuracy, consistency and cost.
Code that I will demo includes a NextJS app + API that uses the node OpenAI API library to lookup company information via an assistant and return it in JSON format. It then uses this information to query another assistant that has access to a vector store database (single json file) + file search to recommend projects that would be appropriate for the company based on the files in the database. Then it uses the same assistant to allow for creating a custom project brief.
If there’s time, I will also briefly show PHP code that uses a more complex tool calling flow.
Related projects
AI Fundamentals and Best Practices
Boston
An overview of AI fundamentals, practical tips for using ChatGPT and Co‑Pilot, and real‑world examples to help beginners…
Okta Ventures: Supporting the Builder Community
San Francisco
Explore how Okta provides startup builders access to its identity platform, partnership pathways, capital, technical guidance, and business…
Drop-in OpenAI Assistants Replacement
Boston
Learn how to replace the OpenAI Assistants API with a compatible library that supports non‑OpenAI LLMs, multilingual embeddings,…
AI APIs and Output Wrangling
Atlanta
This talk explores best practices for interacting with AI APIs, covering prompt design, idempotence, schema management, error detection,…
Baseten
New York City
Learn how to deploy and scale custom ML models using Baseten’s inference layer, covering SOC 2 compliance, self‑hosting options,…
Candy Mountain: Building the Agentic Office
Boston
Learn how to construct a cloud‑based digital office using SQLite, Docker, and AI agents, with a conversational director…