How to Use OpenAI's Assistants API v2 (step-by-step + easter egg)

In this video, I dive into the OpenAI Assistants API v2, showcasing how to effectively use its core functions to enhance your AI agents. You'll learn about function calling, which equips your AI with additional capabilities on top of a robust knowledge base and powerful prompts. I also demonstrate how to use these functions within a custom GPT to create versatile assistants without writing any code. Plus, I'll show you how to update and interact with these assistants using my Replit microservice. This tutorial is ideal for anyone looking to build and manage AI assistants seamlessly.

🦾 Link to Google Colab (for Core Assistant API v2 functions + GUI):

🦾 Link to Google Colab (for Assistant API v2 Function Calling):

🦾 Link to Replit to Create Assistants in ChatGPT:

🕸️ Link to Scrape of Assistants API Documentation:

👋 About Me:
Hello! I'm Mark, a seasoned Data Science Manager by day and an AI automation agency owner by night, hailing from Canada with a decade in the AI space. At Prompt Advisers, we specialize in cutting-edge AI solutions, helping individuals, businesses, and agencies fully harness applied AI. Having been featured in interviews and recognized for our innovative contributions, we're dedicated to guiding you through the AI landscape.

🚀 My Goal:
My mission is to empower you with the knowledge to explore AI technology in your ventures, whether you're an individual, a business, or an agency. I aim to help you leverage applied AI to its fullest potential, providing insights, sharing experiences, and offering partnerships to bring your visions to life.

#AssistantsAPI #OpenAI #FunctionCalling #CustomGPT #AIagents #Replit #TechTutorial #ArtificialIntelligence #AITools #AIIntegration #GPT4Omni #GPT4o

[tuaitituaiti]

Man, I love this deep dive for a newb sub, visual/audio learner 55+ old fella. Beers on me when you are Aotearoa Chur Koko...🎬🦅🙏 bring LO...

[lucvandenboogaart]

Legendary video Mark! I was a bit overwhelmed by the api documentation in terms of how broad it is. This video absolutely helped me in gaining that necessary overview to design my applications software architecture. I love how you just show a working example with all components loosely integrated to demonstrate how all of the components work together. You probably saved me a day of work going back on early uninformed choices in a 30 min video. Subscribed!

[Lyriks_]

Honest, Straight to the point, insightful, that's what we like, good job mate ! By the way i'm curious about the scrapping assistant for documentation, do you have any tutorial about this ?

[uwegenosdude]

Hi Mark. Thanks a lot for this great video. I played around some months ago with the v1 of the assistants API. With this background your video helped me a lot to understand what has changed. I liked the idea of using Perplexity API to get information about recent information which is not part of OpenAIs huge LLMs.

[hadinayebi]

this was very helpful, Thank you so much. Can you also dive into the portion where you define the actions in custom GPT to talk to replit microservice? (The OpenAPI schema you used to make that connection)

[duynguyen]

keep update more video, it's so good. Thank you

[lezgoverci]

you can just add the "file_search" in the tools array when you create the assistant

[TUSHARGOPALKA-njjx]

During the chatbot conversation, how to ensure that the tool call its used only during a specific step, and not for all the user queries?

[JoeKnouse]

Say Mark would you be so kind as to update with the link to the documentation scrape? That would be so useful. Or if you could let us know what you used to scrape the documentation, that would work too. Thanks!

[Rob__NCAA_Champion]

Hey Mark, so I was making the assistant of the ChatGPT website itself but when I run it with my large documents that are in the vector search, it reaches a token limit and I wont be able to ask any more questions until I clear or restart the assistant. Im confused. Using Chat GPT is allows for long conversations. Doing the process you explained, would this allow me to better communicate with the assistant without it hitting a wall? Maybe Im going about this wrong or not being as efficient.

[gayendrawijesekara]

This is amazing. By the way Mark, the link to replit seems broken

[TrevorMacmurray]

Both of your colab links are the same, can you post the one for the function calling?