Purpose
This page has information on how to get started creating your own OpenAI Assistant in ChatGPT. I’ve included details about two potential paths that can be taken, each with its own strengths (💪) and challenges (🧗♂️). Before creating your first AI assistant, consider both paths and how each aligns with your goals.
Both paths will require a ChatGPT Plus account to create an assistant. Despite the differences, both paths will result in an AI assistant that leverages retrieval-augmented generation (RAG) techniques to empower your assistant to quickly search through and summarize key information from a knowledge base, reducing hallucinations and giving you control over how your assistant behaves for your learners.
Navigation
Path 1: Create an Assistant in Playground
Reference Guides
Strengths
💪 Greatest degree of customization to calibrate responses
💪 Can be used to architect an assistant for use in custom applications
💪 Can be embedded into HTML based documents
💪 Users without a ChatGPT account can use the assistant
Challenges
🧗♂️ Adding function calls to external APIs requires a higher level of technical knowledge
🧗♂️ Sharing the assistant with learners requires a web page and basic front end development skills
🧗♂️ File upload and voice control is more challenging to implement
🧗♂️ Assistant owner is billed based on the amount of usage
Path 2: Create an Assistant in ChatGPT Editor
Reference Guides
Strengths
💪 No coding skills needed
💪 Adding and testing function calls to external APIs is simplified
💪 Can be quickly shared with other ChatGPT Plus users
💪 Includes learner file upload and voice mode
💪 Unlimited usage
Challenges
🧗♂️ Less options for customization such as model choice and temperature
🧗♂️ Cannot be embedded on a page
🧗♂️ Learners must have a ChatGPT Plus account
Path 1: Create an AI Assistant in Playground
To build your own assistant in Playground:
Sign up or sign into ChatGPT Plus by selecting this link.
Access the OpenAI Playground.
In the left navigation panel, select Assistants.
Enter a Name for your assistant.
Provide your assistant with specific Instructions on what you want it to do and how you want it to respond to you. See example.
Select the Model you wish to use, gpt-4o is currently the most advanced (and cheapest) option from OpenAI that supports RAG.
Enable File search.
Select + Files to choose the files this assistant should use to answer questions and inform its output.
Enter your message to your Assistant.
Select Run to start testing responses.
Iterate on the instructions until you are satisfied with the assistant’s responses.
This path will result in an OpenAI Assistant that his modular and can be built into a custom application or connected to other platforms and tools like Predictable Dialogs. These assistants can be shared with anyone who has to the custom application or front end implementation.
Connect AI Assistant to Predictable Dialogs
Now that you have an assistant with instructions and a knowledge base to search from, its time to make that assistant visible to your learners. To do this, you can use a tool called Predictable Dialogs which enables easy embedding of your assistant in a web-based document and tracks conversations user have with your AI Assistant.
Part 1 - Create an OpenAI API Secret key
Navigate to the OpenAI API Key page.
Select Create new secret key.
Name the OpenAI Key.
Select Default Project.
Select Create secret key.
Copy secret key.
Save your secret key in a secure location.
Part 2 - Retrieve your OpenAI Assistant ID
Access the OpenAI Playground.
Select your assistant from the drop down menu.
Below the assistant’s name, copy the assistant ID.
Example: asst_ozonwVt41ynwB6q78gHjKELl
Part 3 - Connect to Predictable Dialogs
Sign up or sign into Predicable Dialogs as a free account.
Select Create new agent.
Select OpenAI Assistant v2.
Select Enter new assistant.
Enter one of your OpenAI Secret Keys.
Select Next.
Enter your OpenAI Assistant ID.
Select Next.
Select Next to confirm selected assistant.
In the Install tab, select Copy on the Embed Code for HTML Standard script.
Embed the script code within an HTML based document.
Customize the Theme and Settings to adjust the look and feel of your embedded chat bot.
Path 2: Create an AI Assistant in ChatGPT Editor
This path will result in an OpenAI Assistant that can be shared with other ChatGPT Plus users.
To build your own assistant in ChatGPT Editor:
Sign up or sign into ChatGPT Plus by selecting this link.
Access the OpenAI Playground.
In the left navigation panel, select Assistants.
Enter a Name for your assistant.
Provide your assistant with specific Instructions on what you want it to do and how you want it to respond to you. See example.
Select the Model you wish to use, gpt-4o is currently the most advanced (and cheapest) option from OpenAI that supports RAG.
Enable File search.
Select + Files to choose the files this assistant should use to answer questions and inform its output.
Enter your message to your Assistant.
Select Run to start testing responses.
Share an AI Assistant with Others
Now that you have an assistant with instructions and a knowledge base to search from, its time to make that assistant visible to your learners. To do this, you can use a tool called Predictable Dialogs which enables easy embedding of your assistant in a web-based document and tracks conversations user have with your AI Assistant.
Step 1 - Create an OpenAI API Secret key:
Navigate to the OpenAI API Key page.
Select Create new secret key.
Name the OpenAI Key.
Select Default Project.
Select Create secret key.
Copy secret key.
Save your secret key in a secure location.