feat: Add OpenAI GPT model integration #39
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
JasirZaeem
reviewed
Apr 13, 2023
JasirZaeem
reviewed
Apr 13, 2023
JasirZaeem
reviewed
Apr 13, 2023
JasirZaeem
reviewed
Apr 13, 2023
JasirZaeem
reviewed
Apr 13, 2023
We changed the engineered prompt to suits our case more such as including Discord code block syntax. We also increase the max_tokens so the completion is longer and more detailed.
JasirZaeem
approved these changes
Apr 14, 2023
|
I suggest to Limit the ask command to a particular channel before merging, meant specifically for students to ask questions to the bot. |
scotthallock
approved these changes
Apr 14, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Overview
This PR adds an initial integration for the OpenAI GPT model to the existing codebase. The changes include modifications to the config.ts file to add the openaiApiKey property, importing the
openaipackage in the package.json file, and updating the commands.ts file to include a new slash command named ask that prompts the assistant to answer a question using the GPT model.Engineering the prompt
The prompt was engineered following the few-shot method that provides the model with an example of how it should respond and a few parameters such as being friendly and not responding to prompts that are unrelated to coding.
As a start, I think the few-shots method is the best choice. If we find ourselves in the need to provide the model with more examples while aiming to reduce the overall cost of big prompts, we can try fine-tuning it.
Changes
The following changes have been made:
config.tsopenaiApiKeyproperty to theConfiginterface.OPENAI_API_KEYis now required.package.jsonopenaipackage as a dependency.commands.tscommandsReplies.tsThese changes allow the assistant to answer questions using the OpenAI GPT model.
Related issues