chore: remove slack from openai sample #83
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
daabr
reviewed
Oct 3, 2024
There was a problem hiding this comment.
I like your changes, and using JSON would indeed be a robust solution (i.e. passing prompts and params instead of just a single text string), but supporting HTTP POST with a text body would be easier and actually cover a simple user's needs.
Specifically, limit the trigger to POST and the relevant content type (see the HTTP sample's manifest for examples), and document in the readme and/or code how to send it with curl:
curl -X POST "webhook-URL" -H "Content-Type: text/plain" -d "text"
daabr
reviewed
Oct 3, 2024
daabr
reviewed
Oct 3, 2024
daabr
approved these changes
Oct 3, 2024
Co-authored-by: Daniel Abraham <[email protected]>
Co-authored-by: Daniel Abraham <[email protected]>
pashafateev
added a commit
that referenced
this pull request
Nov 7, 2024
The sample uses a URL parameter for input, which simplifies the implementation but might not be realistic for more complex prompts. I have two options for addressing this: - **Option 1**: Document the current approach, informing users of its limitations with URL parameters for input. - **Option 2**: Rewrite the sample to accept input through the request body, which would introduce slightly more complexity but offer greater flexibility. Additionally, I’ve adjusted how user input influences the prompt. Previously, with the URL parameter approach, the input wasn’t impacting ChatGPT’s responses as expected. Now, users can directly enter their own prompt and see its effect on the output more clearly. If we switch to using a JSON body, we might be able to revert to the previous method of prompting ChatGPT, as longer inputs could have a more noticeable impact. --------- Co-authored-by: Daniel Abraham <[email protected]>
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.
The sample uses a URL parameter for input, which simplifies the implementation but might not be realistic for more complex prompts. I have two options for addressing this:
Additionally, I’ve adjusted how user input influences the prompt. Previously, with the URL parameter approach, the input wasn’t impacting ChatGPT’s responses as expected. Now, users can directly enter their own prompt and see its effect on the output more clearly. If we switch to using a JSON body, we might be able to revert to the previous method of prompting ChatGPT, as longer inputs could have a more noticeable impact.