Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Dicord Client #1

Open
UB-AICLUB opened this issue Aug 28, 2024 · 4 comments
Open

Dicord Client #1

UB-AICLUB opened this issue Aug 28, 2024 · 4 comments
Assignees

Comments

@UB-AICLUB
Copy link
Owner

UB-AICLUB commented Aug 28, 2024

Issue Overview: Discord Bot Command Implementation

This issue focuses on developing a Discord bot that processes messages based on specific commands. The primary goal is to implement two key commands: /remember and /ask. Multiple developers may collaborate on this task.

Resources:

Command Specifications:

  1. /remember Command:

    • Access Control:
      • This command is restricted to users with the Core Members role and can only be used in a designated channel.
    • Functionality:
      • When a user inputs a YouTube link, the bot will:
        1. Caption Retrieval: Extract auto-generated captions from the video using a library like youtube-transcript-api or pytube.
        2. Writing to DB Send a request to the Database handler API at embed:8001 (during development, use localhost:8001) to save it The request body will be {"text":"an example text", "metadata":{...}}, the contents of metadata are TBD and left for the developer to decide and the response will return {"message":"Task started successfully"} during development use a dummy link or ignore this part till Embedder #2 is finished.
        3. Response: The bot will acknowledge the success or failure of the operation with a message.
  2. /ask Command:

    • Functionality:
      • When a user asks a question, the bot will:
        1. Database Query: Query ChromaDB to retrieve the top 5 similar text chunks related to the question (use a persistent client with some dummy data manually dumped for testing).
        2. Response Formation: If any of these chunks are linked to a YouTube video, include a link to the video in the response. or just return the texts as quotes
@apurvabanka
Copy link
Contributor

@beaterblank I am planning to work on this issue. Will post question if I have any.

@beaterblank
Copy link
Contributor

@beaterblank I am planning to work on this issue. Will post question if I have any.

Cool go through the resources lmk if u have any questions about the architecture .
You are free to make decisions about how the data should be structrured or customised.
Make sure to put good commit messages

https://www.conventionalcommits.org/en/v1.0.0/

Refer this for more on how to make good commits

@kcbhola3030
Copy link

@beaterblank I am planning to work on this issue. Will post question if I have any.

Are u still working on it ?
I am willing to collaborate on this one

@apurvabanka
Copy link
Contributor

@beaterblank I am planning to work on this issue. Will post question if I have any.

Are u still working on it ? I am willing to collaborate on this one

Hey @kcbhola3030, not much is left in this issue. All the required functions are created and out for PR review.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants