Problem: open-source maintainers spend a lot of time managing duplicate/related (doppelgänger) issues & pull requests
Solution: doppelgänger compares newly submitted issues/PRs against existing ones to automatically flag duplicate/related (doppelgänger) issues/PRs
Topics: vector db, github, open-source, embedding search, rag, similarity scores
Screen.Recording.2024-04-27.at.4.57.11.PM.mov
-
Clone this repository to your local machine:
git clone https://github.com/dannyl1u/doppelganger.git cd doppelganger
-
Build Docker image and run:
docker build -t doppelganger . && docker run --name doppelganger doppelganger
or
-
Create a virtual environment and install dependencies:
python -m venv venv
source venv/bin/activate
# Usevenv\Scripts\activate
on Windowspip install -r requirements.txt
-
Run the Flask server:
python app.py
-
Configure a GitHub Webhook:
- Go to your GitHub repository settings
- Navigate to "Webhooks" and click "Add webhook"
- Enter the following details:
- Payload URL:
https://your-public-url/webhook
- Content type:
application/json
- Which events would you like to trigger this webhook?: Select "Let me select individual events" and check "Issues" and "Pull requests"
- Payload URL:
- Click "Add webhook"
- To make your Flask server publicly accessible, consider using a tool like ngrok to expose it to the internet during development.
- Ensure proper security measures for the webhook endpoint to avoid unauthorized access or potential attacks.