CoolFace
Apppublic

deepset/should-i-follow

sourceHugging Faceupdated 6mo agoView on Hugging Face
81likes
App README

Should I Follow?

Try it out on ๐Ÿค— Spaces

A simple app to get an overview of what a Bluesky user has been posting about and their tone

This is a demo just for fun ๐Ÿฅณ This repo contains a streamlit application that given a Bluesky handle, tells you what type of things they've been posting about lately, their tone, and the languages they use. It uses the LLM by OpenAI gpt-4.1-nano.

It's been built with Haystack using the `OpenAIChatGenerator` and by creating a `ChatPromptBuilder`

https://user-images.githubusercontent.com/15802862/220464834-f42c038d-54b4-4d5e-8d59-30d95143b616.mov

Points of improvement

Since we're using a generative model here, we need to be a bit creative with the prompt we provide it to minimize any hallucination or similar unwanted results. For this reason, I've tried to be a bit creative with the ChatPromptBuilder template and give some examples of how to construct a summary. However, this still sometimes produces odd results.

If you try to run it yourself and find ways to make this app better, please feel free to create an issue/PR ๐Ÿ™Œ

To learn more about the ChatPromptBuilder

You can create prompt templates with Jinja. Check out the guide on creating prompts here

Installation and Running

To run the bare application which does nothing:

  1. 1.Install requirements: pip install -r requirements.txt
  2. 2.Run the streamlit app: streamlit run app.py

This will start up the app on localhost:8501 where you will dind a simple search bar

The Haystack Community is on Discord