https://github.com/oribarilan/nerdoscope

https://github.com/oribarilan/nerdoscope

Last synced: 4 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/oribarilan/nerdoscope
• Owner: oribarilan
• Created: 2024-03-08T20:46:50.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2024-03-13T10:28:49.000Z (8 months ago)
• Last Synced: 2024-03-13T11:41:10.336Z (8 months ago)
• Language: Jupyter Notebook
• Size: 21.5 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# nerdoscope

A horoscope app for nerds in the tech industry.

## Background

This is a simple demo project aimed at helping with basic first steps in settings up a generative AI based app.

## Recommended Setup

1. Install [Docker](https://www.docker.com/products/docker-desktop)

2. Install [Visual Studio Code](https://code.visualstudio.com/)

3. Install the [Remote Development extension pack](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.vscode-remote-extensionpack)

4. Reopen the project in a dev container (CMD + Shift + P -> Reopen in Container)

5. Inside the dev container, run `ollama serve`

6. Open another terminal and download the model `ollama pull orca-mini:3b`

## Instructions

### Play Around

First, play around with a model that is available to you (some playground are listed below). 

For example, you can use [Hugging Face Model Repository](https://huggingface.co/models) to interact with many models, and pick one that seems promising for your use case.

For ease of use working with these demos, we suggest that you pick a model that is available in the [Ollama model repository](https://ollama.com/library).

Don't worry, you can always change this later :)

### Jupyter Notebook

Now, enter the dev container and open the Jupyter Notebook at `src/demo.ipynb`.

Follow along with the notebook to see how to use the model in your app.

### Code your CLI Tool

Try taking what you learned from the Jupyter Notebook and implement a simple CLI tool for the task.

You can reference `app.py` for the stupidly simple nerdoscope CLI tool.

## Useful Links

### Models and Playgrounds

1. [Azure OpenAI Studio](https://oai.azure.com/)

2. [Hugging Face](https://huggingface.co/)

3. [Ollama](https://ollama.com/)

### Libraries (and coding tutorials)

1. [Azure OpenAI Quickstarts](https://learn.microsoft.com/en-us/azure/ai-services/openai/)

2. [Semantic Kernel](https://learn.microsoft.com/en-us/semantic-kernel/get-started/quick-start-guide?tabs=python)

3. [LangChain](https://python.langchain.com/docs/get_started/quickstart)

### Prompt Engineering

1. [Prompt Engineering Guide](https://www.promptingguide.ai/)