Skip to content
This repository has been archived by the owner on Oct 21, 2024. It is now read-only.

agno-agi/ai-cookbook

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

51 Commits
Jan 29, 2024
Feb 12, 2024
Feb 20, 2024
Feb 5, 2024
Feb 20, 2024
Feb 19, 2024
Feb 5, 2024
Feb 5, 2024
Apr 17, 2024
Jan 15, 2024
Feb 1, 2024
Feb 12, 2024
Feb 20, 2024
Jan 15, 2024
Jan 15, 2024
Apr 17, 2024
Feb 20, 2024
Jan 15, 2024
Jan 15, 2024
Feb 20, 2024
Jan 15, 2024
Jan 29, 2024
Jan 31, 2024
Apr 17, 2024
Apr 17, 2024
Jan 15, 2024

Repository files navigation

AI Cookbook

This repo contains a collection of AI recipes/patterns built using phidata

Live Demos

The AI cookbook apps are live and can be accessed at:

  • HackerNews AI that interacts with the HN API to summarize stories, users, find out what's trending, summarize topics.
  • Streamlit App serving a PDF, Image and Website Assistant (password: admin)
  • FastApi serving a PDF Assistant.

Setup

  1. Clone the git repo

from the ai-cookbook dir:

  1. Create + activate a virtual env:
python3 -m venv aienv
source aienv/bin/activate
  1. Install phidata:
pip install phidata
  1. Setup workspace:
phi ws setup
  1. Copy workspace/example_secrets to workspace/secrets:
cp -r workspace/example_secrets workspace/secrets
  1. Copy .env file:
cp example.env .env
  1. Update .env file:
  • Set the AI apps like HACKERNEWS_AI you'd like to enable as True
  • Set your OPENAI_API_KEY
HACKERNEWS_AI=True
# OPENAI_API_KEY=sk-***
  • You can also export these as environment variable like:
export OPENAI_API_KEY=sk-***

Run AI Cookbook locally

  1. Install docker desktop

  2. Start the workspace using:

phi ws up
  1. Stop the workspace using:
phi ws down