diff --git a/README.md b/README.md index 788213b..023fd0c 100644 --- a/README.md +++ b/README.md @@ -1,28 +1,42 @@ -# Generative AI Hackathon - - - Open In Colab - - -LangChain is a Python framework for developing applications using language models. -It abstracts the connection between applications and LLMs, allowing a loose coupling between code and specific foundation models like Google PaLM. - -## The challenge - -Open [the notebook](hackathon.ipynb) in Jupyter or [Google CoLab](https://colab.research.google.com/github/teamdatatonic/gen-ai-hackathon/blob/main/hackathon.ipynb). -The notebook is self-contained (includes python `pip` install commands). -However, the following pre-requisites are required to get started: - -- Google Cloud Project with Vertex AI API enabled +

Generative AI Hackathon

+ + + + +
+ + Colab logo + Run in Colab + + + + GitHub logo + View on GitHub + + + + Vertex AI logo + Open in Vertex AI Workbench + +
+
+ +**➡️ Your task:** Learn about Generative AI by building your own Knowledge Worker using Python and LangChain! + +**❗ Note:** This workshop has been designed to be run in Google CoLab. Support for running the workshop locally or using VertexAI Workbench is provided, but we heavily recommend CoLab for the best experience. + +The notebook is self-contained (includes python `pip` install commands), however, the following pre-requisites are required to get started: +- Google Cloud Project with Vertex AI API enabled. +- A `credentials.json` file for accessing the Vertex AI API via a service account. ## Going further After completing the workshop, an example setup for deploying the knowledge worker to production is viewable in [gen_ai_hackathon](gen_ai_hackathon). The next steps covered include separating the Gradio front-end into a separate server, and creating a FastAPI LangChain API for serving requests. -## Running the notebook for a Hack event +## Running the notebook for a hackathon event 1. Create a dedicated Google Cloud project with Vertex AI enabled. -2. Create a service account roles: Vertex AI User (for vertex ai endpoints), Storage Object Viewer (to download demo and webarchive materials) and Storage Legacy Bucket Reader (to read the contents of buckets for dynamic selection). +2. Create a service account roles: `Vertex AI User` (for vertex ai endpoints), `Storage Object Viewer` (to download demo and webarchive materials) and `Storage Legacy Bucket Reader` (to read the contents of buckets for dynamic selection). 3. Distribute the JSON credentials for this service account, to allow participants to impersonate the SA and authenticate to access the Vertex AI endpoint. -4. Post-workshop, remember to delete the key to maintain security and prevent further billing. \ No newline at end of file +4. ❗ Post-workshop, remember to delete the key to maintain security and prevent further billing. diff --git a/hackathon.ipynb b/hackathon.ipynb index 29194a3..a51ea55 100644 --- a/hackathon.ipynb +++ b/hackathon.ipynb @@ -1,5 +1,37 @@ { "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "

Generative AI Hackathon

\n", + "\n", + " \n", + " \n", + " \n", + "
\n", + " \n", + " \"Colab\n", + " Run in Colab\n", + " \n", + " \n", + " \n", + " \"GitHub\n", + " View on GitHub\n", + " \n", + " \n", + " \n", + " \"Vertex \n", + " Open in Vertex AI Workbench\n", + " \n", + "
\n", + "
\n", + "\n", + "**➡️ Your task:** Learn about Generative AI by building your own Knowledge Worker using Python and LangChain!\n", + "\n", + "**❗ Note:** This workshop has been designed to be run in Google CoLab. Support for running the workshop locally or using VertexAI Workbench is provided, but we heavily recommend CoLab for the best experience.\n" + ] + }, { "attachments": {}, "cell_type": "markdown", @@ -7,8 +39,6 @@ "id": "ScHDNga8s3Rw" }, "source": [ - "# Generative AI Hackathon\n", - "\n", "## Introduction\n", "\n", "This notebook walks you through the challenge of implementing a **Knowledge Worker** for your organisation using **Generative AI**!\n",