Adding berkeley workshop directory (lastmile-ai#244)

Adding berkeley workshop directory

workshops/berkeley/README.md

@@ -0,0 +1,55 @@
+# Building a Generative AI App (Berkeley x LastMile AI)
+
+This workshop walks you through how to build a generative AI app with open-source LastMile AI tools.
+Workshop Date: November 14, 2023
+
+## Tools
+
+**AI Workbooks**: a notebook-like editor for prompt engineering and model experimentation. You can chain prompts, parametrize prompts, and iterate on model parameters.
+
+**AI Config**: a standardized JSON file format to manage your prompts, models, and model parameters as configs. It allows you to store and iterate on generative AI model behavior separately from your application code.
+
+## What are we building?
+
+We are building an AI teaching assistant app to showcase prompt engineering, prompt routing, function calling, and RAG (retrieval-augmented generation).
+
+## Setup Instructions
+
+1. Go to [LastMile AI](https://lastmileai.dev) and sign up for a free account to get access to AI Workbooks.
+2. Create a [new workbook](https://lastmileai.dev/workbooks/workshop), experiment with some prompts, parameters, and system prompt.
+3. Go to this [AI Workbook](https://lastmileai.dev/workbooks/clowg4ywg00daqpf2cvyz9z0g).
+4. Download the AIConfig .json.
+5. Clone the same [AI Workbook](https://lastmileai.dev/workbooks/clowg4ywg00daqpf2cvyz9z0g) and follow the workshop.
+6. Clone this [Google Colab Notebook](https://colab.research.google.com/drive/1bhG2YbBI4q3ZhoEZ_LdflLf-AkV9WWc9): File > Save a Copy in Drive. Rename to `{Your Name} LastMile Workshop`.
+
+## Tutorial
+
+1. Start with the AI Workbook to prototype your prompts, prompt chains, and model parameters.
+2. Upload the AIConfig to your Google Colab Notebook Files: 'berkeley_lastmile_workshop_aiconfig.json'
+3. Follow the instructions in the Google Colab Notebook.
+
+## Apply for Raffle
+
+Submit your Workshop Colab Notebook to this [spreadsheet](https://docs.google.com/spreadsheets/d/1c38NgDS0IIlYyuiHuCnCU_iWYE1TsxVwkOt_iMM9cdg/edit#gid=0).
+
+## Win a $100 Amazon Gift Card - Berkeley LastMile Challenge
+
+Build a project that uses AI Config (and AI workbooks).
+
+Deadline: Novemeber 28th 12:00AM PST
+
+Read instructions [here](https://github.com/lastmile-ai/aiconfig/blob/main/workshops/berkeley/competition/README.md).
+
+# Key Concepts
+
+**Prompt Engineering**
+Designing and optimizing prompts to effectively communicate with AI models helps ensure that they understand and respond accurately to user inputs. There are several [prompt engineering techniques](https://www.promptingguide.ai/) such as zero-shot, few-shot, chain-of-thought, and tree-of-thoughts. AI Workbooks are a great way to prototype your prompts, prompt chains, and compare different model responses.
+
+**Prompt Routing**
+Prompt routing directs a user's prompt to the most suitable AI model or system, based on the nature of the request, to achieve the most accurate and relevant response. An LLM is usually the router in this case to make the decision of which system to call based on the user prompt.
+
+**Function Calling**
+You can describe functions to OpenAI LLMs (`gpt-4-0613` and `gpt-3.5-turbo-0613`) and have the model intelligently choose to output a JSON object containing arguments to call those functions. This is one way to connect GPT's capabilities with external tools and APIs. Read more [here](https://openai.com/blog/function-calling-and-other-api-updates).
+
+**Retrieval-Augmented Generation (RAG)**
+RAG provides a way to optimize the output of an LLM with targeted information without modifying the underlying model itself; that targeted information can be more up-to-date than the LLM as well as specific to a particular organization and industry.

workshops/berkeley/competition/README.md

@@ -0,0 +1,45 @@
+## 🐻 Berkeley LastMile Challenge
+
+Build a project that uses AI Config (and AI workbooks). You can use Google Colab or a script. Make sure to include a README.md for your project describing what you built and how you used AIConfig.
+
+Suggestions:
+
+- AI-powered Apps: Example: [AI Teaching Assistant x Streamlit](https://github.com/lastmile-ai/aiconfig/tree/main/cookbooks/Basic-Prompt-Routing)
+- Chatbots: Example: [WizardGPT](https://github.com/lastmile-ai/aiconfig/tree/main/cookbooks/Wizard-GPT)
+- Prompt Engineering Techniques: [Example Chain-of-Verification](https://github.com/lastmile-ai/aiconfig/tree/main/cookbooks/Chain-of-Verification)
+
+## How to Enter:
+
+1. Fork the [AIConfig Github repo](https://github.com/lastmile-ai/aiconfig) & submit a pull request with a new folder for your project inside of this [ competition folder](https://github.com/lastmile-ai/aiconfig/tree/main/workshops/berkeley/competition). Deadline to submit the PR is November 28th 12:00 PST.
+2. Send us an email at [[email protected]](mailto:[email protected]) once you've submitted your PR.
+3. Have quesitons? Join our [discord](https://discord.com/invite/xBhNKTetGx) and ask the team.
+
+**Requirements for PR Submission**
+
+Colab Notebook
+
+1. .ipynb of the notebook (download from Colab directly)
+2. AIConfig .json file
+3. README.md with instructions
+
+Script
+
+1. .py or .js files
+2. AIConfig .json file
+3. README.md with instructions
+
+## Rubric
+
+**Creativity and Originality:** The project should be unique and not a copy of existing projects. It should display creativity in using AIConfig and AI workbooks.
+
+**Functionality**: The project should work properly without bugs or errors and be reproducible for others to easily clone.
+
+**Use of AIConfig**: The project should effectively and innovatively integrate AIConfig and AI workbooks. The degree to which AI Config is utilized will be taken into account.
+
+**Documentation**: The README.md file should clearly explain the project, including what it does, how it works, and how AIConfig and AI workbooks are used.
+
+**Submission before the deadline**: Submitting the project on time via a PR to the designated folder is a must before November 28, 2023 12:00 AM PST. Make sure to also send us an email at [[email protected]](mailto:[email protected]) once you have submitted the PR so that we can contact you if you win.
+
+## Additional info
+
+How to submit a PR: https://opensource.com/article/19/7/create-pull-request-github