chitimbwasc / genai-showcase

GenAI Cookbook

Generative AI Use Cases Repository

Introduction

Welcome to the Generative AI Use Cases Repository! This repository is dedicated to showcasing a wide range of applications in generative AI, including Retrieval-Augmented Generation (RAG), AI Agents, and industry-specific use cases. It also provides practical notebooks and guidance on utilizing frameworks such as LlamaIndex and LangChain, and demonstrates how to integrate models from leading AI research companies like Anthropic and OpenAI.

Table of Contents

• Introduction
• Getting Started
• Use Cases
  • RAG
• Notebooks
  • Evaluations
  • RAG
  • Agents
• Tools
• Frameworks and Models
• Contributing
• License
• Contact

Use Cases

This section contains examples of use cases that are commonly seen in industry-focused scenarios and generic applications. Each entry in the table includes a description and links to production-level examples and relevant code.

Use Case	Stack	Link	Description
Customer Support Chatbot	JavaScript, OpenAI, MongoDB	View Repository	The MongoDB Chatbot Framework provides libraries that enable the creation of sophisticated chatbot

Evaluations

• Evaluating your LLM applications
• Angle Embeddings Evaluation
• OpenAI Embeddings Evaluation
• VoyageAI Embeddings Evaluation

RAG Notebooks

Title	Stack	Colab	Article
RAG with Llama3, Hugging Face and MongoDB	Hugging Face, Llama3, MongoDB
How to Build a RAG System Using Claude 3 Opus and MongoDB	MongoDB, Anthropic, Python
How to Build a RAG System with the POLM AI Stack	POLM (Python, OpenAI, LlamaIndex, MongoDB)
MongoDB LangChain Cache Memory Python Example	POLM (Python, OpenAI, LangChain, MongoDB)
MongoDB LangChain Cache Memory JavaScript Example	JavaScript, OpenAI, LangChain, MongoDB
Naive RAG Implementation Example	POLM (Python, OpenAI, LlamaIndex, MongoDB)
OpenAI Text Embedding Example	Python, MongoDB, OpenAI
RAG with Hugging Face and MongoDB Example	Hugging Face, Gemma, MongoDB

Agents

An agent is an artificial computational entity with an awareness of its environment. It is equipped with faculties that enable perception through input, action through tool use, and cognitive abilities through foundation models backed by long-term and short-term memory. Within AI, agents are artificial entities that can make intelligent decisions followed by actions based on environmental perception, enabled by large language models.

Title	Stack	Colab Link	Article Link
AI Research Assistant	FireWorks AI, MongoDB, LangChain

Tools

Useful tools and utilities for working with generative AI models:

• Embeddings Generator: A set of scripts for generating and manipulating embeddings.

Datasets

Below are various datasets with embeddings for use in LLM application POCs and demos. All datasets can be accessed and downloaded from their respective Hugging Face pages.

Dataset Name	Description	Link
Cosmopedia	Chunked version of a subset of the data Cosmopedia dataset
Movies	Western, Action, and Fantasy movies, including title, release year, cast, and OpenAI embeddings for vector search.
Airbnb	AirBnB listings dataset with property descriptions, reviews, metadata and embeddings.
Tech News	Tech news articles from 2022 and 2023 on valuable tech companies.
Restaurant	Restaurant dataset with location, cuisine, ratings, attributes for industry analysis, recommendations, geographical studies.

Frameworks and Models

Explore the utilization of various AI models and frameworks across different notebooks provided.

Contributing

We welcome contributions! Please read our Contribution Guidelines for more information on how to participate.

License

This project is licensed under the MIT License.

Contact

Feel free to reach out for any queries or suggestions:

• Email: [email protected]