Generative AI use cases with pgvector, Aurora PostgreSQL and Amazon Bedrock

This repository showcases how to utilize pgvector, an open-source PostgreSQL extension for vector similarity search. pgvector is designed to work seamlessly with other PostgreSQL features, including indexing and querying, making it a powerful tool for various applications. This repository contains sample code demonstrating various use cases leveraging pgvector on Amazon Aurora PostgreSQL-Compatible Edition, Amazon Bedrock and Generative AI. For more details, please refer to the following:

1. AWS blog post: Leverage pgvector and Amazon Aurora PostgreSQL for Natural Language Processing, Chatbots and Sentiment Analysis.
2. AWS Workshop: Generative AI Use Cases with Aurora PostgreSQL and pgvector.

Use Cases

Here are some exciting use cases covered in this repository:

1. Product Recommendations 🛒
2. Retrieval Augmented Generation (RAG) 🔄
3. Semantic Search and Sentiment Analysis 🧠
4. Knowledge Bases for Amazon Bedrock with Aurora PostgreSQL 📚
5. Movie Recommendations using Aurora ML and Amazon Bedrock 🎬

Getting Started

To get started, clone the repository and follow the setup instructions provided in the respective directories for each use case.

git clone https://github.com/aws-samples/aurora-postgresql-pgvector.git
cd aurora-postgresql-pgvector

Contributing

This repository is intended for educational purposes and does not accept further contributions. Feel free to utilize and enhance the sample code based on your own requirements.

License

The use cases and sample code with pgvector and Aurora PostgreSQL is released under the MIT-0 License.