amazon-bedrock-rag and rag-with-amazon-bedrock-and-pgvector
These are complementary approaches to RAG on AWS: the first uses the managed Knowledge Bases service for simplified vector storage and retrieval, while the second provides a self-managed alternative using PostgreSQL with pgvector for organizations requiring custom infrastructure control.
About amazon-bedrock-rag
aws-samples/amazon-bedrock-rag
Fully managed RAG solution implemented using Knowledge Bases for Amazon Bedrock
This project helps you build a custom chatbot that can answer questions using your own private documents or website content. You provide your proprietary information, and the chatbot generates accurate answers, citing its sources from your data, instead of relying solely on generic internet knowledge. This is ideal for knowledge managers, customer support leads, or anyone needing to make internal company data or specific domain knowledge easily searchable and consumable through a conversational AI.
About rag-with-amazon-bedrock-and-pgvector
aws-samples/rag-with-amazon-bedrock-and-pgvector
Opinionated sample on how to build/deploy a RAG web app on AWS powered by Amazon Bedrock and PGVector (on Amazon RDS)
This project helps developers build and deploy their own question-answering systems for internal documents. It takes a collection of PDF files as input, processes them, and then allows users to ask questions in natural language, retrieving relevant answers from the content. The target user is a software developer or cloud architect responsible for setting up internal knowledge bases or intelligent search applications.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work