Seamlessy implement information extraction pipeline with LangChain and Neo4j

Extracting structured information from unstructured data like text has been around for some time and is nothing new. However, LLMs brought a significant shift to the field of information extraction. If before you needed a team of machine learning experts to curate datasets and train custom models, you only need access to an LLM nowadays.

In this post, you'll learn how you can set up and integrate Amazon Bedrock with your LangChain app for an end-to-end RAG pipeline

👋

New to LangChain? Start with this introductory post first. It'll give you a great overview of everything you need to know before diving in. Come back when you're done!

1. Diagrams

Turn python code into cloud system architecture diagrams

Link: https://github.com/mingrammer/diagrams

https://github.com/blushft/go-diagrams

Go-Diagrams

Fast and easy application diagrams

Go-Diagrams is a loose port of diagrams.

Contents

About Diagrams

Diagrams lets you draw the cloud system architecture in Python code.

It was born for prototyping a new system architecture without any design tools. You can also describe or visualize the existing system architecture as well.

Diagram as Code allows you to track the architecture diagram changes in any version control system.

Create beautiful diagrams in minutes. Simple syntax. Endlessly customizable. D2 is the fastest and easiest way to get a mental model from your head onto the screen, then make edits with your team.

vars: {
  d2-config: {
    layout-engine: elk
    # Terminal theme code
    theme-id: 300
  }
}
network: {
  cell tower: {
    satellites: {
      shape: stored_data
      style.multiple: true
    }

This article was brought to you by IcePanel 🧊