📝 Research :https://ojitha.blogspot.com.au
for my lengthy articles.
LangChain for AWS Bedrock
The first part explained the LLM basics of AWS Bedrock. This second part describes how to integrate LangChain with AWS Bedrock to build AI applications. It covers the implementation of AWS Bedrock with Amazon Titan and Claude models, as well as key LangChain components, including prompt templates, embeddings, memory, and chains. Code examples demonstrate everything from basic model invocation to creating conversational agents with memory, perfect for developers building production AI solutions.
AWS Bedrock Foundation Models
Dive into the essentials of Large Language Models (LLMs) and Foundation Models (FMs) on Amazon Web Services (AWS). This guide explores leveraging AWS Bedrock and related services for building and interacting with powerful generative AI models.
Learn about key concepts including prompt engineering, fine-tuning techniques like prompt-based learning and domain adaptation, and managing inference parameters such as Temperature, Top K, and Top P. Discover how to utilise AWS FM APIs. This post provides the foundational knowledge required to get started with LLMS on AWS. The second part describes how to use LangChain with AWS Bedrock.
Maven Proxy handling
Here are the common challenges when working with development tools like Maven and VSCode behind a corporate proxy within a WSL 2 environment.
Currently, my computer is behind the corporate proxy. As a Java Programmer, when I used Maven 3 on the WSL 2 Ubuntu 20.4 Linux environment, I had to set the proxy in the settings.xml under the /home/user/.m2
folder. Although I’ve set the proxy, it doesn’t work as expected: mvn compile
complains about unresolved Scala dependencies. Another problem is that VSCode doesn’t show the intellisense. I’ve already installed the Microsoft Java extension pack completely.
Lua filters for Pandoc
Lua filter used in Pandoc 3.6.3. This blog has solutions for:
- Creating Glossary for ePub ver 3 book
- GitHub style alerts
AWS PITR Explained
PITR stands for Point-in-Time Recovery, which is a feature offered by several AWS services to provide continuous data protection and the ability to restore data to a specific point in time.