AWS MCP: Model Context Protocol trên AWS
Bắt đầu với MCP
MCP (Model Context Protocol) là một giao thức mở chuẩn hóa cách các ứng dụng cung cấp ngữ cảnh cho các mô hình ngôn ngữ lớn (LLMs). Hãy tưởng t...
Exploring Different LLM Models: A Hands-on Guide - Part 2
In Part 1 of the blog, we explored LLM classification framework, technical considerations and also tried a hands-on by accessing LLama-3 LLM from Meta through Hugging Face platform and Mistral LLM fro...
A Frontend Dev's Guide for Learning AI
AI, and more specifically LLMs, have me really pumped. I am more excited today than I was when I first started working with SPAs and feeling the potential that client-side development opened up for us...
De LLM jailbreaking a 1-click session hijacking
‼️ Essa é uma versão resumida do post que eu gostaria de fazer. Como a vulnerabilidade foi apenas parcialmente resolvida, cortei grande parte dos detalhes e racional de como cheguei a cada resu...
Summary of LLM Function Calling
What I’m discussing here is how Wrtn Technologies is building open source software.
I’ll explain in several parts how our team is preparing for the AI era.
If you’re not a developer, you can sa...
Multi-Agent Hybrid Knowledge Base Retrieval: Building a High-Precision Legal Case Analysis Platform
This article explores how to leverage LangGraph's multi-agent architecture and hybrid knowledge base technology to build a high-precision legal case analysis platform, focusing on the Enron litigation...
Model Hallucination with React Agent
I have created a react agent using langgraph.prebuilt module that uses 3 tools
generate_sql_query_tool
execute_sql_query_tool
analyze_query_results_tool
The LLM appears to be generating fake or synth...
Contrastive Augmented Generation (CAG): AI’s Secret Weapon for Smarter Answers
Artificial Intelligence has made massive strides in generating human-like text, but one persistent challenge remains: accuracy and reliability. We’ve all seen those moments when chatbots confidently...
Langgraph Visualization with get_graph
LangGraph is a library created to make it easier to create stateful, multi-agent applications that make use of Large Language Models (LLMs). By expressing complex agent operations as cyclic graphs, it...
Multilevel RAG
PREMISE
Simply breaking an entire document into regular CHUNKs has some disadvantages:
It does not allow you to incorporate all the semantics of the context because the cut can potentially oc...