Skip to content
GitHubDiscordThreads

Archive

2026

Test MDX Blog Post

LLM

import Table from '../../../../components/Table.astro' export const data = 'Name', 'Age', 'City', 'John', '25', 'NYC', 'Jane', '30', 'LA...

ChatGPT in 2025: A Year in Review

LLM

<!-- more --> My ChatGPT Summary in 2025 !ChatGPT Stats(/assets/images/2026/chat%20stats.png) !ChatGPT Growth(/assets/images/2026/chatgpt.png) !Cha...

2025

LLM Interview Questions

LLM

Questions <!-- more --> Machine Learning ??? tip "Machine Learning Concepts" ??? question "How would you describe the concept of machine learn...

LLM Training Epoch

LLM

Impact of Multi-Epoch On LLM Training <!-- more --> As large language models (LLMs) scale up, researchers have begun to notice a growing imbalance b...

vllm throughput

LLM

Optimizing vLLM Token Throughput: KV-Cache Techniques <!-- more --> Introduction > In large-language-model (LLM) inference serving contexts, once t...

LangGraph Reflection

LLM

<!-- more --> Langgraph Reflections Overview !Overview(/assets/images/2025/Langgraph_Reflections.png) Reflection is related to agent self-improv...

LangGraph Sample Project

LLM

<!-- more --> LangGraph Sample Project Objective - x Independent deployable services - Each agent can scale horizontally (e.g., analysis_service...

LangChain/LangGraph Q&A

LLM

<!-- more --> LangChain/LangGraph Q&A !!! question "Question 1: What is the core design philosophy of LangGraph? Compared to traditional sequentia...

Training LLM From Zero

LLM

1. Objective(objective) 2. Environment Setup(environment-setup) <!-- more --> Objective The goal of this project is to design, implement, and trai...

FastMCP MCP Server Hub

LLM

<!-- more --> MCP Server Hub Currently, our different projects are using various MCP servers. To streamline and unify the process, we plan to implem...

How LLM Tools work

LLM

<!-- more --> Tools in Large Language Models (LLMs) > Tools enable large language models (LLMs) to interact with external systems, APIs, or data sour...

LangChain Retry Logic

LLM

<!-- more --> LangChain Invoke Retry Logic LLM call is not stable and may fail due to network issues or other reasons, therefore, retry logic is nece...

MCP Transports

LLM

<!-- more --> MCP Transports Overview | Feature | stdio | sse (Server-Sent Events) ...

Text to SQL (Smolagents)

LLM

<!-- more --> Guide to Setting Up a Text to SQL Agent with smolagents This is implemented from the guide Code(https://huggingface.co/docs/smolagents...

MCP Server & Client (SSE)

LLM

<!-- more --> Guide to Setting Up a MCP Server/Client (SSE Protocol) This guide is inspired by - Step-by-Step Guide: Building an MCP Server usin...

RAG-Reranking

LLM

<!-- more --> Reranking in Retrieval-Augmented Generation (RAG) Retrieval-Augmented Generation (RAG) is a powerful approach that combines retrieval...

Ollama Import GGUF Models

LLM

<!-- more --> Ollama Models If you're looking to experiment with various models easily, importing GGUF might be your go-to method. Here's how it wo...

GenAI Projects

LLM

<!-- more --> > > Learning never exhausts the mind <br> > &nbsp; &nbsp; &nbsp; &nbsp; ― Leonardo da Vinci Collections Blogs |Name|URL| |---|---|...

Crawling the Web with LLM

LLM

Crawling the Web with Large Language Models (LLMs) <!-- more --> Frameworks - Skyvern - ScrapegraphAI - Crawl4AI - Reader - Firecrawl - Markdowner ...

LangGraph VS AutoGen

LLM

LangGraph VS AutoGen <!-- more --> |Feature| LangGraph| AutoGen| |---|---|---| |Core Concept| Graph-based workflow for LLM chaining| Multi-agent sys...

Autogen Intro and RAG Workflow

LLM

Introduction to Autogen <!-- more --> Autogen(https://github.com/microsoft/autogen) AutoGen is a framework for creating multi-agent AI applications ...

Local LLM Setup

LLM

Local LLM Setup <!-- more --> Introduction This guide will walk you through setting up a local language model (LLM) using Ollama. Ollama is an open-...

2024

Gradio with Ollama

python

Simple Unstructured file processing We have a lot of pdf files that contain import information, however, the information are unstructured (text, table...

Databricks Wheel Job

python

Databricks Jobs <!-- more --> Recently I successfully deploy my python wheel to Databricks Cluster. Here are some tips if you plan to deploy pyspark. ...

Python Decorator

python

Python decorators :question_mark: Why we need decorator :bulb: It will extend your function behaviors during runtime. <!-- more --> For example, you...

ZIO

Scala

Scala Full Stack Recently I read a Blog(https://adrianfilip.com/2022/06/27/scala-3-zio-2-zhttp-laminar-proof-of-concept-impressions/) that introducin...

Reflex Learning

python

Reflex (pynecone) Reflex is a library to build full-stack web apps in pure Python. <!-- more --> - Repo(https://github.com/reflex-dev/reflex) - Video ...

How to execute python modules

python

<!-- more --> runpy module We can use internal runpy to execute different moduls in our project. This is used in my pyspark project. python title...

AutoGen HttpClient

LLM

HttpClient <!-- more --> python linenums="1" title="my_client.py" import httpx class MyHttpClient(httpx.Client): def __deepcopy__(self, dummy)...

Model Registry

ML

<!-- more --> Problem: How to introduce ml-based production/features to cross-functional teams. Question: - Where can we find the best version of th...

2021

Setup Minikube

k8s

Setup Minikube <!-- more --> Installation bash brew upgrade brew install minikube brew install kubectl minikube kubectl -- get pods -A Start/St...

2020

Spark Optimization

spark

Spark run faster and faster - Cluster Optimization - Parameters Optimization - Code Optimization <!-- more --> Cluster Optimization Locality Level...

Spark SQL

spark

<!-- more --> Spark Submit options txt --master MASTER_URL --> 运行模式 例:spark://host:port, mesos://host:port, yarn, or local. --deploy-mode DEPLOY_...

Airflow

airflow

<!-- more --> Code snippet py import airflow from airflow.models import DAG from airflow.operators.python_operator import PythonOperator defa...

Batch Normalization

ML

Batch Normalization is one of important parts in our NN. Why need Normalization This paper title tells me the reason Batch Normalization: Accelerati...

Gradient Descent

ML

gradient-based optimization algorithms <!-- more --> Gradient Descent variants Batch Gradient Descent (BGD) Vanilla gradient descent, aka batch g...

2012

Repo List

Repos <div align="center"> <table> <tr> <td colspan="2" align="center">Repo List</td> </tr> <tr> <td align="center">l...