AI on Learning Notes

MLOps

Mon, 01 Jan 0001 00:00:00 +0000

Moniotor/Logging/K8S #

Name	Doc	Github	Note	Next
OpenTelemetry	Docs	Github	OpenTelemetry is a collection of APIs, SDKs, and tools for generating, collecting, and exporting telemetry data (traces, metrics, and logs).	Getting Started with OpenTelemetry
Prometheus	Docs	Github	Prometheus is a systems and service monitoring system.
Thanos	Docs	Github	Thanos is a set of components that can be composed into a highly available Prometheus setup.
Zabbix	Docs	Github	Zabbix is an enterprise-class open-source monitoring solution for tracking the status of various network services, servers, and other network hardware.
Grafana	Docs	Github	Grafana is an open source, feature rich metrics dashboard and graph editor for Graphite, InfluxDB, Prometheus and other time series databases.
Loki	Docs	Github	Loki is a horizontally-scalable, highly-available, multi-tenant log aggregation system inspired by Prometheus.
containerd	Docs	Github	containerd is an industry-standard container runtime with an emphasis on simplicity, robustness, and portability. It manages the complete container lifecycle, including image transfer, storage, container execution, networking, and low-level runtime integration through OCI runtimes such as runc. It is the default container runtime used by Kubernetes (via CRI).	Need Real Install
runc	Docs	Github	runc is a lightweight, portable, OCI-compliant container runtime. It is responsible for creating and running containers by directly interacting with Linux kernel features such as namespaces and cgroups. runc is the default low-level runtime used by containerd and Kubernetes environments.	Need Real Install
	Docs	Github
	Docs	Github
	Docs	Github
	Docs	Github
	Docs	Github
	Docs	Github

MLOps #

Name	Doc	Github	Note
mlflow	Doc	Github	侧重模型实验追踪 (Tracking) 和生命周期管理
MLRun	Doc	Github	编排式的 MLOps 框架，强于实时数据处理与自动化
Airflow	Doc	Github	通用的工作流调度平台，基于 Python DAG
Argo	Doc	Github	云原生 (K8s) 工作流引擎，适合 CI/CD 和数据流水线
Kubeflow	Doc	Github	基于 K8s 的端到端机器学习平台，生态完整但相对复杂
Databricks	Doc	Github	统一数据分析平台，由 Spark 创始团队打造，深度集成 MLflow
DVC	Doc	Github	机器学习版本控制工具，类似“数据界的 Git”
BentoML	Doc	Github	专注于模型打包、部署与高性能模型服务的框架
Ray	Doc	Github	分布式计算框架，常用于大规模模型训练和在线推理

https://mlops.swiss-ai-center.ch/syllabus/

Learning Map

Mon, 01 Jan 0001 00:00:00 +0000

Maps: #

快速入门AI领域的思维导图（深度学习自学入门） #

Sources #

Name	Doc	Github	Note
Nvidia	Doc	Github	k8s-device-plugin

Reference #

快速入门AI领域的思维导图（深度学习自学入门）

Learning Note

Mon, 01 Jan 0001 00:00:00 +0000

Notes: #

👍 动手学习大模型 (hands-on-llms)

Nvidia Training-CN

Machine Learning Engineering for Production (MLOps), Youtube, Cousera

AI老兵文哲-大模型科普

Udmey - ML Ops Fundamentals Course | MLOps Specialization

End-to-End MLOps project with Open Source tools

2026年李宏毅最新课程：智能体AI（AI Agent）

microsoft/ai-agents-for-beginners

#

项目 #

企业知识库问答Agent （RAG+权限+引用溯源+后台管理）
多工具办公Agent （读邮件/读表格/生成周报/自动归档）

Free GPU Tools #

Vendor	GPU	Runtime limit	Time limit	RAM
Google Colab	NVIDIA T4 / TPU	12 hours/session	–	16GB
ModelScope	CPU
Kaggle	NVIDIA TESLA P100	9 hours/session	30 hours/week	16GB
Codesphere	Shared GPU’s	60 minutes of inactivity	–	5GB
Paperspace Gradient	NVIDIA Quadro M4000	6 hours/session	–	8GB
SageMaker Studio Lab	NVIDIA T4 Tensor Core	4 hours/session	4 hours in a 24-hour period.	16GB
Lightning AI	Various	4 hours/session	80 hours/month	–

AI/Machine Learning Toolkit #

Toolkit	Website	Doc	Github	Note
PyTorch	Website	Doc	Github	主流深度学习框架，以灵活的动态计算图和强大的研究社区著称。
CUDA	Website	Doc	Github
TensorFlow	Website	Tutorial	Github	主流的深度学习框架，生产部署生态完善，支持大模型训练。
Kubeflow	website	Doc	Github	致力于使Kubernetes上的机器学习工作流（流水线、训练、服务）的部署变得简单、可移植和可扩展。
Airflow	Website	Doc	Github	以代码方式定义、调度和监控工作流的平台，是ML工作流编排的事实标准之一。
Prometheus	Website	Doc	Github	开源系统监控和警报工具包，常用于收集和存储ML系统的性能指标。
Grafana	Website	Doc	Github	可视化监控数据的仪表盘工具，常与Prometheus配合使用展示GPU利用率等指标。
	Website	Doc	Github
	Website	Doc	Github
	Website	Doc	Github
	Website	Doc	Github
	Website	Doc	Github
	Website	Doc	Github

NVIDIA/… #

2024吃透AI大模型（LLM+RAG系统+GPT-4o+OpenAI）

LLM & RAG

Mon, 01 Jan 0001 00:00:00 +0000

Notes: #

RAG (Retrieval Augmented Generation) #

What is RAG?, RAG VS Fine Tuning

LLM (Large Language Model) #

What are large language models (LLMs)?

WIKI

Introduction to Large Language Models

what is Transformer / GPT?

Tools table #

Toolkit	Website	Doc	Github
LangChain	Official	Doc	Github
LlamaIndex	Official	Doc	Github
RagFlow	Official	Doc	Github

Reference #

LangChain

Conda

Google Machine Learning Education

DeepSeek

Mon, 01 Jan 0001 00:00:00 +0000

Deepseek #

Github

OpenAI VS DeepSeek

清华大学：DeepSeek从入门到精通（2025）， PDF

#

Tools	Website	Note
DeepSeek Chat
SCNet
SiliconFlow
volcenginer
Tencent	T.Cloud	DeepSeek-R1-Distill-Qwen-32B 免费体验

LLM (Large Language Model) #

Reference #

Hugging Face， ModelScope

gpt-tokenizer

Qwen

Mon, 01 Jan 0001 00:00:00 +0000

千问Qwen #

Demo, 阿里云百炼

Model Name	Doc	Github	Node
Qwen-Agent	Doc	Github	Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
QwenLM/Qwen3	Doc	Github	LLM
	Doc	Github

QwenLM

Reference #

aliyun

Hello-Agents

Mon, 01 Jan 0001 00:00:00 +0000

Hello-Agents #

Name	Doc	Github	Note
Github	Datawhale-web	Datawhale-Github	Bili
AIHubmix
ModelScope

Tools #

Name	Doc	Github	Note
Dify	Doc	Github	开源的 LLM 应用开发平台，集成 RAGPipeline 和工作流编排，非常适合快速落地 AI 项目。
n8n	Doc	Github	强大的工作流自动化工具，支持节点式编程，常用于 AI Agent 的业务逻辑集成。
Coze	Doc	N/A	字节跳动推出的 AI 聊天机器人开发平台，支持丰富的插件和多模态能力（闭源但社区生态极强）。
Flowise	Doc	Github	基于 LangChain 的可视化拖拽界面，适合构建定制化的 LLM 链和 Agent。
Langflow	Doc	Github	另一个主流的 Python 原生可视化编排工具，与 LangChain 生态深度绑定。
MLflow	Doc	Github	传统的 MLOps 标配，专注于实验追踪、模型打包和版本管理。
BentoML	Doc	Github	统一的模型分发和部署框架，支持 GPU 推理优化，是模型上线阶段的关键工具。

框架	Doc	Github	核心概念	主要优势	典型应用场景	Note
AutoGen	Doc	Github	对话的智能体 (Conversable Agent)	自动化多智能体对话流，高度可定制的交互模式。	自动化代码生成与测试、模拟产品开发流程。	Python
AgentScope	Doc	Github	消息传递 (Message Passing)	易用性强，工程化程度高，支持分布式部署。	构建复杂、可运维的大规模多智能体应用。	Python
CAMEL	Doc	Github	角色扮演 (Role-Playing)	极简的协作设定，通过初始提示驱动自主对话。	探索性任务、创意生成、模拟特定领域专家协作。	Python
LangGraph	Doc	Github	状态图 (State Graph)	天然支持循环和条件分支，精准控制复杂工作流。	实现 Reflection、迭代式优化、需要人工介入的流程。	Python