Open-Networking

  AI models 1.opanai(chatcpt) 2.Anthropic(claude) 3.google(gemini) 4.Llama(open-source) 5.Deepseek we can use browser to access these   > to test prompt We can use APIs to access these models > to build Apps Gen AI Framwork (chain,flow,pipeline of components) 1.Langchain 2.LlamaIndex 3.haystack Building a chain = connecting steps into a pipeline Type of chains Simple chain → prompt + LLM RAG chain → retriever + prompt + LLM Agent chain → tools + reasoning + LLM Agentic AI framwork  1.CrewAI  2.autogen 3.metaGPT RAG RAG sits between your app/agent and the LLM User  ↓ Agent / App Logic  ↓ RAG (data retrieval layer)  ↓ LLM (reasoning)  ↓ Response

 ML Python pkg 1.numpy 2.pandas 3.Matplotlib 4.seaborn 5.scikitlearn Maths 1.Linear algebra 2.statistics 3.probability 4.calculus EDA - Exploratory Data Analysis (data trasform) Types - supervised learning,unsupervised learning & reinforced learning (Algorithms will be used) usecase - Training & Testing a model Good for Beginers & Freshers AI python basics Gen AI framework - Langchain,Langgraph,LlamaIndex,haystack,sematic kernel Agentic AI framework -  CrewAI & autogen, metaGPT RAG fine-tuning (open source model)- unsloth Google ADK MCP A2A use case - Build production Applications Good for Experienced 

AI Agent Flow: [1] User Input      ↓ [2] Python Agent      ↓ [3] Run CLI Commands (docker exec)      ↓ [4] Collect Outputs (BGP + Interfaces)      ↓ [5] Build Prompt (VERY IMPORTANT)      ↓ [6] Send to LLM (Ollama API)      ↓ [7] LLM Reasoning (pattern matching + inference)      ↓ [8] Structured Answer      ↓ [9] Print to User Use Case Best LLM BGP troubleshooting                                Claude 🥇 Automation scripts (Ansible/Python)       OpenAI 🥇 Full AI agent (balanced)                           OpenAI Deep root cause analysis                         Claude Local lab (free)                     ...

  Why is it called "AI Factory"? The term was coined by NVIDIA's Jensen Huang . The analogy is: Traditional Factory: AI Factory: Raw materials Raw Data ↓ ↓ Assembly line GPU Compute ↓ ↓ Finished product Trained AI Model / Tokens Just like a factory mass-produces physical goods , an AI Factory mass-produces intelligence — tokens, embeddings, model outputs. Key characteristics that make it a "factory": Factory concept AI Factory equivalent Assembly line GPU pipeline (data → training → inference) Raw material Data (text, images, video) Machines GPUs (H100, H200, B200) Factory floor Data center / GPU cluster Output Trained models, tokens, predictions Throughput metric Tokens/sec, FLOPS/sec Uptime = revenue GPU utilization = revenue The entire infrastructure — networking, power, cooling, storage — is engineered around one goal: k...

  INCAST Spectrum-X switches Bluefield DPUs Flow level loadbalancing vs packet level loadbalancing (spraying) Leads to out-of-order  NVIDIA's RoCE (RDMA over Converged Ethernet) RDMA HPC - high performance computing Need for - high speed low latency connections  Eveyday internet use TCP/IP not good for this Application > OS > TCP/IP stack > NIC card (CPU intence) - adds latency RDMA Approach -rNIC offlocading (OS,stack) 1.Infiniband (dedicated nw switch & nic) 2.iWARP - internet wide area RDMS protocol (need iWARP capablie NICs) 3a.RoCE 3b.RoCEv2 (UDP+IP packets) for RDMA lossless is must *traditional ethernet is lossy when there is a congestion 1.MTU 2.QoS - prioritse roce packet dscp 3.PFC - priority flow control    Network switch (receving switch send a pause frame to sending switch , this will make sending switch to stop sending for some time)    this will help in lossless transaction but intraduce Head-of-line-blocaking  4.DCQCN ...

  NVIDIA RoCE (RDMA over Converged Ethernet) Adaptive Routing is a fine-grained, dynamic load-balancing technology designed to eliminate network congestion and maximize bandwidth in high-performance AI and GPU training environments . Unlike traditional Ethernet that relies on static path selection, RoCE Adaptive Routing  acts on a per-packet basis, rerouting data in real-time to avoid congestion .   NVIDIA Developer  +2 This technology is a core component of the  NVIDIA Spectrum-X networking platform , operating in conjunction with  Spectrum-4 switches  and  BlueField-3 Data Processing Units (DPUs) .   NVIDIA Developer  +1 How RoCE Adaptive Routing Works The process involves close coordination between the network fabric (switches) and the endpoints (DPUs):   Packet-Level Dynamic Routing (Spectrum-4 Switch): As packets arrive, the Spectrum-4 switch evaluates the egress queue loads for all available paths to the destination. Instead o...