« AI Concept » : différence entre les versions

De Marijan Stajic | Wiki
Aller à la navigation Aller à la recherche
mAucun résumé des modifications
 
(11 versions intermédiaires par le même utilisateur non affichées)
Ligne 1 : Ligne 1 :
[[Fichier:N1 Kubernetes.png|none]]
= Notions =


https://learn.microsoft.com/en-us/azure/azure-functions/functions-bindings-http-webhook-trigger?tabs=python-v2%2Cisolated-process%2Cnodejs-v4%2Cfunctionsv2&pivots=programming-language-csharp <br>
There are other notions that are important to understand in relation with AI technologies.
https://learn.microsoft.com/en-us/azure/azure-functions/functions-networking-options?tabs=azure-portal <br>
https://komodor.com/blog/aiops-for-kubernetes-or-kaiops/ <br>
https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/ai-agent-design-patterns <br>
https://learn.microsoft.com/en-us/azure/architecture/ai-ml/architecture/baseline-azure-ai-foundry-chat <br>
 
[[Fichier:N1 Kubernetes Without Azure.drawio.png|none]]
Technologies :
* K8SGPT
* LangChain (+ LangFuse pour monitoring?)
* Ollama (+ il y a des trucs qui permettent d'améliorer les perfs des modèles)
* MCPO // OpenWebUI
* Machine Virtuelle chez Exo bien boostée
 
= Glossary =


== Large Language Model (LLM) ==
== Large Language Model (LLM) ==
Ligne 25 : Ligne 11 :
== Model Context Protocol (MCP) ==
== Model Context Protocol (MCP) ==


A '''Model Context Protocol (MCP)''' is a protocol that '''standardizes communication between Large Language Models'''  (LLMs) and ''' external systems''' , such as ITSM tools (like ServiceNow), Kubernetes clusters, and more.
A '''Model Context Protocol (MCP)''' is a protocol that '''standardizes communication between Large Language Models'''  (LLMs) trough an '''Agent AI''' and ''' external systems''' , such as ITSM tools (like ServiceNow), Kubernetes clusters, and more.


You can use an ''' MCP client''' , for example, '''Continue.dev'''  in your IDE (like VS Code) and then '''configure MCP servers''', such as your Kubernetes cluster, to enable your LLM to interact with these systems.
You can use an ''' MCP client''' , for example, '''Continue.dev'''  in your IDE (like VS Code) and then '''configure MCP servers''', such as your Kubernetes cluster, to enable your LLM to interact with these systems.
Ligne 31 : Ligne 17 :
== Retrieval-Augmented Generation (RAG) ==
== Retrieval-Augmented Generation (RAG) ==


= Technology Stack =
== Low-Code / No-Code ==
 
== LangChain ==
 
'''LangChain''' is an '''application framework''' that '''helps structure your prompts''' using PromptTemplate. For example, with an alerting system, when the '''AI is queried''', you can '''create a template''' that guides it to follow a consistent '''debugging structure''' in its responses :
 
<pre class="linux">
from langchain import PromptTemplate
 
prompt = PromptTemplate(
    input_variables=["alert", "logs", "metrics"],
    template="""
Tu es un expert Kubernetes.
Un incident a été détecté :
{alert}
 
Voici les logs du pod :
{logs}
 
Voici ses métriques :
{metrics}
 
Analyse les causes probables et propose des actions correctives précises.
"""
)
</pre>
 
== K8sGPT ==


'''K8sGPT''' is an '''open-source tool''' that '''scans Kubernetes clusters''', detects issues, and uses a Large Language Model (LLM) such as Azure OpenAI to explain problems and suggest solutions in natural language.
== Prompt Engineering ==


== Ollama ==
Prompt engineering is the practice of '''crafting clear''', '''structured instructions''' to '''guide AI models''' toward producing optimal outputs. Based on my experience :


'''Ollama''' is an '''open-source tool''' that lets you '''download and run large language models''' (LLMs) like Llama 3 or Mistral locally, allowing you to use AI '''without relying on the cloud'''.
* '''Rule 1 :''' '''DON'T''' write '''too much text at once'''; if possible, break the work into '''sequences'''. Otherwise, '''use functions''' of the app.
* '''Rule 2 :''' '''DON'T''' ask the '''AI to write prompt engineering instructions for another AI''', it creates an infinite loop and wastes time.
* '''Rule 3 :'''  🎯 '''Use emojis''' to clarify and sequence your prompt, helping the '''AI recognise when there's a new instruction'''.

Dernière version du 23 décembre 2025 à 21:57

Notions

There are other notions that are important to understand in relation with AI technologies.

Large Language Model (LLM)

A Large Language Model (LLM) is the engine behind an AI application such as ChatGPT. In this case, the engine powering ChatGPT is GPT-4 (or GPT-4o, previously), which is the LLM used by the application.

Azure AI Foundry is a service that allows you to choose which Large Language Model (LLM) you want to use.

Model Context Protocol (MCP)

A Model Context Protocol (MCP) is a protocol that standardizes communication between Large Language Models (LLMs) trough an Agent AI and external systems , such as ITSM tools (like ServiceNow), Kubernetes clusters, and more.

You can use an MCP client , for example, Continue.dev in your IDE (like VS Code) and then configure MCP servers, such as your Kubernetes cluster, to enable your LLM to interact with these systems.

Retrieval-Augmented Generation (RAG)

Low-Code / No-Code

Prompt Engineering

Prompt engineering is the practice of crafting clear, structured instructions to guide AI models toward producing optimal outputs. Based on my experience :

  • Rule 1 : DON'T write too much text at once; if possible, break the work into sequences. Otherwise, use functions of the app.
  • Rule 2 : DON'T ask the AI to write prompt engineering instructions for another AI, it creates an infinite loop and wastes time.
  • Rule 3 : 🎯 Use emojis to clarify and sequence your prompt, helping the AI recognise when there's a new instruction.
Récupérée de "https://wiki.stajic.me/index.php?title=AI_Concept&oldid=2928"