Translate article

content/en/post/evaluate-local-ai-with-ease-on-ovhcloud/index.md

@@ -0,0 +1,242 @@
+---
+title: "Master Your AI: Explore Local AI with OVH for Just 1 Dollar"
+date: !!timestamp '2024-09-04 11:12:00'
+image: /post/evaluate-local-ai-with-ease-on-ovhcloud/og.webp
+toc: true
+tags:
+- ai
+- cloud
+- hosting
+- privacy
+---
+
+Today, generative AIs meet many uses, and it would be a shame not to take advantage of them.
+However, in the age of the GDPR, it's legitimate to question the exposure of customer or partner data when relying solely on AI providers whose data processing remains opaque.
+
+Having myself participated in the construction of one of these new virtual assistant services, I offer here a simple guide to starting up a machine and evaluating the performance of your AI application, or [to offering your employees access to sovereign AI](https://nextcloud.com/blog/nextcloud-releases-assistant-2-0-and-pushes-ai-as-a-service/), with the aim of easily comparing the different models available.
+
+<!-- more -->
+
+This tutorial will show you how to migrate your existing application from an external provider to your own AI service in the cloud.
+
+## Requirements
+
+To carry out this test, we'll need :
+
+- an OVHcloud account,
+- a domain name (hosted by OVH or not),
+- a sub-domain dedicated to this experiment,
+- an application to be migrated,
+- 1 $.
+
+### Domain Name
+
+In the rest of this tutorial, I'll be using the `example.com` domain.
+Within this domain, I've reserved the sub-domain `ia` for experimentation.
+When you see `ia.example.com.`, feel free to replace it with your own domain.
+
+
+### Our Example Application
+
+Here's a very basic example of an application using OpenAI's ChatGPT:
+
+```python
+import os
+from openai import OpenAI
+
+client = OpenAI(
+    api_key=os.environ.get("OPENAI_API_KEY"),
+)
+
+chat_completion = client.chat.completions.create(
+    messages=[
+        {
+            "role": "user",
+            "content": "Suggest a travel itinerary to visit Norway",
+        }
+    ],
+    model="gpt-4",
+)
+
+print(chat_completion.choices[0].message.content)
+```
+
+It's a simple script that asks a virtual assistant a question and displays its answer in return, on the standard output.
+
+In the case of a more complex application, we'll see that the changes required are minimal and realistic.
+
+
+### Costs
+
+It costs €1 to rent a machine for an hour, with a graphics card capable of handling a wide range of scenarios.
+
+If you have a more complex application, this may require more than an hour's testing, but we can see that cost is not a decisive factor in not testing.
+
+Note also that OVHcloud is offering a €200 cloud credit for all new Public Cloud projects, giving you the opportunity to evaluate all their GPU-enabled machines, free of charge.
+
+Ready?
+
+## Creating Our Test Machine
+
+OVHcloud offers to [rent machines with graphics cards by the hour](https://www.ovhcloud.com/en/solutions/nvidia/), in their Public Cloud offer.
+This is the basis for our evaluation: prices range from €1 to €3 per hour.
+
+### 1. Public Cloud Project
+
+To get started, we'll need to create a Public Cloud project.
+
+Go to the OVH manager console, in the Public Cloud section, to create a new project.
+
+![Create a new project](project-public-cloud.png)
+
+Enter a name for the project, which will only be useful for finding your way around the OVH console later on.
+
+A second screen will ask you for the payment method to be debited.
+As this is a cloud offer, the invoice arrives at the end of the month, depending on what you've used during the month.
+
+If this is your first OVHcloud project, don't forget to enter the promo code to benefit from the €200 in credits.
+
+
+### 2. Start a New Instance
+
+Once you've created your project, all the cloud offerings are just a click away.
+
+The one we're interested in here is “Compute”.
+We're going to “Create an instance”:
+
+![Your project's welcome screen](onboarding.png)
+
+#### Instance Type
+
+We want a machine with a graphics card, so go to the GPU tab.
+
+There's a wide choice of machines, with different characteristics in terms of hardware, amount of RAM and graphics card(s).
+The best choice for evaluating models is to use those with NVIDIA L4 or NVIDIA L40S graphics cards: L4-90 or L40S-90 respectively.
+The latter type of instance is 2 times more expensive per hour, and is only useful if you intend to evaluate larger models such as [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev.
+).
+
+![Let's select an L4-90 instance](select-ia-instance.png)
+
+#### Geographical Location
+
+Next, choose a datacenter in which to start the instance.
+There may not be one in every datacenter, but that doesn't matter anyway, as this is a simple evaluation.
+
+#### Operating System Selection and Configuration
+
+Next comes the question of the operating system.
+
+I recommend you choose the latest version of Ubuntu to use [the cloud-init script]({{< relref "cloud-init-to-deploy-localai-in-5-minutes" >}}) which will deploy everything you need automatically.
+
+![Select operating system](select-os.png)
+
+Add an SSH key, even though you probably won't need it today:
+
+![Add SSH key](select-ssh-key.png)
+
+#### Instance Configuration
+
+Now comes the instance configuration.
+We're going to pass a post-installation script so that the machine is configured as it should be, without having to connect to it:
+
+![We add a post-installation script](select-config-1.png)
+
+Place the contents of the [`cloud-init` script I shared with you in this article]({{< relref "cloud-init-to-deploy-localai-in-5-minutes#machine-with-graphic-map" >}}), in the *small* dedicated text field:
+
+![The added post-installation script](select-config-2.png)
+
+{{% card color="warning" title="Post-installation script" %}}
+
+**⚠️ Don't forget to change the domain name in the `cloud-init` script!**
+
+{{% /card%}}
+
+The post-installation script will automatically install the [LocalAI](https://localai.io/) service.
+This is a service that exposes an API fully compatible with OpenAI, but using AI models directly on the machine.
+No data is sent outside the machine.
+
+#### Network Mode
+
+Last question: how is the machine connected?
+
+To keep things simple, we choose Public mode, which assigns a public IP to the machine.
+
+![Public mode provides a public IPv4](select-network.png)
+
+This will enable us to contact our AI service without having to go through another service, such as a load balancer.
+In a production setup, we'd obviously want to use a *load-balancer*, but it's superfluous here.
+
+#### We're off!
+
+We're off!
+
+All that's left to do is choose the hourly rate, then validate the form to start creating the instance.
+
+The billing method to choose](select-price.png)
+
+Allow 10 minutes before the machine is fully operational:
+
+- 1 minute for OVH to allocate a machine and start it up,
+- 8 minutes to run the cloud-init script: configure and download containers, then download templates.
+
+### 3. Domain Name Configuration
+
+While the instance is starting up, we need to configure our domain name to point our sub-domain `ia.example.com.` to our freshly instantiated machine.
+
+Once the creation has been validated, the OVH robots get to work, allocating a public IP to our machine.
+The operation takes a few seconds, so click on the button to refresh the list:
+
+![Refresh instance list to obtain public IP](instances-1.png)
+
+If the instance creation is successful, you should have an IP assigned to you:
+
+![The instance list with the public IP of our machine](instances-2.png)
+
+Now we need to create a new sub-domain pointing to this IP.
+In the case of OVH, this takes place in the “Web Cloud” section:
+
+![The list of instances with the public IP of our machine](domain-1.png)
+
+We create the sub-domain `ia`, pointing to the IP given by OVH:
+
+![The list of instances with our machine's public IP](domain-add.png)
+
+{{% card color="info" title="Set the TTL" %}}
+
+The TTL indicates the length of time the record will remain in the DNS servers' cache.
+Specify a rather low value, such as 60 or 120 (these are seconds), so that you can change machines without waiting too long.
+
+{{% /card%}}
+
+If your DNS provider isn't OVH (and even if it is), you can use [happyDomain to easily modify your domain](https://www.happydomain.org/).
+
+
+## AI Evaluation
+
+All that remains now is to modify our application so that it uses our AI service rather than OpenAI :
+
+```patch
+ client = OpenAI(
+-    api_key=os.environ.get("OPENAI_API_KEY"),
++    endpoint="https://ia.example.com/v1",
+ )
+```
+
+That's it!
+As the LocalAI API is compatible, all the services used will work with the local templates.
+
+We should add, however, that the model names are different.
+For example, if we have `gpt-4` in LocalAI, it's actually an alias to `phi-2` or `hermes-2-pro-mistral` models, depending on the hardware configuration.
+The LocalAI interface allows you to [install other models](https://models.localai.io/).
+It may be necessary to test several of them, as each has its advantages and disadvantages.
+
+Take a look at these in particular:
+
+- [flux.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) for image generation,
+- [hermes-3-llama-3.1-8b](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) to generate text with interesting reflections.
+
+----
+
+The rapid evolution of generative AI offers extraordinary opportunities, but it also poses challenges, particularly in terms of data protection.
+
+Adopting a more sovereign approach, like the one proposed in this tutorial, allows you to take advantage of technological advances while retaining full control over sensitive data, cost control and flexibility. This will enable you not only to guarantee the confidentiality of your information, but also to tailor AI performance to your specific needs, without depending entirely on external service providers. Remember that the effectiveness of AI depends not only on its technical capabilities, but also on how it is integrated and managed within your infrastructure. By taking charge of these aspects, you can ensure that you remain competitive while complying with current regulations.

content/fr/post/cloud-init-to-deploy-localai-in-5-minutes/index.md

@@ -11,7 +11,8 @@ tags:
 
 Utiliser les IA génératives sans partager ses données avec des entreprises ou des États qui raffolent de nos données, c'est possible et accessible.
 
-Le monde des logiciels libres regorge d'applications pour évaluer et utiliser les IA génératives. Après de nombreux tests, je vous présente ici le fichier cloud-init pour déployer votre propre instance de LocalAI en moins de 5 minutes.
+Le monde des logiciels libres regorge d'applications pour évaluer et utiliser les IA génératives.
+Après de nombreux tests, je vous présente ici le fichier cloud-init pour déployer votre propre instance de LocalAI en moins de 5 minutes.
 
 <!-- more -->
 

content/fr/post/evaluate-local-ai-with-ease-on-ovhcloud/index.md

@@ -1,7 +1,7 @@
 ---
-title: "Évaluer l'IA locale grâce à OVH"
+title: "Maîtrisez votre IA : explorez l'IA locale grâce à OVH et 1 €"
 date: !!timestamp '2024-09-04 11:12:00'
-image: /fr/post/evaluate-local-ai-with-ease-on-ovhcloud/og.webp
+image: /post/evaluate-local-ai-with-ease-on-ovhcloud/og.webp
 toc: true
 tags:
 - ai
@@ -11,9 +11,9 @@ tags:
 ---
 
 Les IA génératives répondent aujourd’hui à de nombreux usages, et il serait dommage de ne pas en tirer parti.
-Cependant, à l’heure du RGPD, il est légitime de se questionner sur l’exposition des données de ses clients ou partenaires lorsqu’on se repose uniquement sur des prestataires dont le traitement des données reste opaque.
+Cependant, à l’heure du RGPD, il est légitime de se questionner sur l’exposition des données de ses clients ou partenaires lorsqu’on se repose uniquement sur des prestataires d'IA dont le traitement des données reste opaque.
 
-Ayant moi-même participé à la construction de l’un de ces nouveaux services d’assistant virtuel, je vous propose ici un guide simple pour démarrer une machine et évaluer les performances de votre application IA, ou [pour offrir à vos employés un accès à une IA souveraine](https://nextcloud.com/blog/nextcloud-releases-assistant-2-0-and-pushes-ai-as-a-service/), en comparaison avec les différents modèles disponibles.
+Ayant moi-même participé à la construction de l’un de ces nouveaux services d’assistant virtuel, je vous propose ici un guide simple pour démarrer une machine et évaluer les performances de votre application IA, ou [pour offrir à vos employés un accès à une IA souveraine](https://nextcloud.com/blog/nextcloud-releases-assistant-2-0-and-pushes-ai-as-a-service/), dans le but de comparer facilement les différents modèles disponibles.
 
 <!-- more -->
 
@@ -204,6 +204,8 @@ Indiquez une valeur plutôt basse, comme 60 ou 120 (c'est des secondes), pour po
 
 {{% /card%}}
 
+Si votre hébergeur DNS n'est pas OVH (et même si c'est OVH d'ailleurs), vous pouvez utiliser [happyDomain pour modifier facilement et sans crainte votre domaine](https://www.happydomain.org/).
+
 
 ## Évaluer l'IA