fix conflict

Author: MathieuBsqt

pages/public_cloud/ai_machine_learning/endpoints_tuto_01_audio_summarizer/guide.en-gb.md

@@ -1,7 +1,7 @@
 ---
 title: AI Endpoints - Create your own audio summarizer
 excerpt: Summarize hours of meetings ASR and LLM AI endpoints
-updated: 2025-04-15
+updated: 2025-04-18
 ---
 
 > [!primary]
@@ -21,23 +21,14 @@ In this tutorial, you will create an Audio Summarizer assistant that can not onl
 
 Indeed, thanks to [AI Endpoints](https://endpoints.ai.cloud.ovh.net/), it’s never been easier to create a virtual assistant that can help you stay on top of your meetings and keep track of important information.
 
-This guide will explore how AI APIs can be connected to create an advanced virtual assistant capable of transcribing and summarizing any audio file using **ASR (Automatic Speech Recognition)** technologies and popular **LLMs (Large Language Models)**. We will also build an app to use our assistant!
+This tutorial will explore how AI APIs can be connected to create an advanced virtual assistant capable of transcribing and summarizing any audio file using **ASR (Automatic Speech Recognition)** technologies and popular **LLMs (Large Language Models)**. We will also build an app to use our assistant!
 
 ![connect-ai-apis](images/ai-endpoint-puzzles-connexion.png)
 
 ## Definitions
 
-**Automatic Speech Recognition (ASR)**
-
-Technology that converts spoken language into written text. 
-
-ASR will be used in this context to transcribe long audio recordings into text, which will then be summarized using LLMs.
-
-**Large Language Models (LLMs)**
-
-Advanced models trained to understand context and generate human-like responses. 
-
-In this use case, the LLM prompt will be designed to generate a summary of the input text based on the output from the ASR endpoint.
+- **Automatic Speech Recognition (ASR)**: Technology that converts spoken language into written text. ASR will be used in this context to transcribe long audio recordings into text, which will then be summarized using LLMs.
+- **Large Language Models (LLMs)**: Advanced models trained to understand context and generate human-like responses. In this use case, the LLM prompt will be designed to generate a summary of the input text based on the output from the ASR endpoint.
 
 ## Requirements
 
@@ -69,15 +60,15 @@ python-dotenv==1.0.1
 
 Then, launch the installation of these dependencies:
 
-```
+```console
 pip install -r requirements.txt
 ```
 
 *Note that Python 3.11 is used in this tutorial.*
 
 ### Importing necessary libraries and variables
 
-Once this is done, you can create a Python file named `audio-summarizer-app.py`, where you will first import Python librairies as follow:
+Once this is done, you can create a Python file named `audio-summarizer-app.py`, where you will first import Python librairies as follows:
 
 ```python
 import gradio as gr
@@ -153,7 +144,7 @@ def asr_transcription(audio):
 
 **In this function:**
 
-- The audio file is preprocessed as follow: `.wav` format, `1` channel, `16000` frame rate
+- The audio file is preprocessed as follows: `.wav` format, `1` channel, `16000` frame rate
 - The transformed audio `processed_audio` is read
 - An API call is made to the ASR endpoint named `nvr-asr-en-gb`
 - The full response is stored in `resp` variable and returned by the function
@@ -278,7 +269,7 @@ if __name__ == '__main__':
 
 ### Launch Gradio web app locally
 
-🚀 That’s it! Now, your web app is ready to be used! You can you can start this Gradio app locally by launching the following command:
+🚀 That’s it! Now, your web app is ready to be used! You can start this Gradio app locally by launching the following command:
 
 ```python
 python audio-summarizer-app.py

pages/public_cloud/ai_machine_learning/endpoints_tuto_02_voice_virtual_assistant/guide.en-gb.md

@@ -1,7 +1,7 @@
 ---
 title: AI Endpoints - Create your own voice assistant
 excerpt: Create a voice-enabled chatbot using ASR, LLM, and TTS endpoints in under 100 lines of code
-updated: 2025-04-15
+updated: 2025-04-18
 ---
 
 > [!primary]
@@ -17,7 +17,7 @@ Imagine having a virtual assistant that listens to your voice, understands your
 
 ## Objective
 
-In this guide, you will learn how to create a fully functional Audio Virtual Assistant that:
+In this tutorial, you will learn how to create a fully functional Audio Virtual Assistant that:
 
 - Accepts voice input from a microphone
 - Transcribes it using ASR (Automatic Speech Recognition)
@@ -30,23 +30,9 @@ All of this is done by connecting **AI Endpoints** like puzzle pieces—allowing
 
 ## Definitions
 
-**Automatic Speech Recognition (ASR)**
-
-Technology that converts spoken language into text.
-
-ASR makes it possible in this context for your assistant to understand voice input.
-
-**Large Language Models (LLMs)**
-
-Advanced models trained to understand context and generate human-like responses. 
-
-Here, LLMs will handle the logic and answer your questions intelligently.
-
-**Text-To-Speech (TTS)**
-
-Technology that converts written text into spoken audio. 
-
-With TTS, your assistant will respond with natural-sounding speech, completing the conversation loop.
+- **Automatic Speech Recognition (ASR)**: Technology that converts spoken language into text. ASR makes it possible in this context for your assistant to understand voice input.
+- **Large Language Models (LLMs)**: Advanced models trained to understand context and generate human-like responses. Here, LLMs will handle the logic and answer your questions intelligently.
+- **Text-To-Speech (TTS)**: Technology that converts written text into spoken audio. With TTS, your assistant will respond with natural-sounding speech, completing the conversation loop.
 
 ## Requirements
 
@@ -80,15 +66,15 @@ python-dotenv==1.0.1
 
 Then, launch the installation of these dependencies:
 
-```
+```console
 pip install -r requirements.txt
 ```
 
 *Note that Python 3.11 is used in this tutorial.*
 
 ### Importing necessary libraries and variables
 
-Once this is done, you can create a Python file named `audio-virtual-assistant-app.py`, where you will first import Python librairies as follow:
+Once this is done, you can create a Python file named `audio-virtual-assistant-app.py`, where you will first import Python librairies as follows:
 
 ```python
 import os
@@ -239,7 +225,7 @@ if __name__ == '__main__':
 
 ### Launch Streamlit web app locally
 
-🚀 That’s it! Now, your web app is ready to be used! You can you can start this Streamlit app locally by launching the following command:
+🚀 That’s it! Now your web app is ready to be used! You can start this Streamlit app locally by launching the following command:
 
 ```python
 streamlit run audio-virtual-assistant.py

pages/public_cloud/ai_machine_learning/endpoints_tuto_03_code_assistant_continue/guide.en-gb.md

@@ -1,7 +1,7 @@
 ---
 title: AI Endpoints - Create a code assistant with Continue
 excerpt: Build your own code assistant directly in VSCode or JetBrains IDEs using the Continue plugin
-updated: 2025-04-15
+updated: 2025-04-18
 ---
 
 > [!primary]
@@ -15,7 +15,7 @@ updated: 2025-04-15
 
 Want more control over your code assistant? Looking to integrate your own LLM configuration and use models hosted on **[AI Endpoints](https://endpoints.ai.cloud.ovh.net/)**?
 
-This guide shows you how to build your own developer assistant using **[Continue](https://www.continue.dev/)**, an open-source IDE plugin that works with both VSCode and JetBrains IDEs, in combination with OVHcloud.
+This tutorial shows you how to build your own developer assistant using **[Continue](https://www.continue.dev/)**, an open-source IDE plugin that works with both VSCode and JetBrains IDEs, in combination with OVHcloud.
 
 Continue lets you plug in your own LLMs, enabling full control over which models you use and how they interact with your code.
 

pages/public_cloud/ai_machine_learning/endpoints_tuto_04_sentiment_analyzer/guide.en-gb.md

@@ -1,7 +1,7 @@
 ---
 title: AI Endpoints - Create a sentiment analyzer
 excerpt: Build a sentiment analyzer with AI Endpoints and Java using Quarkus
-updated: 2025-04-15
+updated: 2025-04-18
 ---
 
 > [!primary]
@@ -13,13 +13,13 @@ updated: 2025-04-15
 
 ## Introduction
 
-In this guide, we’ll show you how to create a sentiment analyzer using **[AI Endpoints](https://endpoints.ai.cloud.ovh.net/)** and Java with **[Quarkus](https://github.com/quarkusio/quarkus)**.
+In this tutorial, we’ll show you how to create a sentiment analyzer using **[AI Endpoints](https://endpoints.ai.cloud.ovh.net/)** and Java with **[Quarkus](https://github.com/quarkusio/quarkus)**.
 
 We'll use a model from the `Natural Language Processing (NLP)` category, specifically the `roberta-base-go_emotions` model. This model can analyze text and return emotions in response.
 
 ### Project setup
 
-To simplify the project, we'll use **[Quarkus](https://github.com/quarkusio/quarkus)**. for fast development and REST exposure.
+To simplify the project, we'll use **[Quarkus](https://github.com/quarkusio/quarkus)** for fast development and REST exposure.
 
 Start by adding the necessary dependencies in your `pom.xml`:
 

pages/public_cloud/ai_machine_learning/endpoints_tuto_05_chatbot_langchain_python/guide.en-gb.md

@@ -1,7 +1,7 @@
 ---
 title: AI Endpoints - Build a Python Chatbot with LangChain
 excerpt: Learn how to build a chatbot in Python using LangChain and OVHcloud AI Endpoints
-updated: 2025-04-15
+updated: 2025-04-18
 ---
 
 > [!primary]
@@ -19,7 +19,7 @@ In this tutorial, we’ll use LangChain (Python edition) with OVHcloud **[AI End
 
 ## Objective
 
-This guide demonstrates how to:
+This tutorial demonstrates how to:
 
 - Build a chatbot using LangChain and FastAPI
 - Connect to OVHcloud AI Endpoints to access LLMs
@@ -28,17 +28,10 @@ This guide demonstrates how to:
 
 ## Definitions
 
-**Streaming LLM Response**
-Instead of waiting for a full response from the model, streaming allows the application to start processing output tokens as they’re generated. This creates a smoother, faster user experience—especially useful for chatbots.
-
-**[LangChain4j](https://github.com/langchain4j/langchain4j)**
-Java-based framework inspired by [LangChain](https://github.com/langchain-ai/langchain), designed to simplify the integration of LLMs (Large Language Models) into applications. It offers abstractions and annotations for building intelligent agents and chatbots. Note that LangChain4j is not officially maintained by the LangChain team, despite the similar name.
-
-**[Quarkus](https://quarkus.io/)**
-A Kubernetes-native Java framework designed to optimize Java applications for containers and the cloud. In this tutorial we will use the [quarkus-langchain4j](https://github.com/quarkiverse/quarkus-langchain4j/) extension.
-
-**[AI Endpoints](https://endpoints.ai.cloud.ovh.net/)**
-A serverless platform by OVHcloud providing easy access to a variety of world-renowned AI models including Mistral, LLaMA, and more. This platform is designed to be simple, secure, and intuitive, with data privacy as a top priority.
+- **Streaming LLM Response**: Instead of waiting for a full response from the model, streaming allows the application to start processing output tokens as they’re generated. This creates a smoother, faster user experience—especially useful for chatbots.
+- **[LangChain4j](https://github.com/langchain4j/langchain4j)**: Java-based framework inspired by [LangChain](https://github.com/langchain-ai/langchain), designed to simplify the integration of LLMs (Large Language Models) into applications. It offers abstractions and annotations for building intelligent agents and chatbots. Note that LangChain4j is not officially maintained by the LangChain team, despite the similar name.
+- **[Quarkus](https://quarkus.io/)**: A Kubernetes-native Java framework designed to optimize Java applications for containers and the cloud. In this tutorial we will use the [quarkus-langchain4j](https://github.com/quarkiverse/quarkus-langchain4j/) extension.
+- **[AI Endpoints](https://endpoints.ai.cloud.ovh.net/)**: A serverless platform by OVHcloud providing easy access to a variety of world-renowned AI models including Mistral, LLaMA, and more. This platform is designed to be simple, secure, and intuitive, with data privacy as a top priority.
 
 ## Requirements
 
@@ -60,7 +53,7 @@ _OVH_AI_ENDPOINTS_MODEL_URL=https://mistral-7b-instruct-v0-3.endpoints.kepler.ai
 
 **Make sure to replace the token value (`OVH_AI_ENDPOINTS_ACCESS_TOKEN`) by yours.** If you do not have one yet, follow the instructions in the [AI Endpoints - Getting Started](/pages/public_cloud/ai_machine_learning/endpoints_guide_01_getting_started) guide.
 
-You will also have to set two other environements variables, related to the model you want to use. You can find these model-specific values in the `documentation` tab of each model. For example, if you want to add the `Mistral-7B-Instruct-v0.3` model, the expected environement variables will be:
+You will also have to set two other environments variables, related to the model you want to use. You can find these model-specific values in the `documentation` tab of each model. For example, if you want to add the `Mistral-7B-Instruct-v0.3` model, the expected environment variables will be:
 
 - `OVH_AI_ENDPOINTS_MODEL_NAME`: Mistral-7B-Instruct-v0.3
 - `OVH_AI_ENDPOINTS_MODEL_URL`: https://mistral-7b-instruct-v0-3.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1
@@ -76,7 +69,7 @@ python-dotenv==1.0.1
 
 Then, launch the installation of these dependencies:
 
-```
+```console
 pip install -r requirements.txt
 ```
 
@@ -139,7 +132,7 @@ python3 chat-bot.py --question "What is OVHcloud?"
 
 Which will give you an output similar to: 
 
-```
+```console
 🤖: OVHcloud is a global cloud computing company that offers a variety of services such as virtual private servers, dedicated servers, 
 storage solutions, and other web services. 
 It was founded in France and has since expanded to become a leading provider of cloud infrastructure, with data centers located around the 

pages/public_cloud/ai_machine_learning/endpoints_tuto_06_chatbot_langchain_javascript/guide.en-gb.md

@@ -1,7 +1,7 @@
 ---
 title: AI Endpoints - Build a JavaScript Chatbot with LangChain
 excerpt: Learn how to build a chatbot using JavaScript, LangChain, and AI Endpoints
-updated: 2025-04-15
+updated: 2025-04-18
 ---
 
 > [!primary]
@@ -15,11 +15,11 @@ updated: 2025-04-15
 
 **[LangChain](https://github.com/langchain-ai/langchain)** is a leading framework for building applications powered by Large Language Models (LLMs). While it's well-known for Python, LangChain also provides support for JavaScript/TypeScript—ideal for frontend and fullstack applications.
 
-In this guide, we'll show you how to build a simple command-line chatbot using LangChain and OVHcloud **[AI Endpoints](https://endpoints.ai.cloud.ovh.net/)**, first in **blocking mode**, and then with **streaming** for real-time responses.
+In this tutorial, we'll show you how to build a simple command-line chatbot using LangChain and OVHcloud **[AI Endpoints](https://endpoints.ai.cloud.ovh.net/)**, first in **blocking mode**, and then with **streaming** for real-time responses.
 
 ## Objective
 
-This guide demonstrates how to:
+This tutorial demonstrates how to:
 
 - Set up a Node.js chatbot using LangChain JS
 - Connect to OVHcloud AI Endpoints to access LLMs
@@ -45,7 +45,7 @@ _OVH_AI_ENDPOINTS_MODEL_URL=https://mistral-7b-instruct-v0-3.endpoints.kepler.ai
 
 **Make sure to replace the token value (`OVH_AI_ENDPOINTS_ACCESS_TOKEN`) by yours.** If you do not have one yet, follow the instructions in the [AI Endpoints - Getting Started](/pages/public_cloud/ai_machine_learning/endpoints_guide_01_getting_started) guide.
 
-You will also have to set two other environements variables, related to the model you want to use. You can find these model-specific values in the `documentation` tab of each model. For example, if you want to add the `Mistral-7B-Instruct-v0.3` model, the expected environement variables will be:
+You will also have to set two other environments variables, related to the model you want to use. You can find these model-specific values in the `documentation` tab of each model. For example, if you want to add the `Mistral-7B-Instruct-v0.3` model, the expected environment variables will be:
 
 - `OVH_AI_ENDPOINTS_MODEL_NAME`: Mistral-7B-Instruct-v0.3
 - `OVH_AI_ENDPOINTS_MODEL_URL`: https://mistral-7b-instruct-v0-3.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1
@@ -138,11 +138,9 @@ You can test your new assistant with the following command:
 node chatbot.js --question "What is OVHcloud?"
 ```
 
+Which will give you an output similar to:
 
-
-Which will give you an output similar to: 
-
-```
+```console
 OVHcloud is a global cloud computing company that offers a wide range of services including web hosting, 
 virtual private servers, cloud storage, and dedicated servers. 
 It was founded in 1999 and is headquartered in Roubaix, France. 
@@ -154,7 +152,7 @@ OVHcloud is known for its high-performance, scalable, and secure cloud infrastru
 
 ### Enable streaming mode
 
-As usual, you certainly want a real chatbot with conversational style. To do that let’s add streaming feature with the following code:
+As usual, you certainly want a real chatbot with conversational style. To do that, let’s add a streaming feature with the following code:
 
 ```js
 import { ChatMistralAI } from "@langchain/mistralai";