docs: change from ChatGPT word to Chat Application

docs/tutorial/01-introduction.md

@@ -1,14 +1,14 @@
-# Tutorial - Create a Serverless ChatGPT with RAG using LangChain.js and TypeScript
+# Tutorial - Create a Serverless Chat Application with RAG using LangChain.js and TypeScript
 
-Welcome to the tutorial _Create a Serverless ChatGPT with RAG using LangChain.js and TypeScript_.
+Welcome to the tutorial _Create a Serverless Chat Application with RAG using LangChain.js and TypeScript_.
 
-This tutorial will guide you through creating a serverless a ChatGPT and RAG (Retrieval-Augmented Generation) application using **[LangChain.js](https://js.langchain.com/docs/get_started/introduction)**, **[Azure Functions](https://learn.microsoft.com/azure/azure-functions/)**, **[Azure Cosmos DB for MongoDB vCore](https://learn.microsoft.com/azure/cosmos-db/mongodb/vcore/)**, **[Azure Blob Storage](https://learn.microsoft.com/azure/storage/blobs/)**, and **[Azure Static Web Apps](https://learn.microsoft.com/azure/static-web-apps/)**.
+This tutorial will guide you through creating a serverless a Chat Application and RAG (Retrieval-Augmented Generation) application using **[LangChain.js](https://js.langchain.com/docs/get_started/introduction)**, **[Azure Functions](https://learn.microsoft.com/azure/azure-functions/)**, **[Azure Cosmos DB for MongoDB vCore](https://learn.microsoft.com/azure/cosmos-db/mongodb/vcore/)**, **[Azure Blob Storage](https://learn.microsoft.com/azure/storage/blobs/)**, and **[Azure Static Web Apps](https://learn.microsoft.com/azure/static-web-apps/)**.
 
 The chatbot will be able to answer questions based on a set of enterprise documents uploaded from a fictional company called _Contoso Real Estate_.
 
 Here's an example of the application in action:
 
-![ChatGPT with RAG](../../docs/images/demo.gif)
+![Chat Application with RAG](../../docs/images/demo.gif)
 
 This tutorial will teach you how to build a serverless application using Azure Functions and LangChain.js.
 
@@ -54,7 +54,7 @@ The code sample includes sample data to make trying the application quick and ea
 
 The architecture of the project is shown in the following diagram:
 
-![ChatGPT with RAG](../../docs/images/architecture.drawio.png)
+![Chat Application with RAG](../../docs/images/architecture.drawio.png)
 
 To understand the architecture of the project, let's break it down into its individual components:
 

docs/tutorial/02-setting-up-azure-functions.md

@@ -1,6 +1,6 @@
 # Setting Up the Serverless Environment using Azure Functions
 
-This section explains how to configure the development environment to create the API for the ChatGPT application. We'll use Azure Functions in its 4.x version and with the programming model version 4.
+This section explains how to configure the development environment to create the API for the Chat Application application. We'll use Azure Functions in its 4.x version and with the programming model version 4.
 
 ## Prerequisites for this section
 
@@ -241,11 +241,11 @@ If that happened, congratulations! The environment has been set up correctly!
 
 ## Next Steps
 
-This tutorial explains how to configure the development environment to create functions for the ChatGPT project using Functions version 4.x and the programming model v4 for Node.js.
+This tutorial explains how to configure the development environment to create functions for the Chat Application project using Functions version 4.x and the programming model v4 for Node.js.
 
 Additionally, we configured the project to run the functions we created. And finally we created the `chat-post`, `documents-post`, and `documents-get` functions for the project.
 
-Before we proceed with developing the functions, it's important to grasp a fundamental concept for those building ChatGPT applications: Retrieval-Augmented Generation (RAG).
+Before we proceed with developing the functions, it's important to grasp a fundamental concept for those building Chat Application applications: Retrieval-Augmented Generation (RAG).
 
 We will talk about RAG in the next section.
 

docs/tutorial/03-understanding-rag.md

@@ -1,6 +1,6 @@
 # Understanding the RAG (Retrieval Augmented Generation) architecture
 
-In this section, we'll understand what the RAG (Retrieval Augmented Generation) architecture is, how it works, and why it's important for integration with ChatGPT.
+In this section, we'll understand what the RAG (Retrieval Augmented Generation) architecture is, how it works, and why it's important for integration with Chat Application.
 
 ## What is RAG (Retrieval Augmented Generation)?
 
@@ -39,11 +39,11 @@ Implement the standard RAG architecture following this flow. It should include:
    - **How it works:** With the most relevant passages retrieved, the generator's task is to produce a final response, synthesizing and expressing this information in natural language.
    - **Mechanisms:** The generator, which is typically a model like GPT, BART, or T5, uses both the query and the relevant documents identified by retriever to create its response. It is important to note that the generator relies on the retriever to identify the relevant documents.
 
-## Why is RAG architecture important for integration with ChatGPT?
+## Why is RAG architecture important for integration with Chat Application?
 
-The RAG architecture is useful for ChatGPT in business contexts. It allows for flexible and efficient integration with various databases, improving the relevance and accuracy of generated responses while customizing the application to meet specific business needs.
+The RAG architecture is useful for Chat Application in business contexts. It allows for flexible and efficient integration with various databases, improving the relevance and accuracy of generated responses while customizing the application to meet specific business needs.
 
-Here are some advantages of integrating RAG architecture with ChatGPT:
+Here are some advantages of integrating RAG architecture with Chat Application:
 
 ### Adapting the RAG Architecture to different Enterprise Databases
 
@@ -53,7 +53,7 @@ Examples of data types that can be integrated:
 
 1. **Textual documents:** Internal documents, analysis reports, procedure manuals, and technical documentation. RAG can retrieve relevant information from these documents to answer specific questions that require detailed knowledge contained therein.
 
-2. **Relational Databases:** Structured data such as customer records, financial transactions and inventory records. Although traditionally not the main focus of LLMs, by integrating RAG, ChatGPT can extract and use information from tables and databases to enrich its answers or perform specific analyses.
+2. **Relational Databases:** Structured data such as customer records, financial transactions and inventory records. Although traditionally not the main focus of LLMs, by integrating RAG, Chat Application can extract and use information from tables and databases to enrich its answers or perform specific analyses.
 
 3. **Social media data and customer feedback:** Comments and reviews that can be used to better understand market trends, consumer sentiment, and to answer questions related to customer service.
 
@@ -77,8 +77,8 @@ RAG has significant implications in many fields:
 
 ## Next Steps
 
-The RAG architecture is a powerful tool for improving the accuracy and relevance of ChatGPT's responses. It makes ChatGPT a more effective solution for business scenarios and other contexts where access to specific information is essential.
+The RAG architecture is a powerful tool for improving the accuracy and relevance of Chat Application's responses. It makes Chat Application a more effective solution for business scenarios and other contexts where access to specific information is essential.
 
-Now that we have a clear understanding of the RAG architecture, we can begin developing the functions for integration with ChatGPT on the FrontEnd side. In the next section, we will start developing the `chat-post` function or the `chat` API for integration with ChatGPT.
+Now that we have a clear understanding of the RAG architecture, we can begin developing the functions for integration with Chat Application on the FrontEnd side. In the next section, we will start developing the `chat-post` function or the `chat` API for integration with Chat Application.
 
 **[⬅️ Back: Setting Up the Serverless Environment using Azure Functions](02-setting-up-azure-functions.md)** | **[Next: Developing the `chat` API ➡️ ](./04-preparing-understanding-language-models.md)**

docs/tutorial/04-preparing-understanding-language-models.md

@@ -62,7 +62,7 @@ The templates used to deploy the resources can be found in the `infra` folder, w
 
 You will notive that an `.env` file has been created in the `.azure` folder. Copy the contents of the `.env` file to your local machine, keep it a safe place, and return to the `starter` branch and create an `.env` file inside the `api` folder with the same content. Why? Because we will neede these credentials to use throughout the tutorial.
 
-> **Note:** if you want to simply browse the project code and see it in action, go to the `main` branch where the entire application is ready and follow the steps described in the article [Build a serverless ChatGPT with RAG using LangChain.js](https://techcommunity.microsoft.com/t5/apps-on-azure-blog/build-a-serverless-chatgpt-with-rag-using-langchain-js/ba-p/4111041), written by **[Yohan Lasorsa](https://twitter.com/sinedied)**.
+> **Note:** if you want to simply browse the project code and see it in action, go to the `main` branch where the entire application is ready and follow the steps described in the article [Build a serverless Chat Application with RAG using LangChain.js](https://techcommunity.microsoft.com/t5/apps-on-azure-blog/build-a-serverless-chatgpt-with-rag-using-langchain-js/ba-p/4111041), written by **[Yohan Lasorsa](https://twitter.com/sinedied)**.
 
 ## Installing Ollama and Local Models
 
@@ -95,7 +95,7 @@ After downloading the models, you can verify the proper functioning of the Ollam
 ollama run mistral
 ```
 
-An invitation will be sent to your terminal, allowing you to directly communicate with the AI model in a chat-like format similar to ChatGPT.
+An invitation will be sent to your terminal, allowing you to directly communicate with the AI model in a chat-like format similar to Chat Application.
 
 ![Ollama Mistral](./images/ollama-mistra-cli.png)