Fix typo (#16)

* Update README.md

* Update README.md

* change LangChain4J to LangChain4j

* typo

* Update README.md

---------

Co-authored-by: Bruno Borges <[email protected]>

Author: SandraAhlgrimm

README.md

@@ -37,7 +37,7 @@ description: A Java sample app that chats with your data using OpenAI.
 
 </div>
 
-This sample shows how to build an AI chat experience with Retrieval-Augmented Generation (RAG) using LangChain4J and OpenAI language models. The application is hosted on [Azure Static Web Apps](https://learn.microsoft.com/azure/static-web-apps/overview) and [Azure Container Apps](https://learn.microsoft.com/azure/container-apps/overview), with [Qdrant](https://qdrant.tech/) as the vector database. You can use it as a starting point for building more complex AI applications.
+This sample shows how to build an AI chat experience with Retrieval-Augmented Generation (RAG) using LangChain4j and OpenAI language models. The application is hosted on [Azure Static Web Apps](https://learn.microsoft.com/azure/static-web-apps/overview) and [Azure Container Apps](https://learn.microsoft.com/azure/container-apps/overview), with [Qdrant](https://qdrant.tech/) as the vector database. You can use it as a starting point for building more complex AI applications.
 
 > [!IMPORTANT]
 > 👉 **Follow the [full-length workshop](https://aka.ms/ws/openai-rag-quarkus)** to learn how we built this sample and how you can run and deploy it.

docs/sections/06-chat-api.md

@@ -14,7 +14,7 @@ We're going to use [Quarkus' Context And Dependency Injection (CDI) mechanism](h
 - The `ai.azure.openai.rag.workshop.backend.configuration.EmbeddingModelProducer` will be responsible for configuring the embedding model.
 - The `ai.azure.openai.rag.workshop.backend.configuration.EmbeddingStoreProducer` will be responsible for configuring the Qdrant embedding store.
 
-As those producers are configured in separate files, and use the LangChain4J API, they can later be switched easily to use other implementations: this will be useful for example to use a more powerful language or embedding model, or for running tests locally.
+As those producers are configured in separate files, and use the LangChain4j API, they can later be switched easily to use other implementations: this will be useful for example to use a more powerful language or embedding model, or for running tests locally.
 
 Let's start by configuring `ChatLanguageModelAzureOpenAiProducer`, using the Azure OpenAI API.
 
@@ -167,7 +167,7 @@ And let's finish with configuring the `EmbeddingStoreProducer`, using the Qdrant
 
 ### Creating the Chat API
 
-Now that our data has been ingested, and that our services are configured in Quarkus, it's time to interact with our vector database and an LLM using LangChain4J. 
+Now that our data has been ingested, and that our services are configured in Quarkus, it's time to interact with our vector database and an LLM using LangChain4j. 
 
 ![ChatResource and dependencies](./assets/class-diagram-rest.png)