# From LLM to RAG: How Azure OpenAI Powers Smarter Maritime ERP at mBluewave

### Introduction

Large Language Models (LLMs) like GPT are changing how we interact with systems. They can generate human-like answers, write summaries, and even reason across documents. But there is a catch: LLMs don’t know your company’s data, asking any question specific to that data will result in convincing but **wrong** answer. A serious risk in industries like banking, finance and maritime, where compliance and safety are non-negotiable.

That is where **Retrieval-Augmented Generation (RAG)** comes in: you ground the LLM with your own data. At **mBluewave**, our AI-first Maritime ERP platform, we built a RAG-powered assistant using **Azure OpenAI + Azure AI Search** to make vessel manuals and procedures accessible using simple human-like interaction.

### Why RAG?

Ask GPT: *“How do I reset the fire suppression system?”* It might give you a plausible but incorrect procedure. With RAG, the answer is pulled directly from the vessel’s own safety manual, ensuring compliance and accuracy.

**Architecture at a glance:**

* Manuals and safety documents in **Azure Blob Storage**
    
* Chunked, embedded, and indexed with **Azure AI Search**
    
* Retrieval with metadata filters (by vessel, department, doc type)
    
* **Azure OpenAI** generates grounded answers with citations
    

![](https://cdn.hashnode.com/res/hashnode/image/upload/v1756627528124/3624654c-d25c-480a-a9b7-be3399b3be8f.png align="center")

### [mBluewave RAG Exa](https://github.com/geekabyte-au/azure-search-openai-demo?utm_source=chatgpt.com)mple

**User query:**

> “What are the steps to reset the fire suppression system on Vessel A?”

**Workflow:**

1. Search service retrieves the most relevant passages from Vessel A’s manuals.
    
2. Context is injected into the GPT prompt.
    
3. Model answers *only from sources*, returning step-by-step instructions.
    
4. Citations show exactly which manual and page were used.
    

**Result:** A precise, compliant answer tailored to that vessel — not a hallucination.

![Enterprise GTP using Azure Open AI and Azure AI Search](https://cdn.hashnode.com/res/hashnode/image/upload/v1756622836512/72533056-3813-46db-8bdc-fe3b5668cfa0.png align="center")

(Not an actual example but similar to ours, copied from an open-source GitHub repository)

### Sample Code (C# / [ASP.NET](http://ASP.NET) Minimal API)

```csharp
// Ask endpoint: retrieve, ground, and answer
app.MapPost("/ask", async (AskRequest req, SearchClient search, OpenAIClient openai) =>
{
    // 1) Vector search with vessel filter
    var options = new SearchOptions { Size = 5 };
    options.Filter = $"vessel eq '{req.Vessel}'";
    options.Select.Add("chunkText");
    options.Select.Add("source");

    var results = await search.SearchAsync<SearchDocument>("", options);
    var top = results.Value.GetResults().Select(r => (string)r.Document["chunkText"]).ToList();

    // 2) Build grounded prompt
    var sys = "Answer ONLY from provided sources. If unknown, say so.";
    var context = string.Join("\n\n", top);
    var user = $"{req.Question}\n\nSources:\n{context}";

    var chat = new ChatCompletionsOptions
    {
        DeploymentName = "gpt-4.1-mini",
        Temperature = 0,
        Messages =
        {
            new ChatRequestSystemMessage(sys),
            new ChatRequestUserMessage(user)
        }
    };

    var completion = await openai.GetChatCompletionsAsync(chat);
    return Results.Ok(completion.Value.Choices[0].Message.Content[0].Text);
});
```

### Handling Wrong Answers

No AI system is perfect. Besides putting a disclaimer that *AI can make mistakes,* the way we are handling these scenarios are:

* **Guardrails in design** if the answer isn’t in the docs, the AI says *“I don’t know, please check the manual”*.
    
* **Citations** every answer points back to the source, building user trust.
    
* **Feedback loop** crew can flag answers, helping us refine and retrain.
    

### Keeping Costs in Check

It is not cheap to keep this running but cost are manageable if right practices are followed:

* **Use smaller models where possible** (e.g., GPT-4.1-mini instead of full GPT-4.1 for everyday queries).
    
* **Embed once, reuse often** embeddings are only re-generated when documents change.
    
* **Chunk smartly** splitting docs into ~700–900 token sections balances accuracy and token usage.
    
* **Cache common queries** frequent lookups (e.g., “When is next inspection due?”) can be cached for near-zero cost.
    
* **Monitor usage** track tokens, queries per vessel, and adjust.
    

---

### Future Directions

* **Multi-modal RAG** combining text with diagrams, checklists, and images.
    
* **Offline/on-board sync** ensuring crews have access even without internet.