Add LLM endpoints, web frontend, and rate limiting config

- Added OpenAI-compatible LLM endpoints to API backend - Introduced web
frontend with Jinja2 templates and static assets - Implemented API proxy
routes in web service - Added sample db.json data for items, users,
orders, reviews, categories, llm_requests - Updated ADC and Helm configs
for separate AI and standard rate limiting - Upgraded FastAPI, Uvicorn,
and added httpx, Jinja2, python-multipart dependencies - Added API
configuration modal and client-side JS for web app

web/templates/llm.html

@@ -0,0 +1,135 @@
+{% extends "base.html" %} {% block title %}LLM Chat - API Demo{% endblock %} {%
+block content %}
+<div class="page-header">
+    <h1>🤖 AI Chat - Videogame Expert</h1>
+    <p>Chat with our AI assistant (Rate limited: 100 tokens/60s)</p>
+</div>
+
+<div class="chat-container">
+    <div class="chat-messages" id="chat-messages">
+        <div class="system-message">
+            Welcome! Ask me anything about videogames. I'm powered by the
+            videogame-expert model.
+        </div>
+    </div>
+
+    <div class="chat-input-container">
+        <textarea
+            id="chat-input"
+            placeholder="Type your message here..."
+            rows="3"
+        ></textarea>
+        <button id="send-btn" class="btn btn-primary" onclick="sendMessage()">
+            Send Message
+        </button>
+    </div>
+
+    <div class="chat-info">
+        <small>
+            Model: <strong>videogame-expert</strong> | Status:
+            <span id="status">Ready</span> | Rate Limit:
+            <strong>100 tokens/60s</strong>
+        </small>
+    </div>
+</div>
+{% endblock %} {% block scripts %}
+<script src="https://cdn.jsdelivr.net/npm/marked@11.1.1/marked.min.js"></script>
+<script>
+    const API_BASE = "/api";
+    let isProcessing = false;
+
+    function addMessage(content, isUser = false) {
+        const messagesDiv = document.getElementById("chat-messages");
+        const messageDiv = document.createElement("div");
+        messageDiv.className = isUser ? "user-message" : "assistant-message";
+
+        if (isUser) {
+            messageDiv.textContent = content;
+        } else {
+            // Parse markdown for assistant messages
+            messageDiv.innerHTML = marked.parse(content);
+        }
+
+        messagesDiv.appendChild(messageDiv);
+        messagesDiv.scrollTop = messagesDiv.scrollHeight;
+    }
+
+    function setStatus(text, isError = false) {
+        const statusSpan = document.getElementById("status");
+        statusSpan.textContent = text;
+        statusSpan.style.color = isError ? "#f44336" : "#4CAF50";
+    }
+
+    async function sendMessage() {
+        if (isProcessing) return;
+
+        const input = document.getElementById("chat-input");
+        const prompt = input.value.trim();
+
+        if (!prompt) {
+            alert("Please enter a message");
+            return;
+        }
+
+        // Add user message
+        addMessage(prompt, true);
+        input.value = "";
+
+        // Set processing state
+        isProcessing = true;
+        document.getElementById("send-btn").disabled = true;
+        setStatus("Processing...");
+
+        try {
+            const response = await fetch(`${API_BASE}/llm/chat`, {
+                method: "POST",
+                headers: {
+                    "Content-Type": "application/json",
+                },
+                body: JSON.stringify({
+                    prompt: prompt,
+                    max_tokens: 150,
+                    temperature: 0.7,
+                    model: "videogame-expert",
+                }),
+            });
+
+            if (!response.ok) {
+                const error = await response.json();
+                throw new Error(error.detail || "API request failed");
+            }
+
+            const data = await response.json();
+
+            // Add assistant response
+            addMessage(data.response, false);
+
+            // Show tokens used
+            const tokensInfo = `Tokens used: ${data.tokens_used}`;
+            const infoDiv = document.createElement("div");
+            infoDiv.className = "system-message";
+            infoDiv.textContent = tokensInfo;
+            document.getElementById("chat-messages").appendChild(infoDiv);
+
+            setStatus("Ready");
+        } catch (error) {
+            console.error("Error:", error);
+            addMessage(`Error: ${error.message}`, false);
+            setStatus("Error", true);
+        } finally {
+            isProcessing = false;
+            document.getElementById("send-btn").disabled = false;
+        }
+    }
+
+    // Allow Enter to send (Shift+Enter for newline)
+    document
+        .getElementById("chat-input")
+        .addEventListener("keydown", function (e) {
+            if (e.key === "Enter" && !e.shiftKey) {
+                e.preventDefault();
+                sendMessage();
+            }
+        });
+</script>
+{% endblock %}