feat: deploy Kalpana RIF O(1) Studio with Needle-in-a-Haystack benchmarks, layer architecture, and Swagger API

index.html

@@ -508,18 +508,32 @@ print(cache.layers[0].key_rif.re_state.shape)
         </div>
       </section>
 
-      <!-- ============================================================ -->
+            <!-- ============================================================ -->
       <!-- TAB 4: SWAGGER / OPENAPI DOCUMENTATION -->
       <!-- ============================================================ -->
       <section class="tab-pane" id="tab-swagger">
         <div class="pane-inner">
-          <div class="section-header">
-            <h2>🔌 Developer OpenAPI / Swagger API Reference</h2>
-            <p>OpenAI-compatible inference and telemetry endpoints for integrating Kalpana RIF into cloud applications.</p>
+          <div class="section-header" style="display: flex; justify-content: space-between; align-items: center; flex-wrap: wrap; gap: 1rem;">
+            <div>
+              <h2>🔌 Developer OpenAPI / Swagger API Reference</h2>
+              <p>Standard OpenAI-compatible inference and telemetry endpoints powered by ZeroGPU (NVIDIA A100).</p>
+            </div>
+            <a href="https://madurox-kalpana-api-cpu.hf.space/docs" target="_blank" class="btn-primary" style="text-decoration: none; width: auto; padding: 0.6rem 1.2rem; display: inline-flex; align-items: center; gap: 0.5rem;">
+              <span>📖 Open Full Swagger UI (/docs) ↗️</span>
+            </a>
           </div>
 
-          <!-- Swagger Endpoint 1 -->
-          <div class="swagger-endpoint">
+          <!-- Base URL Banner -->
+          <div style="background: rgba(0, 240, 255, 0.05); border: 1px solid var(--border-cyan); border-radius: 8px; padding: 0.8rem 1.2rem; margin-bottom: 1.5rem; display: flex; justify-content: space-between; align-items: center;">
+            <div>
+              <span style="color: var(--text-muted); font-size: 0.8rem;">HOSTED ZERO-GPU ENDPOINT:</span>
+              <span style="font-family: var(--font-mono); font-weight: 700; color: var(--cyan); margin-left: 0.5rem;">https://madurox-kalpana-api-cpu.hf.space</span>
+            </div>
+            <span class="status-tag tag-pass">ONLINE · ZERO-GPU (A100)</span>
+          </div>
+
+          <!-- Swagger Endpoint 1: Chat Completions -->
+          <div class="swagger-endpoint open">
             <div class="endpoint-header" onclick="toggleSwagger(this)">
               <span class="http-method method-post">POST</span>
               <span class="endpoint-path">/v1/chat/completions</span>
@@ -528,24 +542,25 @@ print(cache.layers[0].key_rif.re_state.shape)
             </div>
             <div class="endpoint-body">
               <p style="font-size: 0.85rem; color: var(--text-muted); margin-bottom: 1rem;">
-                Generates streaming or complete responses using `KalpanaDynamicCache` across all model layers.
+                Standard OpenAI-compatible endpoint. Executes autoregressive generation using <code>KalpanaDynamicCache</code> across all model hidden layers on ZeroGPU.
               </p>
               
               <div class="code-header">Example Request (cURL)</div>
               <pre class="code-block"><code>curl -X POST https://madurox-kalpana-api-cpu.hf.space/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{
-    "model": "Qwen/Qwen2.5-0.5B-Instruct",
-    "messages": [{"role": "user", "content": "Explain O(1) holographic memory"}],
-    "cache_type": "kalpana_dynamic",
-    "bands": 4096,
-    "stream": true
+    "model": "kalpana-qwen2.5-0.5b",
+    "messages": [
+      {"role": "user", "content": "Explain O(1) holographic memory"}
+    ],
+    "max_tokens": 512,
+    "temperature": 0.7
   }'</code></pre>
             </div>
           </div>
 
-          <!-- Swagger Endpoint 2 -->
-          <div class="swagger-endpoint" style="margin-top: 1rem;">
+          <!-- Swagger Endpoint 2: Telemetry -->
+          <div class="swagger-endpoint">
             <div class="endpoint-header" onclick="toggleSwagger(this)">
               <span class="http-method method-get">GET</span>
               <span class="endpoint-path">/api/telemetry</span>
@@ -559,30 +574,71 @@ print(cache.layers[0].key_rif.re_state.shape)
   "active_model": "Qwen/Qwen2.5-0.5B-Instruct",
   "hidden_layers": 24,
   "cache_type": "KalpanaDynamicCache",
-  "kalpana_kv_memory_mb": 12.00,
-  "standard_kv_memory_mb": 64.00,
-  "vram_compression_ratio": "5.3x Reduction",
+  "kalpana_kv_memory_mb": 6.00,
+  "standard_kv_memory_mb": 2637.00,
+  "vram_compression_ratio": "439.5x Reduction",
   "patent_application": "LK/P/1/24089"
 }</code></pre>
             </div>
           </div>
 
-          <!-- Swagger Endpoint 3 -->
-          <div class="swagger-endpoint" style="margin-top: 1rem;">
+          <!-- Swagger Endpoint 3: Knowledge Pack Compiler -->
+          <div class="swagger-endpoint">
             <div class="endpoint-header" onclick="toggleSwagger(this)">
               <span class="http-method method-post">POST</span>
-              <span class="endpoint-path">/api/ingest</span>
-              <span class="endpoint-summary">Ingest text or Knowledge Pack into O(1) holographic state</span>
+              <span class="endpoint-path">/v1/knowledge_packs/compile</span>
+              <span class="endpoint-summary">Compile massive documents (100K-3M tokens) into portable O(1) Knowledge Packs (.kp)</span>
+              <span class="expand-icon">▼</span>
+            </div>
+            <div class="endpoint-body">
+              <div class="code-header">Example Request (cURL)</div>
+              <pre class="code-block"><code>curl -X POST https://madurox-kalpana-api-cpu.hf.space/v1/knowledge_packs/compile \
+  -H "Content-Type: application/json" \
+  -d '{
+    "text": "Paste large document text or manual here...",
+    "bandwidth": 2048
+  }'</code></pre>
+            </div>
+          </div>
+
+          <!-- Swagger Endpoint 4: Models List -->
+          <div class="swagger-endpoint">
+            <div class="endpoint-header" onclick="toggleSwagger(this)">
+              <span class="http-method method-get">GET</span>
+              <span class="endpoint-path">/v1/models</span>
+              <span class="endpoint-summary">List supported local and remote LLM models</span>
               <span class="expand-icon">▼</span>
             </div>
             <div class="endpoint-body">
-              <div class="code-header">Example Request (Python SDK)</div>
-              <pre class="code-block"><code>from kalpana_embed_to_kv import KalpanaDynamicCache
+              <div class="code-header">Example Response (JSON)</div>
+              <pre class="code-block"><code>{
+  "object": "list",
+  "data": [
+    {"id": "kalpana-qwen2.5-0.5b", "object": "model", "owned_by": "kalpana-ai"},
+    {"id": "qwen2.5-72b", "object": "model", "owned_by": "qwen"},
+    {"id": "llama-3.1-8b", "object": "model", "owned_by": "meta"}
+  ]
+}</code></pre>
+            </div>
+          </div>
 
-# Initialize O(1) Cache and ingest context
-cache = KalpanaDynamicCache(num_layers=32, bands=4096)
-cache.ingest_document("Project Chronos secret key is OMEGA-7749.")
-print("Document modulated into O(1) continuous state!")</code></pre>
+          <!-- Swagger Endpoint 5: Health Check -->
+          <div class="swagger-endpoint">
+            <div class="endpoint-header" onclick="toggleSwagger(this)">
+              <span class="http-method method-get">GET</span>
+              <span class="endpoint-path">/health</span>
+              <span class="endpoint-summary">System health, active packs count, and hardware status</span>
+              <span class="expand-icon">▼</span>
+            </div>
+            <div class="endpoint-body">
+              <div class="code-header">Example Response (JSON)</div>
+              <pre class="code-block"><code>{
+  "status": "ok",
+  "engine": "Kalpanā RIF Engine",
+  "device": "ZeroGPU (NVIDIA A100)",
+  "active_packs": 0,
+  "version": "5.0.0"
+}</code></pre>
             </div>
           </div>
         </div>