Spaces:

thecollabagepatch
/

magenta-retry

Running

App Files Files Community

thecollabagepatch commited on Sep 11

Commit

4a4198e

1 Parent(s): 7ac8db1

root endpoint updated for websockets route

Browse files

Files changed (1) hide show

app.py +83 -30

app.py CHANGED Viewed

@@ -973,36 +973,8 @@ async def log_requests(request: Request, call_next):
     print(f"📤 {response.status_code} {request.url.path} [rid={rid}]")
     return response
-@app.get("/ping")
-def ping():
-    return {"ok": True}
-@app.get("/", response_class=Response)
-def read_root():
-    """Root endpoint that explains what this API does"""
-    html_content = """
-    <!DOCTYPE html>
-    <html>
-    <head><title>MagentaRT Research API</title></head>
-    <body style="font-family: Arial; max-width: 800px; margin: 50px auto; padding: 20px;">
-        <h1>🎵 MagentaRT Research API</h1>
-        <p><strong>Purpose:</strong> AI music generation for iOS app research using Google's MagentaRT</p>
-        <h2>Available Endpoints:</h2>
-        <ul>
-            <li><code>POST /generate</code> - Generate 4-8 bars of music</li>
-            <li><code>POST /jam/start</code> - Start continuous jamming</li>
-            <li><code>GET /jam/next</code> - Get next chunk</li>
-            <li><code>POST /jam/consume</code> - confirm a chunk as consumed</li>
-            <li><code>POST /jam/stop</code> - End session</li>
-            <li><code>GET /docs</code> - API documentation</li>
-        </ul>
-        <p><strong>Research Only:</strong> Experimental implementation for iOS app development.</p>
-        <p><strong>Licensing:</strong> Uses MagentaRT (Apache 2.0 + CC-BY 4.0). Users responsible for outputs.</p>
-        <p>Visit <a href="/docs">/docs</a> for detailed API documentation.</p>
-    </body>
-    </html>
-    """
-    return Response(content=html_content, media_type="text/html")
 # ----------------------------
@@ -1320,4 +1292,85 @@ async def ws_jam(websocket: WebSocket):
             if websocket.client_state != WebSocketState.DISCONNECTED:
                 await websocket.close()
         except Exception:
-            pass

     print(f"📤 {response.status_code} {request.url.path} [rid={rid}]")
     return response
 # ----------------------------
             if websocket.client_state != WebSocketState.DISCONNECTED:
                 await websocket.close()
         except Exception:
+            pass
+@app.get("/ping")
+def ping():
+    return {"ok": True}
+@app.get("/", response_class=Response)
+def read_root():
+    """Root endpoint that explains what this API does"""
+    html_content = """
+    <!DOCTYPE html>
+    <html>
+    <head>
+      <meta charset="utf-8">
+      <title>MagentaRT Research API</title>
+      <style>
+        body { font-family: Arial, sans-serif; max-width: 860px; margin: 48px auto; padding: 0 20px; color:#111; }
+        code, pre { background:#f6f8fa; border:1px solid #eaecef; border-radius:6px; padding:2px 6px; }
+        pre { padding:12px; overflow:auto; }
+        .muted { color:#555; }
+        ul { line-height: 1.8; }
+      </style>
+    </head>
+    <body>
+      <h1>🎵 MagentaRT Research API</h1>
+      <p class="muted"><strong>Purpose:</strong> AI music generation for iOS/web app research using Google's MagentaRT.</p>
+      <h2>Available Endpoints</h2>
+      <ul>
+        <li><code>POST /generate</code> – Generate 4–8 bars of music (HTTP, bar-aligned)</li>
+        <li><code>POST /jam/start</code> – Start continuous jamming (HTTP)</li>
+        <li><code>GET /jam/next</code> – Get next chunk (HTTP)</li>
+        <li><code>POST /jam/consume</code> – Confirm a chunk as consumed (HTTP)</li>
+        <li><code>POST /jam/stop</code> – End session (HTTP)</li>
+        <li><code>WEBSOCKET /ws/jam</code> – Realtime streaming (<code>mode="rt"</code>)</li>
+        <li><code>GET /docs</code> – API documentation (Gradio)</li>
+      </ul>
+      <h2>WebSocket Quick Start (rt mode)</h2>
+      <p>Connect to <code>wss://&lt;your-space&gt;/ws/jam</code> and send:</p>
+      <pre>{
+  "type": "start",
+  "mode": "rt",
+  "binary_audio": false,
+  "params": {
+    "styles": "warmup",
+    "temperature": 1.1,
+    "topk": 40,
+    "guidance_weight": 1.1,
+    "pace": "realtime",          // or "asap" to bootstrap quickly
+    "max_decode_frames": 50      // default ~2.0s; try 36–45 on smaller GPUs
+  }
+}</pre>
+      <p>Update parameters live:</p>
+      <pre>{
+  "type": "update",
+  "styles": "jazz, hiphop",
+  "style_weights": "1.0,0.8",
+  "temperature": 1.2,
+  "topk": 64,
+  "guidance_weight": 1.0,
+  "pace": "realtime",
+  "max_decode_frames": 40
+}</pre>
+      <p>Stop:</p>
+      <pre>{"type":"stop"}</pre>
+      <h2>Notes</h2>
+      <ul>
+        <li>Audio: 48 kHz stereo, ~2.0 s chunks by default with ~40 ms crossfade.</li>
+        <li>L40S 48GB: faster than realtime → prefer <code>pace: "realtime"</code>.</li>
+        <li>L4 24GB: slightly under realtime even with pre-roll and tuning.</li>
+        <li>For sustained realtime, target ~40 GB VRAM per active stream (e.g., A100 40GB or ≈35–40 GB MIG slice).</li>
+      </ul>
+      <p class="muted"><strong>Licensing:</strong> Uses MagentaRT (Apache 2.0 + CC-BY 4.0). Users are responsible for outputs.</p>
+      <p>See <a href="/docs">/docs</a> for full API details and client examples.</p>
+    </body>
+    </html>
+    """
+    return Response(content=html_content, media_type="text/html")