diff --git a/frontend/src/data/sample.js b/frontend/src/data/sample.js index ee92620..fc542fc 100644 --- a/frontend/src/data/sample.js +++ b/frontend/src/data/sample.js @@ -127,8 +127,8 @@ export function fallbackServices() { category: "ai", summary: "LLM chat (public beta)", link: "/ai", - host: "bstein.dev/ai", - status: "beta", + host: "chat.ai.bstein.dev", + status: "live", }, { name: "AI Image", diff --git a/frontend/src/views/AiView.vue b/frontend/src/views/AiView.vue index 83da6f0..21d4a9a 100644 --- a/frontend/src/views/AiView.vue +++ b/frontend/src/views/AiView.vue @@ -5,8 +5,8 @@

Atlas AI

Chat

- Lightweight LLM running on titan-24 (RTX 3080, 8GB). Anyone can chat without auth. Responses are single-turn per - send; the client sends the on-page history with every request. + Lightweight LLM running on titan-24 (RTX 3080, 8GB). Anyone can chat without auth. The client streams responses and + shows round-trip latency for each turn.

Online
@@ -21,7 +21,7 @@
Endpoint - /api/ai/chat + {{ apiHost }}
@@ -29,10 +29,11 @@
-
+
{{ msg.role === 'assistant' ? 'ai' : 'you' }}

{{ msg.content }}

-
{{ msg.latency_ms }} ms
+
streaming…
+
{{ msg.latency_ms }} ms
@@ -72,6 +73,10 @@