added chat streaming

packages/orchestration-service/src/services/inference.js

@@ -13,6 +13,17 @@ async function complete(prompt, options ={}) {
     return res.json();
 }
 
+async function completeStream(prompt, options={}) {
+    const res = await fetch(`${BASE_URL}/complete/stream`, {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json'},
+        body: JSON.stringify({prompt, ...options}),
+    })
+    if (!res.ok) throw new Error(`Inference service error: ${res.status}`);
+    return res;
+}
+
 module.exports = {
-    complete
+    complete,
+    completeStream
 }