implemented inference service

packages/inference-service/src/routes/inference.js

@@ -0,0 +1,48 @@
+const { Router } = require('express');
+const { complete, completeStream } = require('../infer');
+
+const router = Router();
+
+// Standard completion endpoint - returns full response when done
+router.post('/complete', async (req, res) => {
+    const { prompt, model, temperature, maxTokens } = req.body;
+
+    if (!prompt) {
+        return res.status(400).json({ error: 'prompt is required'});
+    }
+
+    try {
+        const result = await complete (prompt, {model, temperature, maxTokens});
+        res.json(result);
+    } catch (error) {
+        console.error('[Inference] Completion error:', error.message);
+        res.status(500).json({ error: error.message });
+    }
+});
+
+// Streaming completion endpoint - sends partial responses as they arrive
+router.post('/complete/stream', async (req, res) => {
+    const { prompt, model, temperature } = req.body;
+
+    if (!prompt) {
+        return res.status(400).json({error: 'prompt is required'});
+    }
+
+    res.setHeader('Content-Type', 'text/event-stream');
+    res.setHeader('Cache-Control', 'no-cache');
+    res.setHeader('Connection', 'keep-alive');
+
+    try {
+        for await (const chunk of completeStream(prompt, {model, temperature})) {
+            res.write(`data: ${JSON.stringify(chunk)}\n\n`);
+        }
+        res.write('data: [DONE]\n\n');
+    } catch (error) {
+        console.error('[Inference] Streaming error:', error.message);
+        res.write(`data: ${JSON.stringify({ error: error.message })}\n\n`);
+    } finally {
+        res.end();
+    }
+});
+
+module.exports = router;