Upload pages/api/chat.js with huggingface_hub

pages/api/chat.js

@@ -0,0 +1,64 @@
+import { OpenAI } from 'openai'
+
+export default async function handler(req, res) {
+  if (req.method !== 'POST') {
+    return res.status(405).json({ error: 'Method not allowed' })
+  }
+
+  try {
+    const { messages, stream = true } = req.body
+
+    if (!process.env.HF_TOKEN) {
+      return res.status(500).json({ error: 'HF_TOKEN environment variable is not set' })
+    }
+
+    const client = new OpenAI({
+      baseURL: "https://router.huggingface.co/v1",
+      apiKey: process.env.HF_TOKEN,
+      defaultHeaders: {
+        "X-HF-Bill-To": "huggingface" 
+      }
+    })
+
+    if (stream) {
+      // Set headers for streaming response
+      res.setHeader('Content-Type', 'text/plain')
+      res.setHeader('Cache-Control', 'no-cache')
+      res.setHeader('Connection', 'keep-alive')
+
+      const stream = await client.chat.completions.create({
+        model: "Qwen/Qwen3-VL-30B-A3B-Instruct:novita",
+        messages,
+        stream: true,
+      })
+
+      try {
+        for await (const chunk of stream) {
+          const delta = chunk.choices?.[0]?.delta?.content
+          if (delta) {
+            res.write(`data: ${JSON.stringify(chunk)}\n\n`)
+          }
+        }
+        res.write(`data: [DONE]\n\n`)
+      } catch (error) {
+        console.error('Streaming error:', error)
+        res.write(`data: ${JSON.stringify({ error: error.message })}\n\n`)
+      } finally {
+        res.end()
+      }
+    } else {
+      const completion = await client.chat.completions.create({
+        model: "Qwen/Qwen3-VL-30B-A3B-Instruct:novita",
+        messages,
+        stream: false,
+      })
+
+      res.status(200).json(completion)
+    }
+  } catch (error) {
+    console.error('API Error:', error)
+    res.status(500).json({ 
+      error: error.message || 'Internal server error' 
+    })
+  }
+}