ESC
On this page
Features > Replicate Integration
Deploying to Replicate is straightforward, although it may require a bit more effort compared to Runpod.
Check out the AI Services tutorial to understand how to deploy your custom AI models on Replicate.
Once your model is deployed, retrieve its version, input type, and adjust: api/ai/replicate.ts to enable making requests to your model within your NuxtStarter project.
As the Replicate API is asynchronous, meaning the response isn't immediate, we must wait and retry if necessary. Don't worry,We handle all the waiting/retrying logic for you.
api/ai/runpod.ts
1
2 let data = JSON.stringify({
3 // MODELS INPUT AS A JSON OBJECT.
4 version: "#YOUR_DEPLOYED_MODEL_VERSION", // YOUR DEPLOYED MODEL VERSION,
5 input: {
6 image: base64,// Modify the input type to match the request body of your API, exact types depend on your model
7 prompt: requestBody.prompt,
8 seed: requestBody.seed,
9 style: requestBody.style,
10 },
11 });
12
13 let config = {
14 method: "post",
15 maxBodyLength: Infinity,
16 url: "https://api.replicate.com/v1/predictions",
17 headers: {
18 Authorization: `Bearer ${process.env.REPLICATE_API_TOKEN}`, // place in your API key here or use environment variables
19 "Content-Type": "application/json",
20 },
21 data: data,
22 };
23
24 // ...
25 // Since replicate api is async, we need to wait and retry if necessary.
26 try {
27 axiosRetry(axios, {
28 retryDelay: (retryCount) => {
29 return retryCount * 1;
30 },
31 retries: 15,
32 });
33
34 let result = await axios.request(config);
35 if (result.status === 200) {
36 if (result.data.status === "failed") {
37 throw createError({
38 statusCode: 400,
39 statusMessage: result.data
40 })
41 }
42
43 let waitCount = 0;
44 let predId = result.data.id;
45 while (
46 result.data.status == "starting" ||
47 result.data.status == "processing"
48 ) {
49 if (waitCount > 20) {
50 // at least 20 seconds
51 throw createError({
52 statusCode: 500,
53 statusMessage: result.data
54 }); // max wait, timeout
55 }
56 await new Promise((resolve) => setTimeout(resolve, 1000)); // wait 1 second
57 result = await axios.get(`https://api.replicate.com/v1/predictions/${predId}`, {
58 {
59 headers: {
60 Authorization: `Bearer ${process.env.REPLICATE_API_TOKEN}`,
61 "Content-Type": "application/json",
62 },
63 }
64 );
65 waitCount++;
66 if (result.data.status === "failed") {
67 throw createError({
68 statusCode: 500,
69 statusMessage: result.data
70 });
71 }
72 if (result.data.status === "succeeded") {
73 return result.data;
74 }
75 }
76 } else {
77 return result.data;
78 }
79 } catch (error) {
80 throw createError({
81 statusCode: 500,
82 statusMessage: error.response.data
83 });
84 }
85}
86
87
88
89 Input Type
The input schema varies depending on the model you're using. To view the available inputs, click the "API" tab on the model you're running on Replicate.Adjust the input type to match the request body of your API.