Skip to main content

​
Text Completion

Simple text-based chat completion: 
import createRvencClient from "./index";

const client = await createRvencClient({
  apiKey: "your-api-key",
});

const response = await client.chat.completions.create({
  model: "openai/gpt-oss-120b",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Explain quantum computing in simple terms" }
  ],
});

console.log(response.choices[0].message.content);

​
Image Analysis

Analyze and describe images in detail: 
const response = await client.chat.completions.create({
  model: "OpenGVLab/InternVL3-38B",
  messages: [{
    role: "user",
    content: [
      { type: "text", text: "Describe this image in detail" },
      {
        type: "image_url",
        image_url: {
          url: "https://docs.cci.prem.io/docs/images/examples/basic.jpg",
        },
      },
    ],
  }],
});

console.log(response.choices[0].message.content);

​
Document & Chart Intelligence with JSON Output

Extract structured data from charts, invoices, or reports: 
const response = await client.chat.completions.create({
  model: "OpenGVLab/InternVL3-38B",
  messages: [{
    role: "user",
    content: [
      { 
        type: "text", 
        text: `Analyze this sales chart and return the data in JSON format:
        {
          "chart_type": "...",
          "key_findings": ["...", "..."],
          "data_points": [{"label": "...", "value": "..."}],
          "trends": "..."
        }` 
      },
      {
        type: "image_url",
        image_url: {
          url: "https://docs.cci.prem.io/docs/images/examples/sales-chart.png",
        },
      },
    ],
  }],
  response_format: { type: "json_object" },
});

const data = JSON.parse(response.choices[0].message.content || "{}");
console.log(data);

​
Receipt & Invoice Processing

Extract and structure financial information from receipts: 
const response = await client.chat.completions.create({
  model: "OpenGVLab/InternVL3-38B",
  messages: [{
    role: "user",
    content: [
      { 
        type: "text", 
        text: `Extract all information from this receipt and format as JSON:
        {
          "merchant_name": "...",
          "date": "YYYY-MM-DD",
          "items": [{"name": "...", "quantity": 1, "price": 0.00}],
          "subtotal": 0.00,
          "tax": 0.00,
          "total": 0.00,
          "payment_method": "..."
        }` 
      },
      {
        type: "image_url",
        image_url: { url: "https://docs.cci.prem.io/docs/images/examples/invoice.png" },
      },
    ],
  }],
  response_format: { type: "json_object" },
});

const data = JSON.parse(response.choices[0].message.content || "{}");
console.log(data);

​
Product Catalog Automation

Generate structured product information from images: 
const response = await client.chat.completions.create({
  model: "OpenGVLab/InternVL3-38B",
  messages: [{
    role: "user",
    content: [
      { 
        type: "text", 
        text: `Analyze this product image and generate catalog data in JSON:
        {
          "product_category": "...",
          "attributes": {"color": "...", "material": "...", "style": "..."},
          "target_audience": "...",
          "suggested_tags": ["...", "..."],
          "description": "..."
        }` 
      },
      {
        type: "image_url",
        image_url: { url: "https://docs.cci.prem.io/docs/images/examples/tshirt.png" },
      },
    ],
  }],
  response_format: { type: "json_object" },
});

const data = JSON.parse(response.choices[0].message.content || "{}");
console.log(data);

​
Image-Based Question Answering

Ask specific questions about any image: 
import fs from "fs";

const imagePath = "./scene.jpg";
const base64Image = fs.readFileSync(imagePath, "base64");

const response = await client.chat.completions.create({
  model: "OpenGVLab/InternVL3-38B",
  messages: [{
    role: "user",
    content: [
      { 
        type: "text", 
        text: "How many people are in this image and what are they doing?" 
      },
      {
        type: "image_url",
        image_url: { url: `data:image/jpeg;base64,${base64Image}` },
      },
    ],
  }],
});

console.log(response.choices[0].message.content);

​
Multi-Image Comparison Analysis

Compare multiple images for quality control or change detection: 
const response = await client.chat.completions.create({
  model: "OpenGVLab/InternVL3-38B",
  messages: [{
    role: "user",
    content: [
      { 
        type: "text", 
        text: "Compare these before/after images and identify all changes." 
      },
      {
        type: "image_url",
        image_url: { url: "https://docs.cci.prem.io/docs/images/examples/before.png" },
      },
      {
        type: "image_url",
        image_url: { url: "https://docs.cci.prem.io/docs/images/examples/after.png" },
      },
    ],
  }],
});

console.log(response.choices[0].message.content);

​
Streaming Vision Analysis

Stream responses for real-time creative content generation: 
const stream = await client.chat.completions.create({
  model: "OpenGVLab/InternVL3-38B",
  messages: [{
    role: "user",
    content: [
      { 
        type: "text", 
        text: "Create an engaging social media caption for this image" 
      },
      {
        type: "image_url",
        image_url: { url: "https://example.com/image.jpg" },
      },
    ],
  }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}