{"type":"error","code":"deploymentFailed","ctx":"The deployment failed: UNCAUGHT_EXCEPTION\n\nError: This API is not supported in this environment\n    at Object.Module._extensions..node (node:module:790:21)\n    at Module.load (node:module:655:32)\n    at Function.Module._load (node:module:523:13)\n    at Module.require (node:module:674:19)\n    at require (node:module:801:16)\n    at Object.<anonymous> (file:///node_modules/.deno/[email protected]/node_modules/onnxruntime-node/dist/binding.js:9:1)\n    at Object.<anonymous> (file:///node_modules/.deno/[email protected]/node_modules/onnxruntime-node/dist/binding.js:11:4)\n    at Module._compile (node:module:736:34)\n    at Object.Module._extensions..js (node:module:757:11)\n    at Module.load (node:module:655:32)"}

const quantized = false; // change to `true` for a much smaller model (e.g. 87mb vs 345mb for image model), but lower accuracy
import {
  AutoProcessor,
  CLIPVisionModelWithProjection,
  RawImage,
  AutoTokenizer,
  CLIPTextModelWithProjection,
} from "npm:@huggingface/transformers";

const imageProcessor = await AutoProcessor.from_pretrained(
  "Xenova/clip-vit-base-patch16"
);
const visionModel = await CLIPVisionModelWithProjection.from_pretrained(
  "Xenova/clip-vit-base-patch16",
  { quantized }
);
const tokenizer = await AutoTokenizer.from_pretrained(
  "Xenova/clip-vit-base-patch16"
);
const textModel = await CLIPTextModelWithProjection.from_pretrained(
  "Xenova/clip-vit-base-patch16",
  { quantized }
);

function cosineSimilarity(A: number[], B: number[]) {
  if (A.length !== B.length) throw new Error("A.length !== B.length");
  let dotProduct = 0,
    mA = 0,
    mB = 0;
  for (let i = 0; i < A.length; i++) {
    dotProduct += A[i] * B[i];
    mA += A[i] * A[i];
    mB += B[i] * B[i];
  }
  mA = Math.sqrt(mA);
  mB = Math.sqrt(mB);
  const similarity = dotProduct / (mA * mB);
  return similarity;
}

export async function getImageEmbedding(imageLocation: string) {
  const image = await RawImage.read(imageLocation);
  const imageInputs = await imageProcessor(image);
  const { image_embeds } = await visionModel(imageInputs);
  // console.log(image_embeds.data);
  return image_embeds.data;
}

Deno.serve(async () => {
  const embed = await getImageEmbedding("./image.png");
  console.log(embed);
  console.log(embed.length);
  return new Response(JSON.stringify(embed));
});