genkitx-mistral/lib/ocr.js

Firebase Genkit AI framework plugin for Mistral AI APIs.

"use strict";
var __defProp = Object.defineProperty;
var __defProps = Object.defineProperties;
var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
var __getOwnPropDescs = Object.getOwnPropertyDescriptors;
var __getOwnPropNames = Object.getOwnPropertyNames;
var __getOwnPropSymbols = Object.getOwnPropertySymbols;
var __hasOwnProp = Object.prototype.hasOwnProperty;
var __propIsEnum = Object.prototype.propertyIsEnumerable;
var __defNormalProp = (obj, key, value) => key in obj ? __defProp(obj, key, { enumerable: true, configurable: true, writable: true, value }) : obj[key] = value;
var __spreadValues = (a, b) => {
  for (var prop in b || (b = {}))
    if (__hasOwnProp.call(b, prop))
      __defNormalProp(a, prop, b[prop]);
  if (__getOwnPropSymbols)
    for (var prop of __getOwnPropSymbols(b)) {
      if (__propIsEnum.call(b, prop))
        __defNormalProp(a, prop, b[prop]);
    }
  return a;
};
var __spreadProps = (a, b) => __defProps(a, __getOwnPropDescs(b));
var __export = (target, all) => {
  for (var name in all)
    __defProp(target, name, { get: all[name], enumerable: true });
};
var __copyProps = (to, from, except, desc) => {
  if (from && typeof from === "object" || typeof from === "function") {
    for (let key of __getOwnPropNames(from))
      if (!__hasOwnProp.call(to, key) && key !== except)
        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
  }
  return to;
};
var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
var __async = (__this, __arguments, generator) => {
  return new Promise((resolve, reject) => {
    var fulfilled = (value) => {
      try {
        step(generator.next(value));
      } catch (e) {
        reject(e);
      }
    };
    var rejected = (value) => {
      try {
        step(generator.throw(value));
      } catch (e) {
        reject(e);
      }
    };
    var step = (x) => x.done ? resolve(x.value) : Promise.resolve(x.value).then(fulfilled, rejected);
    step((generator = generator.apply(__this, __arguments)).next());
  });
};
var ocr_exports = {};
__export(ocr_exports, {
  OCRModel: () => OCRModel,
  ocr: () => ocr
});
module.exports = __toCommonJS(ocr_exports);
var import_genkit = require("genkit");
var import_model = require("genkit/model");
const ImageURLSchema = import_genkit.z.object({
  url: import_genkit.z.string(),
  detail: import_genkit.z.string().nullable().optional()
});
const OCRSchema = import_genkit.GenerationCommonConfigSchema.extend({
  document: import_genkit.z.object({
    type: import_genkit.z.enum(["document_url", "image_url"]).optional(),
    documentUrl: import_genkit.z.string(),
    documentName: import_genkit.z.string().nullable().optional(),
    imageUrl: import_genkit.z.union([import_genkit.z.string(), ImageURLSchema]).optional()
  })
});
const ocr = (0, import_model.modelRef)({
  name: "mistral/ocr",
  info: {
    versions: ["mistral-ocr-latest"],
    label: "Mistral - OCR",
    supports: {
      media: false,
      output: ["text", "json"],
      multiturn: false,
      systemRole: false,
      tools: false
    }
  },
  configSchema: OCRSchema
});
function toOCRRequest(request) {
  var _a, _b, _c, _d, _e, _f, _g, _h, _i, _j, _k;
  const docType = ((_b = (_a = request.config) == null ? void 0 : _a.document) == null ? void 0 : _b.type) || "document_url";
  const options = {
    model: "mistral-ocr-latest",
    document: docType === "document_url" ? {
      type: "document_url",
      documentUrl: ((_d = (_c = request.config) == null ? void 0 : _c.document) == null ? void 0 : _d.documentUrl) || "",
      documentName: ((_f = (_e = request.config) == null ? void 0 : _e.document) == null ? void 0 : _f.documentName) || null
    } : {
      type: "image_url",
      imageUrl: typeof ((_h = (_g = request.config) == null ? void 0 : _g.document) == null ? void 0 : _h.imageUrl) === "string" ? request.config.document.imageUrl : ((_k = (_j = (_i = request.config) == null ? void 0 : _i.document) == null ? void 0 : _j.imageUrl) == null ? void 0 : _k.url) || ""
    }
  };
  Object.keys(options).forEach((k) => {
    if (options[k] === void 0) {
      delete options[k];
    }
  });
  return options;
}
function toGenerateResponse(result) {
  const candidates = result.pages.map(
    (page, index) => ({
      index,
      finishReason: "stop",
      message: {
        role: "model",
        content: [
          {
            text: page.markdown
          },
          ...page.images.map((image) => ({
            media: {
              contentType: "image/png",
              url: `data:image/png;base64,${image.imageBase64}`
            }
          }))
        ]
      }
    })
  );
  return { candidates };
}
function OCRModel(ai, client) {
  return ai.defineModel(
    __spreadProps(__spreadValues({
      name: ocr.name
    }, ocr.info), {
      configSchema: ocr.configSchema
    }),
    (request) => __async(this, null, function* () {
      const result = yield client.ocr.process(toOCRRequest(request));
      return toGenerateResponse(result);
    })
  );
}
// Annotate the CommonJS export names for ESM import in node:
0 && (module.exports = {
  OCRModel,
  ocr
});
//# sourceMappingURL=ocr.js.map