@genkit-ai/ai
Version:
Genkit AI framework generative AI APIs.
159 lines • 4.6 kB
JavaScript
;
var __defProp = Object.defineProperty;
var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
var __getOwnPropNames = Object.getOwnPropertyNames;
var __hasOwnProp = Object.prototype.hasOwnProperty;
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 document_exports = {};
__export(document_exports, {
Document: () => Document,
DocumentDataSchema: () => DocumentDataSchema,
checkUniqueDocuments: () => checkUniqueDocuments
});
module.exports = __toCommonJS(document_exports);
var import_core = require("@genkit-ai/core");
var import_parts = require("./parts.js");
const DocumentDataSchema = import_core.z.object({
content: import_core.z.array(import_parts.PartSchema),
metadata: import_core.z.record(import_core.z.string(), import_core.z.any()).optional()
});
function deepCopy(value) {
if (value === void 0) {
return value;
}
return JSON.parse(JSON.stringify(value));
}
class Document {
content;
metadata;
constructor(data) {
this.content = deepCopy(data.content);
this.metadata = deepCopy(data.metadata);
}
static fromText(text, metadata) {
return new Document({
content: [{ text }],
metadata
});
}
// Construct a Document from a single media item
static fromMedia(url, contentType, metadata) {
return new Document({
content: [
{
media: {
contentType,
url
}
}
],
metadata
});
}
// Construct a Document from content
static fromData(data, dataType, metadata) {
if (dataType === "text") {
return this.fromText(data, metadata);
}
return this.fromMedia(data, dataType, metadata);
}
/**
* Concatenates all `text` parts present in the document with no delimiter.
* @returns A string of all concatenated text parts.
*/
get text() {
return this.content.map((part) => part.text || "").join("");
}
/**
* Media array getter.
* @returns the array of media parts.
*/
get media() {
return this.content.filter((part) => part.media && !part.text).map((part) => part.media);
}
/**
* Gets the first item in the document. Either text or media url.
*/
get data() {
if (this.text) {
return this.text;
}
if (this.media) {
return this.media[0].url;
}
return "";
}
/**
* Gets the contentType of the data that is returned by data()
*/
get dataType() {
if (this.text) {
return "text";
}
if (this.media && this.media[0].contentType) {
return this.media[0].contentType;
}
return void 0;
}
toJSON() {
return {
content: deepCopy(this.content),
metadata: deepCopy(this.metadata)
};
}
/**
* Embedders may return multiple embeddings for a single document.
* But storage still requires a 1:1 relationship. So we create an
* array of Documents from a single document - one per embedding.
* @param embeddings The embeddings to create the documents from.
* @returns an array of documents based on this document and the embeddings.
*/
getEmbeddingDocuments(embeddings) {
const documents = [];
for (const embedding of embeddings) {
const jsonDoc = this.toJSON();
if (embedding.metadata) {
if (!jsonDoc.metadata) {
jsonDoc.metadata = {};
}
jsonDoc.metadata.embedMetadata = embedding.metadata;
}
documents.push(new Document(jsonDoc));
}
checkUniqueDocuments(documents);
return documents;
}
}
function checkUniqueDocuments(documents) {
const seen = /* @__PURE__ */ new Set();
for (const doc of documents) {
const serialized = JSON.stringify(doc);
if (seen.has(serialized)) {
console.warn(
"Warning: embedding documents are not unique. Are you missing embed metadata?"
);
return false;
}
seen.add(serialized);
}
return true;
}
// Annotate the CommonJS export names for ESM import in node:
0 && (module.exports = {
Document,
DocumentDataSchema,
checkUniqueDocuments
});
//# sourceMappingURL=document.js.map