chonkie
Version:
🦛 CHONK your texts in TS with Chonkie!✨The no-nonsense lightweight and efficient chunking library.
130 lines • 6.34 kB
JavaScript
;
/** Semantic chunker client for Chonkie API. */
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
var desc = Object.getOwnPropertyDescriptor(m, k);
if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
desc = { enumerable: true, get: function() { return m[k]; } };
}
Object.defineProperty(o, k2, desc);
}) : (function(o, m, k, k2) {
if (k2 === undefined) k2 = k;
o[k2] = m[k];
}));
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
Object.defineProperty(o, "default", { enumerable: true, value: v });
}) : function(o, v) {
o["default"] = v;
});
var __importStar = (this && this.__importStar) || (function () {
var ownKeys = function(o) {
ownKeys = Object.getOwnPropertyNames || function (o) {
var ar = [];
for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
return ar;
};
return ownKeys(o);
};
return function (mod) {
if (mod && mod.__esModule) return mod;
var result = {};
if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
__setModuleDefault(result, mod);
return result;
};
})();
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
return new (P || (P = Promise))(function (resolve, reject) {
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
step((generator = generator.apply(thisArg, _arguments || [])).next());
});
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.SemanticChunker = void 0;
const base_1 = require("./base");
const semantic_1 = require("../types/semantic");
const fs = __importStar(require("fs"));
const path = __importStar(require("path"));
class SemanticChunker extends base_1.CloudClient {
constructor(apiKey, config = {}) {
var _a, _b;
super({ apiKey });
this.config = {
embeddingModel: config.embeddingModel || "minishlab/potion-base-8M",
threshold: (_a = config.threshold) !== null && _a !== void 0 ? _a : "auto",
chunkSize: config.chunkSize || 512,
similarityWindow: config.similarityWindow || 1,
minSentences: config.minSentences || 1,
minChunkSize: config.minChunkSize || 2,
minCharactersPerSentence: config.minCharactersPerSentence || 12,
thresholdStep: config.thresholdStep || 0.01,
delim: config.delim || [".", "!", "?", "\n"],
includeDelim: (_b = config.includeDelim) !== null && _b !== void 0 ? _b : "prev",
};
}
chunk(input) {
return __awaiter(this, void 0, void 0, function* () {
const formData = new FormData();
if (input.filepath) {
const fileContent = fs.readFileSync(input.filepath);
const fileName = path.basename(input.filepath) || 'file.txt';
formData.append("file", new Blob([fileContent]), fileName);
}
else if (input.text) {
// JSON encode the text
formData.append("text", JSON.stringify(input.text));
// Append empty file to ensure multipart form
formData.append("file", new Blob(), "text_input.txt");
}
else {
throw new Error("Either text or filepath must be provided");
}
// Add all config options to the form data
formData.append("embedding_model", this.config.embeddingModel);
formData.append("threshold", this.config.threshold.toString());
formData.append("chunk_size", this.config.chunkSize.toString());
formData.append("similarity_window", this.config.similarityWindow.toString());
formData.append("min_sentences", this.config.minSentences.toString());
formData.append("min_chunk_size", this.config.minChunkSize.toString());
formData.append("min_characters_per_sentence", this.config.minCharactersPerSentence.toString());
formData.append("threshold_step", this.config.thresholdStep.toString());
formData.append("delim", JSON.stringify(this.config.delim));
formData.append("include_delim", this.config.includeDelim || "prev");
formData.append("return_type", "chunks");
const data = yield this.request("/v1/chunk/semantic", {
method: "POST",
body: formData,
});
// Convert from snake_case to camelCase
const camelCaseData = data.map((chunk) => {
return {
text: chunk.text,
startIndex: chunk.start_index,
endIndex: chunk.end_index,
tokenCount: chunk.token_count,
embedding: chunk.embedding || undefined,
sentences: chunk.sentences.map((sentence) => {
return {
text: sentence.text,
startIndex: sentence.start_index,
endIndex: sentence.end_index,
tokenCount: sentence.token_count,
embedding: sentence.embedding || undefined,
};
}),
};
});
return camelCaseData.map((chunk) => semantic_1.SemanticChunk.fromDict(chunk));
});
}
chunkBatch(inputs) {
return __awaiter(this, void 0, void 0, function* () {
return Promise.all(inputs.map(input => this.chunk(input)));
});
}
}
exports.SemanticChunker = SemanticChunker;
//# sourceMappingURL=semantic.js.map