fanyubo
feat(kb): HF Space KB Worker — 解析/分块/向量化/标签/质量审核
142ad12
Raw
History Blame Contribute Delete
298 Bytes
// hf-space/src/lib/knowledge/parser/pdf.ts
import pdf from 'pdf-parse';
import type { ParsedDocument } from './index';
export async function parsePDF(buffer: Buffer): Promise<ParsedDocument> {
const data = await pdf(buffer);
return {
content: data.text,
pages: data.numpages,
};
}