Edu SDKextractContent
Extract text from PDF, plain text, or markdown file bytes.
Turns file bytes into text you can inspect, cache, or pass into generators. The SDK does not host uploads — your app still handles <input type="file">, multipart routes, and storage. Pass the resulting bytes here (or straight into create* as content).
Usage
import { extractContent, createQuiz } from "edu-sdk";
import { readFile } from "node:fs/promises";
const data = await readFile("./lecture.pdf");
const extracted = await extractContent({
type: "file",
data,
mimeType: "application/pdf",
filename: "lecture.pdf",
});
console.log(extracted.text, extracted.pageCount);
const quiz = await createQuiz({
model: "google/gemini-3.6-flash",
content: extracted.text,
count: 10,
});Or skip the helper and pass a file into a generator:
const quiz = await createQuiz({
model: "google/gemini-3.6-flash",
content: {
type: "file",
data,
mimeType: "application/pdf",
filename: "lecture.pdf",
},
count: 10,
});From an upload route:
const file = formData.get("file") as File;
const data = new Uint8Array(await file.arrayBuffer());
await createQuiz({
model: "google/gemini-3.6-flash",
content: {
type: "file",
data,
mimeType: file.type || "application/octet-stream",
filename: file.name,
},
count: 10,
});Options
| Field | Type | Required | Notes |
|---|---|---|---|
type | "file" | Yes | Discriminator |
data | Uint8Array | ArrayBuffer | Yes | Node Buffer works (it is a Uint8Array) |
mimeType | string | Yes | See supported types |
filename | string | No | Used as a fallback when mimeType is unknown (e.g. application/octet-stream) |
Supported types (v1)
| MIME | Filename fallback |
|---|---|
application/pdf | .pdf |
text/plain | .txt |
text/markdown | .md, .markdown |
Text-based PDFs only. Scanned/image PDFs without OCR are not supported and throw if no text is extracted.
Returns
{
text: string;
mimeType: string;
filename?: string;
pageCount?: number; // PDF only
}Errors
| Error | When |
|---|---|
UnsupportedContentError | Unknown MIME and no usable filename extension |
ContentExtractionError | Empty bytes, empty extracted text, or PDF parse failure |
InvalidInputError | Malformed FileContent (missing type, bad data, empty mimeType) |
All extend EduSDKError.
See also Working with files for upload patterns and when to extract vs pass a file through.