feat: add Phase 4 AI tools with Python bridge and 6 new tools

Add Python bridge (packages/ai/src/bridge.ts) that calls Python scripts
via child_process with venv-first fallback to system python3. Implements
6 AI-powered tools:

- Remove Background: rembg-based with U2-Net/IS-Net models
- Image Upscaling: Real-ESRGAN with Lanczos fallback
- OCR/Text Extraction: Tesseract + PaddleOCR engines
- Face/PII Blur: MediaPipe face detection with configurable blur
- Object Eraser: LaMa inpainting with mask-based input
- Smart Crop: Sharp attention-based entropy cropping (no Python needed)

Each tool includes: Python script, TypeScript wrapper, API route,
and React settings component. All Python scripts handle ImportError
gracefully with clear installation messages.
This commit is contained in:
Siddharth Kumar Sah
2026-03-22 04:31:49 +08:00
parent a8cc611eb2
commit 5524939b6f
30 changed files with 1880 additions and 2 deletions
+68
View File
@@ -0,0 +1,68 @@
import type { FastifyInstance, FastifyRequest, FastifyReply } from "fastify";
import { randomUUID } from "node:crypto";
import { basename } from "node:path";
import { extractText } from "@stirling-image/ai";
import { createWorkspace } from "../../lib/workspace.js";
/**
* OCR / text extraction route.
* Returns JSON with extracted text rather than an image.
*/
export function registerOcr(app: FastifyInstance) {
app.post(
"/api/v1/tools/ocr",
async (request: FastifyRequest, reply: FastifyReply) => {
let fileBuffer: Buffer | null = null;
let filename = "image";
let settingsRaw: string | null = null;
try {
const parts = request.parts();
for await (const part of parts) {
if (part.type === "file") {
const chunks: Buffer[] = [];
for await (const chunk of part.file) {
chunks.push(chunk);
}
fileBuffer = Buffer.concat(chunks);
filename = basename(part.filename ?? "image");
} else if (part.fieldname === "settings") {
settingsRaw = part.value as string;
}
}
} catch (err) {
return reply.status(400).send({
error: "Failed to parse multipart request",
details: err instanceof Error ? err.message : String(err),
});
}
if (!fileBuffer || fileBuffer.length === 0) {
return reply.status(400).send({ error: "No image file provided" });
}
try {
const settings = settingsRaw ? JSON.parse(settingsRaw) : {};
const jobId = randomUUID();
const workspacePath = await createWorkspace(jobId);
const result = await extractText(fileBuffer, workspacePath, {
engine: settings.engine,
language: settings.language,
});
return reply.send({
jobId,
filename,
text: result.text,
engine: result.engine,
});
} catch (err) {
return reply.status(422).send({
error: "OCR failed",
details: err instanceof Error ? err.message : "Unknown error",
});
}
},
);
}