NuExtract3

by numind

Template-driven structured extraction from documents and images (VLM)

10Kdl/month

~4B (Qwen3.5-4B base)params

HuggingFace Run on your data, free

Identifiers

Model ID

numind/NuExtract3

Feature URI

mixpeek://document_extractor@v1/numind_nuextract3_v1

Overview

NuExtract 3 turns a vision-language model (built on Qwen3.5-4B) into a structured-extraction engine. Instead of returning free text, you hand it a schema — a JSON template describing the fields you want — and it fills that template from the input, whether the input is plain text or a document *image*. Because it sees the page, it reads scanned PDFs, invoices, forms, and screenshots directly, with no separate OCR stage, and it can also emit clean document-to-markdown.

On Mixpeek, NuExtract 3 is the extraction step that converts messy documents into queryable structured records — pull line items, dates, parties, and amounts into typed fields, then filter and search them like any other metadata.

Architecture

Vision-language model fine-tuned from Qwen3.5-4B (~4B params) for template-conditioned extraction. Takes an image or text plus a JSON schema/example and generates the populated structure, with light reasoning before committing values. Multilingual; handles document images at native resolution (inherited from the Qwen vision encoder), so layout and figures are read directly rather than flattened to a text dump.

Mixpeek SDK Integration

import { Mixpeek } from "mixpeek";

const mx = new Mixpeek({ apiKey: "API_KEY" });

// Extract structured fields from document images at ingest
const collection = await mx.collections.create({
  namespace_id: "my-namespace",
  collection_name: "invoices",
  source: { type: "bucket", bucket_ids: ["bkt_your_bucket"] },
  feature_extractor: {
    feature_extractor_name: "structured_extraction",
    version: "v1",
    parameters: { model_id: "numind/NuExtract3" },
  },
});

Capabilities

Schema/template-driven extraction — you define the fields, it fills them
Reads document images directly (scanned PDFs, invoices, forms) — no separate OCR step
Document-to-markdown conversion for clean downstream chunking
Multilingual extraction with reasoning before value assignment
Open weights (Apache-2.0), self-hostable