Build retail agents with open source models

Superlinked gives your agent one API to inspect shelf photos, read shelf labels and return cited stock checks.

Get started

Humans in the Loop shelf dataset · CC0

Agent finding Panadol Children 5–12 Years Elixir, 100 mL See how one shelf photo became a stock check

Your shelf-replenishment agent

Review the shelf, identify the facing and return evidence.

Shelf photo Photo 042 · pharmacy aisle

Stock check Check Panadol Children 5–12 Years Elixir, 100 mL

Your store context

The product and inventory records your agent checks before it acts.

PLAN Planogram Expected facings

LABEL Shelf labels SKU and price

CATALOG Product catalog Pack and variant

STOCK Inventory feed Store and backroom

Browse all tasks

from pathlib import Path
from sie_sdk import SIEClient
client = SIEClient(
    api_key="API keysk-sie-…",
    base_url="https://api.superlinked.com",
)
image = {"data": Path(imagepharmacy-shelf.jpgbrowse).read_bytes(), "format": "jpeg"}
result = client.extract(
    "modelIDEA-Research/grounding-dino-base",
    {"images": [image]},
    labels=[
        "labelempty shelf space",
        "labelout of stock sign",
        "labelprice tag",
    ],
)
for obj in result["objects"]:
    print(obj["label"], obj["score"], obj["bbox"])

import { readFile } from 'node:fs/promises';
import { SIEClient } from '@superlinked/sie-sdk';

const client = new SIEClient('https://api.superlinked.com', {
  apiKey: 'sk-sie-…',
});

const image = await readFile("pharmacy-shelf.jpg");
const result = await client.extract(
  'IDEA-Research/grounding-dino-base',
  { images: [image] },
  { labels: ["empty shelf space","out of stock sign","price tag"] },
);
console.log(result.objects);

images_bytes=$(base64 < 'pharmacy-shelf.jpg' | tr -d '\n')
curl https://api.superlinked.com/v1/extract/IDEA-Research%2Fgrounding-dino-base \
  -H "Authorization: Bearer sk-sie-…" \
  -H "Content-Type: application/json" \
  -d "{\"items\":[{\"images\":[{\"data\":\"$images_bytes\",\"format\":\"jpeg\"}]}],\"params\":{\"labels\":[\"empty shelf space\",\"out of stock sign\",\"price tag\"]}}"

Build the "Detect" capability into my app using the Superlinked Inference Engine (SIE).

Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: IDEA-Research/grounding-dino-base (SIE primitive: /extract). Keep the model id configurable.

Task
- Input: an uploaded image plus the object labels to find.
- Behaviour: return the named objects with confidence scores and bounding boxes
- Call the selected SIE primitive once per request and map the response into your domain type.

Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.

Run

from pathlib import Path
from sie_sdk import SIEClient
client = SIEClient(
    api_key="API keysk-sie-…",
    base_url="https://api.superlinked.com",
)
image = {"data": Path(imagepharmacy-oos-sign.jpgbrowse).read_bytes(), "format": "jpeg"}
result = client.extract(
    "modellightonai/LightOnOCR-2-1B",
    {"images": [image]},
)
print(result["entities"][0]["text"])

import { readFile } from 'node:fs/promises';
import { SIEClient } from '@superlinked/sie-sdk';

const client = new SIEClient('https://api.superlinked.com', {
  apiKey: 'sk-sie-…',
});

const image = await readFile("pharmacy-oos-sign.jpg");
const result = await client.extract(
  'lightonai/LightOnOCR-2-1B',
  { images: [image] },
  { labels: [] },
);
console.log(result.entities[0].text);

images_bytes=$(base64 < 'pharmacy-oos-sign.jpg' | tr -d '\n')
curl https://api.superlinked.com/v1/extract/lightonai%2FLightOnOCR-2-1B \
  -H "Authorization: Bearer sk-sie-…" \
  -H "Content-Type: application/json" \
  -d "{\"items\":[{\"images\":[{\"data\":\"$images_bytes\",\"format\":\"jpeg\"}]}]}"

Build the "OCR" capability into my app using the Superlinked Inference Engine (SIE).

Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: lightonai/LightOnOCR-2-1B (SIE primitive: /extract). Keep the model id configurable.

Task
- Input: an uploaded image containing text.
- Behaviour: return the text visible in the image
- Call the selected SIE primitive once per request and map the response into your domain type.

Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.

Run

Output

empty shelf space0.26[2043, 2137, 2666, 2540]

1 objects with bounding boxes

Finds the objects you name
Returns a confidence score for each match

Output

Source pharmacy-oos-sign.jpg — source · pharmacy-oos-sign.jpg

I am temporarily

out-of-stock

from our supplier

Please ask our friendly staff

for a substitute.

[name redacted]

Reads text directly from images and photos

PRICE

$ / 1k images $ / 1M input tokens $ / 1M output tokens ↓

$0.232 SIE OWLv2 Base

$0.309 SIE Grounding DINO

AWS Rekognition $1

Google Vision Labels $1.5

Google Vision Objects $2.25

OpenAI GPT-5.4 mini $0.75

OpenAI GPT-5.4 mini $4.5

QUALITY

AP · COCO ↑

SIE Grounding DINO 0.58

0.56

0.55

SIE OWLv2 Base 0.43

0.42

0.41

LATENCY

p50 ms ↓

SIE Grounding DINO 786ms

900ms

950ms

SIE OWLv2 Base 1008ms

1120ms

1180ms

PRICE

$ / 1k pages ↓

$1.5 AWS Textract

$1.5 Google Enterprise Document OCR

$1.5 Azure Document Intelligence Read

$1.86 SIE docling OCR

SIE LightOnOCR 2 1B $2

Mistral OCR 4 $4

QUALITY

Accuracy · olmOCR ↑

SIE LightOnOCR 2 1B 0.78

0.75

0.74

0.33 SIE docling OCR

0.32

0.31

LATENCY

p50 ms ↓

320ms SIE docling OCR

360ms

390ms

SIE LightOnOCR 2 1B 600ms

680ms

720ms

Your agent identifies the SKU behind the shelf gap

View on GitHub

Localize the empty facing Grounding DINO base

Pharmacy shelf with an empty Panadol facing, an out-of-stock sign and a shelf label

Read the sign and label LightOnOCR-2-1B

Close crop of the pharmacy out-of-stock sign — I am temporarily out-of-stock from our supplier

Close crop of the Panadol shelf label below the empty facing — `Panadol Child · 5-12Yrs Elixir 100ml · 101760 · 10⁹⁹`

Your agent returns the stock check

Product: Panadol Children 5–12 Years Elixir, 100 mL
SKU: 101760
State: Supplier stockout
Evidence: Detection box + OCR crops
Next check: Verify on-hand stock and replenishment ETA

Deploy your way

Managed Cloud

Full compute toolkit for your agents with zero ops.

No idle GPUs, pay for what you use
Fits your stack: SDK, API, CLI, MCP
Zero lock-in, self-host the same stack
SOC 2 Type 2, US or EU data residency

$50 Example credit balance

1.3B tokens embedded

120k pages parsed

27M tokens generated (1:1 in:out)

Get started

no credit card required

Self-host with K8s

Easy & scalable deployment in your own cloud.

Terraform to your cloud in minutes
Apache-2.0, same engine as Cloud
Scales to zero, no bill between jobs
Per-tenant pools, no noisy neighbors

Agent prompt

Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our GCP project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our Azure AKS cluster via helm install. Requirements: superlinked.com/docs/deployment

Deploy guide

Run locally

Run the same models on your own machine.

Runs on NVIDIA GPU or Apple Silicon
One command, no Docker or cluster
All 100+ Cloud models, fully offline
Same SDK and IDs, no code changes

pip install "sie-server[local]" && sie-server servepip install "sie-server[local]" && sie-server serve --device cuda

Quickstart

Compare models for this task

Your agent identifies the SKU behind the shelf gap

Deploy your way