Overview
Pictograph developer docs. Annotate images with SAM3, train detection and segmentation models, and deploy inference APIs from a typed Python SDK, CLI, and REST API.
Pictograph turns directories of images into trained CV models with as little hand-annotation as possible. The same REST API drives three surfaces: a typed Python SDK, a CLI, and an agent toolkit for Claude and OpenAI.
from pictograph import get_model, DetectionModel, DetectionResult
model: DetectionModel = get_model(name="Road Signs", task="object_detection")
result: DetectionResult = model.predict(
image="photo.jpg",
)
for p in result.predictions:
print(p.name, round(p.confidence, 2), p.bounding_box)What you can do
- Upload directories of images; subdirectories become virtual paths.
- Auto-annotate with SAM3 - point, box, or text prompts, single image or async batch.
- Train detection (YOLOX, RF-DETR), segmentation (instance and semantic), keypoint, and classification models on managed GPUs.
- Export to 12 formats - COCO, YOLO (incl. OBB and pose), DOTA, Darwin V7, Pascal VOC, CVAT, Datumaro, LabelMe, CSV, or Pictograph JSON.
- Import existing datasets from V7 (Darwin) or Roboflow.
- Search by visual similarity or auto-generated content tags.
- Run locally with Pictograph’s own tooling - export to any of 12 formats, feed a PyTorch training loop, run trained models locally, and draw annotations, no server round-trip.
- Drive everything from agents - Claude Agent SDK, openai-agents, Vercel AI SDK, LangChain, or any framework that speaks JSON Schema.
Map of the docs
| Section | Pages |
|---|---|
| Get Started | Installation · Quick start · Authentication · Local inference |
| Guides | Overview · Upload images · SAM3 auto-annotation · Tile & augment · Train · Deployments · Export & conversion · Local inference |
| API Reference | Overview · Datasets · Images · Annotations · Auto-annotate · Search · Batch · Exports · Training · Models · Deployments API · Workflows API · Webhooks · Credits · Connectors · Video · Organizations · Directories · API keys · Tools |
| Agents | Overview · Claude · OpenAI · Dynamic discovery · Cookbook |
| Reference | Error handling · Annotation format · CLI · Async client · Rate limits |
Every page has a “Copy as Markdown” button and an .md mirror for agents to consume directly. Documented methods link to the code that implements them, pinned to the released tag.
For agents browsing this site
- Site index:
/docs/llms.txt - Full doc bundle (one file):
/docs/llms-full.txt - Tool registry (JSON Schema):
/api/v1/developer/tools.json - SDK source:
pictograph-io/pictograph-sdk