Pictograph
Build computer-vision datasets and train models from Python, the CLI, or an agent.
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 Client
from pictograph.workflows import full_pipeline
client = Client()
report = full_pipeline(
client,
dataset_name="road-signs",
folder="./road_signs",
classes=[("stop_sign", "bbox"), ("yield", "bbox")],
pipeline="yolox",
)
print("model:", report.model.id if report.success else "see report")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 YOLOX, Detectron2, SM-PyTorch, RF-DETR, or classification models on A10G / A100 / H100 GPUs.
- Export to COCO, YOLO, CVAT, Pascal VOC, LabelMe, CSV, or Pictograph JSON.
- Import existing datasets from V7 (Darwin) or Roboflow.
- Search by visual similarity (SigLIP2) or auto-generated content tags.
- 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 · Quickstart · Authentication |
| Workflows | Full pipeline · Upload · Auto-annotate · Train |
| API Reference | Overview · Datasets · Images · Annotations · Auto-annotate · Search · Batch · Exports · Training · Models · Credits · Connectors · Video · Organizations · Projects · API Keys · Tools |
| Agents | Overview · Claude · OpenAI · Dynamic discovery · Cookbook |
| Reference | Annotation format · Error handling · Rate limits · CLI |
Every page has a “Copy as Markdown” button and an .md mirror for agents to consume directly.
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